Latest Articles

Articles in press have been peer-reviewed and accepted, which are not yet assigned to volumes/issues, but are citable by Digital Object Identifier (DOI).
Display Method:
A Computational Offloading Incentive Forward Contract Taking into Account Risk Appetite
ZHANG Biling, JIAO Zhengyang, LIU Jiahua, GUO Caili
Available online  , doi: 10.11999/JEIT230617
In edge computing networks, to stimulate the Edge Computing Nodes (ECNs) to assist in computation offloading to relieve the pressure of computing Service Provider (SP), a forward transaction oriented incentive mechanism is studied. Considering that there is information asymmetry between SP and ECNs and the uncertainty of ECNs idle resources can lead to cooperation risks, a risk-aware forward incentive mechanism based on contract theory for computation offloading is proposed. Firstly, a risk preference model for nodes is established; and then the Individual Rationality (IR) constraints and Incentive Compatibility (IC) constraints are defined, and the incentive problem is modeled as a forward contract design problem to maximize the benefits of SP; finally, the optimal forward contract is derived after constraint simplification. The simulation results verify the feasibility and rationality of the proposed forward contract, and prove that the contract can effectively incentivize ECNs to participate in computation offloading and increase the profits of SP.
SDL PUF: A High Reliability Self-Adaption Deviation Locking PUF
ZHANG Yuan, LUO Jingru, ZHANG Jiliang
Available online  , doi: 10.11999/JEIT231313
As a novel hardware security primitive, Physical Unclonable Function (PUF) extracts process deviations to generate a unique response sequence, providing a root of trust for computing systems. However, existing PUFs based on Field Programmable Gate Arrays (FPGAs) cannot maintain high reliability over a wide range of temperatures and voltages. In this work, we propose a Self-Timed Ring (STR) based Self-adaption Deviation Locking PUF (SDL PUF). Firstly, the PUF response is generated utilizing the oscillation frequency difference caused by the STR delay. Secondly, the adaptive configuration in the initialization stage can effectively expand the deviation of the event arrival time in the STR, substantially enhancing the reliability of PUF. Then, a comparator obfuscation strategy is proposed, automatically configuring the comparator by extracting the process deviation to resist the side-channel attack. Finally, our proposed structure is implemented on a Xilinx Virtex-6 FPGA. Experimental results show that the proposed SDL PUF achieves 0 bit error rate in the temperature range of 0°C~80°C and the voltage range of 0.85~1.15V, and ensures 49.29% uniqueness and 49.84% uniformity while maintaining high reliability.
Key Technologies and Development Trends of Free Space Optical UAV Communication Network
FENG Simeng, ZHAO Yidi, DONG Chao, WU Qihui
Available online  , doi: 10.11999/JEIT230644
Considering the electromagnetic spectrum congestion and serious interference, the Free Space Optical (FSO)-based Unmanned Aerial Vehicle (UAV) communication network constitutes an important part for the space-air-ground integration, attracting substantial attention from both academia and industry. Compared to radio frequency communication, FSO communication is benefited from high data rate, low latency and high security. However, the FSO link is susceptible to atmospheric environment, while the mobile UAV dynamics topology and limited resources bring further challenges. Therefore, this paper first introduces the FSO transmission characteristics and then focuses on the key technologies to enhance stability and quality of FSO-based UAV networks. Furthermore, the development trend of FSO-based UAV network, in terms of high reliability, strong intelligence and long endurance is analyzed.
Advances in Privacy-Preserving Ciphertext Retrieval
CHI Jialin, FENG Dengguo, ZHANG Min, JIANG Haohao, WU Axin, SUN Tianqi
Available online  , doi: 10.11999/JEIT231300
The ciphertext retrieval techniques are designed to provide query services over encrypted data and to improve the availability of encrypted data. However, most of existing methods leak additional information besides the query result, which may be utilized by the attacker to recover plaintext data or queries. How to enhance the privacy-preserving features in ciphertext retrieval and achieve the minimisation of information leakage has received a lot of attention from researchers. In recent years, with the rapid development of hardware chip technology and new cryptographic technology, a number of novel methods were proposed for privacy-preserving ciphertext retrieval. This paper mainly focuses on the research hotspots of diversified ciphertext retrieval, ciphertext retrieval based on trusted execution environment and private information retrieval, and summarizes the future development trends.
A Review of High-Resolution Audio Sigma-Delta Modulator
SUN Aoyun, WEN Peixu, SHAO Huaixian, WANG Annan, LU Yi, ZHANG Biao, ZENG Yonghong, ZHANG Zhang
Available online  , doi: 10.11999/JEIT231208
Sigma-Delta (Σ-Δ) Analog-to-Digital Converter (ADC) is based on oversampling and noise shaping techniques to achieve high-resolution, and is characterized by low passive component matching requirements and simple structure. In high-resolution audio applications, Σ-Δ ADC has gained widespread attention and applications since it can achieve high dynamic range with good power efficiency. Recently, there has been a growing research trend in designing low-power, high-resolution audio ADCs using advanced processes and technologies. However, with process technology going to lower nodes and the reduction of supply voltages, the circuit design becomes more challenging. This paper reviews the state-of-the-art of the discrete-time and continuous-time design of high-resolution audio Sigma-Delta modulators, provides theoretical background for the design of high-resolution audio Sigma-Delta modulators, and gives research prospects.
Incremental Deep Learning for Remote Sensing Image Interpretation
WENG Xingxing, PANG Chao, XU Bowen, XIA Guisong
Available online  , doi: 10.11999/JEIT240172
The significant advancement of deep learning has facilitated the emergence of high-precision interpretation models for remote-sensing images. However, a notable drawback is that the majority of interpretation models are trained independently on static datasets, rendering them incapable of adapting to open environments and dynamic demands. This limitation poses a substantial obstacle to the widespread and long-term application of remote-sensing interpretation models. Incremental learning, empowering models to continuously learn new knowledge while retaining previous knowledge, has been recently utilized to drive the evolution of interpretation models and improve their performance. A comprehensive investigation of incremental learning methods for multi-modal remote sensing data and diverse interpretation tasks is provided in this paper. Existing research efforts are organized and reviewed in terms of mitigating catastrophic forgetting and facilitating interpretation model evolution. Drawing from this research progress, this study deliberates on the future research directions for incremental learning in remote sensing, with the aim of advancing research in model evolution for remote sensing image interpretation.
A Review of Neural Radiance Field Approaches for Scene Reconstruction of Satellite Remote Sensing Imagery
ZHOU Xin, WANG Yang, SUN Xian, LIN Daoyu, LIU Junyi, FU Kun
Available online  , doi: 10.11999/JEIT240202
High-resolution satellite remote sensing images have been recognized as an indispensable means for understanding geographical spaces, and their role in areas such as urban mapping, ecological monitoring, and navigation, has become increasingly important. The use of satellite remote sensing images for large-scale 3D reconstruction of the Earth’s surface is currently a subject of active research in the fields of computer vision and photogrammetry. Neural Radiance Fields (NeRF), which utilizes differentiable rendering to learn implicit representations of scenes, has achieved the most realistic visual effects in novel view synthesis tasks of complex scenes and has attracted significant attention in the field of 3D scene reconstruction and rendering. Recent research has been primarily focused on using neural radiance field technology to extract scene representation and reconstruction from satellite remote sensing images. Ray space optimization, scene representation optimization, and efficient model training are mainly focused on by the neural radiance field methods for satellite remote sensing images. The latest progress in the application of neural radiance field technology in satellite remote sensing is comprehensively summarized in this paper. First, the basic concepts of neural radiance field technology and related datasets are introduced. Then a classification framework of neural radiance field methods for satellite remote sensing images is proposed to systematically review and organize the research progress of this technology in the field of satellite remote sensing. The relevant results of the application of neural radiance field technology in actual satellite remote sensing scenarios are detailed. Finally, analysis and discussion are conducted based on the problems and challenges faced by current research, and future development trends and research directions are prospected.
Power Allocation and Trajectory Design for Unmanned Aerial Vehicle Relay Network with Mobile Users
YAN Zhi, LU Yuanyuan, DING Cong, HE Daiyu, OUYANG Bo, YANG Liang, WANG Yaonan
Available online  , doi: 10.11999/JEIT231337
In Unmanned Aerial Vehicle (UAV) relay networks, communication resource allocation and motion planning of UAV are the key problems that should be solved. In order to improve the communication efficiency of UAV relay communication system, a joint planning method of UAV relay power allocation and trajectory design is proposed based on proximal policy optimization algorithm. The joint planning problem of UAV relay power allocation and trajectory design in the user movement scenario is modelled as a Markov decision-making process. Considering the inaccurate acquisition of user location information, the reward function is set with the maximum throughput of the relay communication system as the optimization goal under the premise of satisfying the user interruption probability constraint. Then, a deep reinforcement learning algorithm with high convergence speed—the Proximal Policy Optimization (PPO) algorithm, is used to solve the problem and realized the flight trajectory optimization of relay UAV and the reasonable and effective allocation of relay transmission power. The simulation experimental results show that for the scenario of UAV relay communication with random users movement, the proposed method improves system throughput by 22% and 15%, respectively, compared to the methods based on random strategy and traditional Deep Deterministic Policy Gradient (DDPG). The results show that the proposed method can effectively improve the communication efficiency of the system.
EvolveNet: Adaptive Self-Supervised Continual Learning without Prior Knowledge
LIU Zhuang, SONG Xiangrui, ZHAO Siheng, SHI Ya, YANG Dengfeng
Available online  , doi: 10.11999/JEIT240142
Unsupervised Continual Learning(UCL) refers to the ability to learn over time while remembering previous patterns without supervision. Although significant progress has been made in this direction, existing works often assume strong prior knowledge about forthcoming data (e.g., knowing class boundaries), which may not be obtainable in complex and unpredictable open environments. Inspired by real-world scenarios, a more practical problem setting called unsupervised online continual learning without prior knowledge is proposed in this paper. The proposed setting is challenging because the data are non-i.i.d. and lack external supervision or prior knowledge. To address these challenges, a method called EvolveNet is intriduced, which is an adaptive unsupervised continual learning approach capable of purely extracting and memorizing representations from data streams. EvolveNet is designed around three main components: adversarial pseudo-supervised learning loss, self-supervised forgetting loss, and online memory update for uniform subset selection. The design of these three components aims to synergize and maximize learning performance. We conduct comprehensive experiments on five public datasets with EvolveNet. The results show that EvolveNet outperforms existing algorithms in all settings, achieving significantly improved accuracy on CIFAR-10, CIFAR-100, and TinyImageNet datasets, as well as performing best on the multimodal datasets Core-50 and iLab-20M for incremental learning. We also conduct cross-dataset generalization experiments, demonstrating EvolveNet's robustness in generalization. Finally, we open-source the EvolveNet model and core code on GitHub, facilitating progress in unsupervised continual learning and providing a useful tool and platform for the research community.
Trajectory and Resource Optimization in Energy-Efficient 3D Coverage of Unmanned Aerial Vehicle
ZHAO Nan, HUANG Xianggang, DENG Na, ZOU Deyue
Available online  , doi: 10.11999/JEIT240151
"Ubiquitous coverage" will become the main form of 6G networks, and complete the deployment in the mountains, hills, deserts and other blind area, to achieve full-area wireless coverage. However, the large-scale deployment of terrestrial base stations in remote areas is extremely difficult. For this reason, combining Unmanned Aerial Vehicle (UAV) communications with Non-Orthogonal Multiple Access(NOMA) technology, an energy-efficient three-dimensional coverage scheme to maximize the energy efficiency of network throughput is proposed in this paper. First, the system model is established and a user pairing algorithm is proposed based on the K-Means algorithm and the Gale-Shapley algorithm. Then, after user pairing is completed, the initial problem is split into two optimization subproblems, which are transformed to convex respectively. Finally, the block coordinate ascent method is used to alternately optimize the UAV trajectory and transmit power to maximize the energy efficiency. Simulation results show that compared with benchmarks, the proposed scheme can significantly improve the throughput energy efficiency of air-ground networks under large-scale wireless coverage.
A Improve Service and Reduce Consumption Algorithm for Proximal Policy Optimization
YAN Zhi, YU Huailong, OUYANG Bo, WANG Yaonan
Available online  , doi: 10.11999/JEIT230902
In order to solve the high-dimensional Service Function Chain (SFC) deployment problem of high reliability and low cost in the Network Function Virtualization (NFV) environment, a Improve Service and Reduce Consumption for Proximal Policy Optimization (PPO-ISRC) is proposed. Firstly, considering the characteristics of the underlying physical server and SFC, the state transition process of the underlying server network is descried, and the deployment of SFC is taken as a Markov Decision Process. The reward function is set with the optimization goal of maximizing the service rate and minimizing resource consumption. Finally the PPO method is used to solve the SFC deployment strategy. The results show that compared with the heuristic algorithm First-Fit Dijkstra (FFD) and the Deep Deterministic Policy Gradient (DDPG) algorithm, the proposed algorithm has the characteristics of fast convergence speed and higher stability. Under the requirements of service quality, the deployment cost is reduced and the reliability of network service is improved.
Gated Recurrent Unit Network of Particle Swarm Optimization for Drifting Buoy Trajectory Prediction
LIU SongZuo, WANG Qian, LI Lei, LI Hui, YU Yun
Available online  , doi: 10.11999/JEIT230945
Considering the trajectory prediction problem of drift buoys, an end-to-end prediction model based on the depth learning framework is proposed in this paper.The hydrodynamic models in different sea areas are quite different, and the calculation of fluid load of floating buoys on the sea surface is also complicated. Therefore, a more universal data-driven trajectory prediction model based on the multidimensional time series formed is proposed by the historical trajectories of drifting buoys. In this model, Particle Swarm Optimization (PSO) is combined with Gated Recurrent Unit (GRU), and the PSO is used to initialize the hyperparameters of the GRU neural network. The optimal drifting buoy trajectory prediction model is obtained after multiple migration iteration training. Finally, several real drifting buoy track data in the North Atlantic are used to verify the results. The results show that the PSOGRU algorithm can achieve accurate drifting buoy track prediction results.
A Multi-Factor Authentication Scheme Under the SM9 Algorithm Framework
ZHU Liufu, WANG Ding
Available online  , doi: 10.11999/JEIT231197
Wireless sensor networks use public wireless channels and their storage and computing resources are limited, making them vulnerable to active attacks and passive attacks. Identity authentication acts as the first line to ensure the security of information systems. Then, how to design multi-factor authentication schemes for wireless sensor devices is currently a hot topic. Nowadays, most existing schemes are based on foreign cryptographic standards that do not comply with the autonomous and controllable cyberspace security development strategy. SM9 is an identity-based cryptographic algorithm that has become a Chinese cryptographic standard recently. Therefore, this paper focuses on how to combine passwords, biometrics, and smart cards to design a multi-factor authentication scheme that can be used for wireless sensor networks under the framework of SM9. The proposed scheme applies the fuzzy verifier technique and the honeyword method to resist password guessing attacks and further enables session key negotiation and password update. The security is proved under the Random Oracle Model (ROM) and a heuristic security analysis is provided additionally. The comparison results show that the proposed scheme can be deployed to wireless sensor networks.
Multistable State and Phase Synchronization of Memristor-coupled Heterogeneous Memristive Cellular Neural Network
WU Huagan, BIAN Yixuan, CHEN Mo, XU Quan
Available online  , doi: 10.11999/JEIT240010
Memristors have a natural plasticity that enables silicon-based neurons and nano-synapses with similar or the same mechanisms as biological neurons and synapses. Using a memristor as a synapse to couple two heterogeneous memristive cellular neural networks, a memristor-coupled heterogeneous cellular neural network is constructed in this paper. The coupled network contains a space equilibrium set related to the initial value conditions of memristor synapse and subnets, which can exhibit complex dynamic evolution. The multi-stable behaviors of the coupling network, such as stable point, period, chaos, hyperchaos and unbounded oscillation, which depend on the initial value conditions, are revealed by numerical simulation method. In addition, under the control of memristor synapse, two heterogeneous subnets can achieve phase synchronization. Finally, the experimental verification of the circuit is completed based on STM32 MCU hardware platform.
Extraction of Attributed Scattering Center Based on Physics Informed Machine Learning
YUE Ziyu, XU Feng
Available online  , doi: 10.11999/JEIT231215
To estimate parameters of parameterized scattering center models is one of the basic methods for Synthetic Aperture Radar Advanced Information Retrieval (SAR AIR). Traditional Attributed Scattering Center (ASC) parameter estimation algorithms usually suffer from issues such as slow computation speed, high algorithm complexity, and high sensitivity to initial values of parameters. In this paper, a novel end-to-end framework for inverting ASC parameters from radar images based on unsupervised deep learning is proposed. Firstly, an autoencoder network structure is employed to effectively extract image features of targets, alleviating the difficulties solving directly caused by the complex non-convex optimization space and resolving the sensitivity to initial values. Secondly, the ASC model is embedded as a physical decoder to constrain the encoder output to correct ASC parameters. Finally, the end-to-end architecture are utlized to train and infer the model, achieving the purpose of reducing algorithm complexity and improving estimation speed. Through testing on simulated and measured data, experimental results indicate that the estimation error obtained on the SAR image test set with a resolution of 0.15 m is less than 0.1 m while the average processing time is 0.06 s for the inversion of one single scattering center, which demonstrate the effectiveness, efficiency, and robustness of the proposed approach.
Convolutional Neural Network STAP Low Level Wind Shear Wind Speed Estimation
Available online  , doi: 10.11999/JEIT231335
Due to the non-uniform ground clutter in the forward array of airborne weather radar, it is difficult to obtain enough independent and equally distributed samples, which affects the accurate estimation of clutter covariance matrix and wind speed estimation. In this paper, a novel estimation method of low altitude wind shear speed based on convolutional neural network STAP is proposed, which can realize high resolution clutter space-time spectrum estimation with a small number of samples. First, the high-resolution clutter space-time spectrum convolutional neural network is trained based on the convolutional neural network model, and then the clutter covariance matrix is calculated, and then the optimal weight vector of the convolutional neural network STAP is calculated for clutter suppression, so as to accurately estimate the wind shear speed at low altitude. In this paper, the sparse recovery problem is realized by convolutional neural network in the case of small samples, and the space-time spectrum of high-resolution clutter is effectively estimated. The simulation results show that the proposed method can effectively estimate the space-time spectrum and complete the wind speed estimation.
Research Progress of Electromagnetic Neural Network Based on Metamaterials
MA Qian, FENG Zirui, GAO Xinxin, GU Ze, YOU Jianwei, CUI Tiejun
Available online  , doi: 10.11999/JEIT231285
With the widespread application of artificial intelligence technology, the demand for computing power for intelligent computing has grown exponentially. At present, the rapid development of chips has approached the bottleneck of its manufacturing process, and power consumption is also increasing. Therefore, research on high-speed, energy-efficient intelligent computing hardware is an important direction. Computing architectures represented by photonic circuit neural networks and all-optical diffraction neural networks have received widespread attention due to their advantages such as fast calculation and low power consumption. This article reviews the representative work of optical neural networks, and introduces it through the two main lines of development of three-dimensional diffractive neural networks and optical neural network chips. At the same time, it focuses on the bottlenecks and challenges faced by optical diffractive neural networks and photonic neural network chips, such as network scale and Integration degree, etc., analyze and compare their characteristics, performance and respective advantages and disadvantages. Secondly, taking into account the development needs of generalization, this article further discusses the programmable design of neuromorphic computing hardware, and introduces some representative work on programmable neural networks to each part. In addition to intelligent neural networks in the optical band, this article also discusses the development and application of microwave diffraction neural networks and demonstrates their programmability. Finally, the future direction and development trends of intelligent neuromorphic computing are introduced, as well as its potential applications in wireless communications, information processing and sensing.
Optimal Miner Allocation Scheme for Sub-metaverses: From Multi-knapsack Problem Perspective
KANG Jiawen, WU Tianhao, WEN Jinbo, CHEN Junlong, XIONG Zehui, HUANG Xumin, LIU Lei
Available online  , doi: 10.11999/JEIT231214
Metaverses is a new type of internet social ecosystem that promotes user interaction, provides virtual services, and enables digital asset transactions. Blockchain, as the underlying technology of metaverses, supports the circulation of digital assets such as Non-Fungible Token (NFT) within the metaverse. However, the increase in consensus nodes can decrease the consensus efficiency of digital asset transactions. Therefore, this paper proposes a multi-metaverse digital assets transaction management framework based on edge computing and cross-chain technology. Firstly, cross-chain technology is utilized to connect multiple sub-metaverses into a multi sub-metaverse system. Secondly, edge devices are allocated as miners in various sub-metaverses, contributing idle computational resources to enhance the efficiency of digital asset transactions. Additionally, the paper models the edge device allocation problem as a multi-knapsack problem and designs a miner selection approach. To address the dynamic allocation problem caused by environmental changes, the Deep Reinforcement Learning Proximal Policy Optimization (DRL-PPO) algorithm from deep reinforcement learning is employed. Simulation results demonstrate the effectiveness of the proposed scheme in achieving secure, efficient, and flexible cross-chain NFT transactions and sub-metaverse management.
A Survey of Adversarial Attacks on 3D Point Cloud Object Recognition
LIU Weiquan, ZHENG Shijun, GUO Yu, WANG Cheng
Available online  , doi: 10.11999/JEIT231188
Currently, artificial intelligence systems have achieved significant success in various domains, with deep learning technology playing a pivotal role. However, although the deep neural network has strong inference recognition ability, it is still vulnerable to the attack of adversarial examples, showing its vulnerability. Adversarial samples are specially crafted input data designed to attack and mislead the outputs of deep learning models. With the rapid development of 3D sensors such as LiDAR, the use of deep learning technology to address various intelligent tasks in the 3D domain is gaining increasing attention. Ensuring the security and robustness of artificial intelligence systems that process 3D point cloud data, such as deep learning-based autonomous 3D object detection and recognition for self-driving vehicles, is crucial. In order to analyze the methods by which 3D adversarial samples attack deep neural networks, and reveal the interference mechanisms of 3D adversarial samples on deep neural networks, this paper summarizes the research progress on adversarial attack methods for deep neural network models based on 3D point cloud data. The paper first introduces the fundamental principles and implementation methods of adversarial attacks, and then it summarizes and analyzes digital domain adversarial attacks and physical domain adversarial attacks on 3D point clouds. Finally, it discusses the challenges and future research directions in the realm of 3D point cloud adversarial attacks.
Group Activity Recognition under Multi-scale Sub-group Interaction Relationships
ZHU Liping, WU Silin, CHEN Xiaohe, LI Chengyang, ZHU Kaijie
Available online  , doi: 10.11999/JEIT231304
Group activity recognition aims to identify behaviors involving multiple individuals. In real-world applications, group behavior is often treated as a hierarchical structure, which consists group, subgroups and individuals. Previous researches have been focused on modeling relationships between individuals, without in-depth relationship analysis between subgroups. Therefore, a novel hierarchical group activity recognition framework based on Multi-scale Sub-group Interaction Relationships (MSIR) is proposed, an innovative multi-scale interaction features extraction method between subgroups is presented as specified below. A sub-group division module is implemented. It aggregates individuals with potential correlations based on their appearance features and spatial positions, then dynamically generates subgroups of different scales using semantic information. A sub-group interactive feature extraction module is developed to extract more discriminative subgroup features. It constructs interaction matrices between different subgroups and leverages the relational reasoning capabilities of graph neural networks. Compared with existing twelve methods on benchmark datasets for group behavior recognition, including volleyball and collective activity datasets, the methodology of the paper demonstrates superior performance. This research presents an easily extendable and adaptable group activity recognition framework, exhibiting strong generalization capabilities across different datasets.
Deep Learning-based Joint Multi-branch Merging and Equalization Algorithm for Underwater Acoustic Channel
LIU Zhiyong, JIN Zihao, YANG Hongjuan, LIU Biao, TANG Xinfeng, LI Bo
Available online  , doi: 10.11999/JEIT231196
To better solve the fading and severe inter-symbol interference problems in underwater acoustic channels, a Joint Multi-branch Merging and Equalization algorithm based on Deep Learning (JMME-DL) is proposed in this paper. The algorithm jointly implements multi-branch merging and equalization with the help of the nonlinear fitting ability of the deep learning network. The merging and equalization are not independent of each other, in the implementation of the algorithm, the total error is first calculated based on the total output of the deep learning network, and then the network parameters of each part are jointly adjusted with the total error, and the dataset is constructed based on the statistical underwater acoustic channel model. Simulation results show that the proposed algorithm achieves faster convergence speed and better BER performance compared to the existing algorithms, making it better adapted to underwater acoustic channels.
Joint Internal and External Parameters Calibration of Optical Compound Eye Based on Random Noise Calibration Pattern
LI Dongsheng, WANG Guoyan, LIU Jinxin, FAN Hongqi, LI Biao
Available online  , doi: 10.11999/JEIT230652
In tasks such as precise guidance and obstacle avoidance navigation based on optical compound eyes, the calibration of optical compound eyes plays a crucial role in achieving high accuracy. The classical Zhang's calibration method requires each ommatidium of the optical compound eyes to observe a complete chessboard pattern. However, the complexity of the optical compound eye structure makes it difficult to satisfy this requirement in practical applications. In this paper, a joint internal and external parameters calibration algorithm of optical compound eyes based on a random noise calibration pattern is proposed. This algorithm utilizes the local information captured by the ommatidia when photographing the random noise calibration pattern, enabling simple and fast calibration for optical compound eyes with arbitrary configurations and numbers of ommatidia. To improve the robustness of the calibration, a multi-threshold matching mechanism is introduced to address the issue of sparse feature point quantity in ommatidial visual fields leading to matching failures. Moreover, an error model for the joint internal and external parameters calibration of optical compound eyes is presented to evaluate the accuracy of the proposed algorithm. Experimental comparisons with Zhang’s calibration method demonstrate the robustness of the proposed algorithm. Furthermore, the high accuracy of the proposed joint calibration algorithm is validated in a physical system of optical compound eyes.
Resource Allocation Algorithm for Intelligent Reflecting Surface-assisted Secure Integrated Sensing And Communications System
ZHU Zhengyu, YANG Chenyi, LI Zheng, HAO Wanming, YANG Jing, SUN Gangcan
Available online  , doi: 10.11999/JEIT240083
In order to solve the problems of information security, and spectrum limitation in Integrated Sensing And Communications (ISAC) systems, a secure resource allocation scheme in Intelligent Reflecting Surface (IRS)-assisted ISAC systems is investigated in this paper. To start with, in this IRS-ISAC system, where the user is being maliciously attacked by eavesdroppers, the security of the system is ensured by incorporating a jammer and deploying an IRS that utilizes its intelligent regulation of the wireless environment. Then, a secrecy rate maximization problem that subjects to the maximum transmit power constraints of the base station and the jammer, the IRS reflecting phase shift constraints, and the radar's signal-to-noise ratio constraints is formulated by jointly designing the transmit beamforming of base station, jammer precoding vectors, and IRS phase shifts. Next, utilizing techniques such as alternating optimization and Semi-Definite Relaxation (SDR) algorithm, the original non-convex optimization problem is reformulated into a convex optimization problem, capable of determining a definitive solution. Finally, simulation results verify the security and effectiveness of the proposed algorithm and the superiority of the IRS-ISAC system.
Website Fingerprinting Attacks and Defenses on Tor: A Survey
YANG Hongyu, SONG Chengyu, WANG Peng, ZHAO Yongkang, HU Ze, CHENG Xiang, ZHANG Liang
Available online  , doi: 10.11999/JEIT240091
The anonymity network represented by The onion router(Tor) is one of the most widely used encrypted communication networks, criminals utilize encrypted networks to conceal their illegal activities, posing significant challenges to network regulation and cybersecurity. The emergence of website fingerprinting attack has made the analysis of encrypted traffic possible, enabling supervisors to identify Tor traffic and infer the web pages being visited by users by utilizing features such as packet direction and so on. In this paper, a wide survey and analysis of website fingerprinting attack and defense methods on Tor are conducted. Firstly, relevant techniques of website fingerprinting attacks on Tor are summarized and compared. The emphasis is placed on website fingerprinting attacks based on traditional machine learning and deep learning technologies. Secondly, a comprehensive survey and analysis of various existing defense methods are conducted. The limitations in the field of website fingerprinting attack methods on Tor are analyzed and summarized, and the future development directions and prospects are looked forward to.
Research on Intelligent Spectrum Allocation Techniques for Incomplete Electromagnetic Information
ZHAO Haoqin, DUAN Guodong, SI Jiangbo, HUANG Rui, SHI Jia
Available online  , doi: 10.11999/JEIT231005
To solve the problem of low spectrum utilization of multi-node autonomous frequency decision-making in the dynamic electromagnetic countermeasure environment, the research on intelligent cooperative spectrum allocation technology for non-complete electromagnetic information is carried out, which improves spectrum utilization through multi-node intelligent collaboration. Firstly, the spectrum allocation problem is modelled as an optimization problem to maximize the frequency-using equipment, and secondly, a resource decision-making algorithm based on the multi-node cooperative diversion experience repetition mechanism (Cooperation- Deep double Q-network, Co-DDQN) is proposed. This algorithm evaluates the historical experience data based on the cooperative diversion function and is trained by a hierarchical experience pool, so that each agent can form a lightweight cooperative decision-making ability under self-observation, and solve the problem of inconsistency between the optimization direction of multi-node decision-making and the overall optimization goal under low-visibility conditions. Besides, a hybrid reward function based on confidence allocation is designed, and each node considers itself when the decision is made, which can reduce the emergence of lazy nodes, explore a better overall action strategy, and further improve the system efficiency. Simulation results show that when the number of nodes is 20, the number of accessible devices of the proposed algorithm outperforms the global greedy algorithm and the genetic algorithm, and the difference with the centralized spectrum allocation algorithm with complete information sharing is within 5%, which is more suitable for cooperative spectrum allocation of low-visibility nodes.
Visibility Region Spatial Distribution Dataset for XL-MIMO Arrays
GAO Ruifeng, MIAO Yanchun, CHEN Ying, WANG Jue, ZHANG Jun, HAN Yu, JIN Shi
Available online  , doi: 10.11999/JEIT231273
The Visibility Region (VR) information can be used to reduce the complexity in transmission design of Extremely Large-scale massive Multiple-Input Multiple-Output (XL-MIMO) systems. Existing theoretical analysis and transmission design are mostly based on simplified VR models. In order to evaluate and analyze the performance of XL-MIMO in realistic propagation scenarios, this paper discloses a VR spatial distribution dataset for XL-MIMO systems, which is constructed by steps including environmental parameter setting, ray tracing simulation, field strength data preprocessing and VR determination. For typical urban scenarios, the dataset establishes the connections between user locations, field strength data, and VR data, with a total number of hundreds of millions of data entries. Furthermore, the VR distribution is visualized and analyzed, and a VR-based XL-MIMO user access protocol is taken as an example usecase, with its performance evaluated with the proposed VR dataset.
Self-tuning Multivariate Variational Mode Decomposition
LANG Xun, WANG Jiayi, CHEN Qiming, HE Bingbing, MAO Rukai, XIE Lei
Available online  , doi: 10.11999/JEIT230763
The Multivariate Variational Mode Decomposition (MVMD), being an extension of the Variational Mode Decomposition (VMD), inherits the merits of VMD. However, it encounters an issue wherein its decomposition performance relies heavily on two predefined parameters, the number of modes (K) and the penalty factor (\begin{document}$ \alpha $\end{document}). To address this issue, a Self-tuning MVMD (SMVMD) algorithm is proposed. SMVMD employs the notion of matching pursuit to adaptively update K and \begin{document}$ \alpha $\end{document} based on energy occupation and mode orthogonality in the frequency domain, respectively. The experimented results of both simulated signals and real cases demonstrate that the proposed SMVMD not only effectively addresses the parameter rectification problem of the original MVMD, but also exhibits the following advantages: (i) SMVMD displays superior resilience to mode-mixing compared to MVMD, along with enhanced robustness to both noise and variations in \begin{document}$ \alpha $\end{document}-value. (ii) In comparison to the classical algorithms of multivariate empirical mode decomposition, fast multivariate empirical mode decomposition, and multivariate variational mode decomposition, SMVMD showcases the lowest decomposition error and the best decomposition effect.
Multi-scale Attention Recurrent Network with Multi-order Taylor Differential Knowledge for Deep Spatiotemporal Sequence Prediction
SUN Qiang, ZHAO Ke
Available online  , doi: 10.11999/JEIT231108
Deep spatiotemporal sequence prediction methods that incorporate a priori physical knowledge are commonly characterized by the utilization of Partial Differential Equations (PDE) for modeling. However, two main issues are concerned: (1) the limited precision in approximations with PDEs; and (2) the inability to efficiently capture spatiotemporal features at multiple spatial scales as well as the edge spatial information of the spatiotemporal sequences in the recurrent network. To address these challenges, one Taylor Differential Incorporated Convolutional Recurrent Neural Network (TDI-CRNN) is proposed in this paper. Firstly, in order to enhance the approximation accuracy of higher-order partial differential equations and to alleviate the limitations of PDE applications, one physical module with multi-order Taylor approximation is designed. The module is firstly used for the differential approximation of the input sequence by means of the Taylor expansion, and then couples via differential coefficients the differential convolution layers with different orders, and dynamically adjusts the truncation order and the number of differential terms of the Taylor expansions. Secondly, to capture the multiple spatial scale features of the hidden states in the recurrent network and to better capture the edge spatial information of the spatiotemporal sequences, one Multi-Scale Attention Recurrent Module (MSARM) is devised. Multi-scale convolution and spatial attention mechanisms are utilized in the convolution layer of the Multi-Scale Convolution Spatial Attention UNet (MCSA-UNet), aiming to focus on local spatial regions within spatiotemporal sequences. Extensive experiments are conducted on the Moving MNIST, KTH, and CIKM datasets. The Mean Squared Error (MSE) on the Moving MNIST dataset dropped to 42.7, while the Structural Similarity Index Measure (SSIM) increased to 0.912. The SSIM and Peak Signal-to-Noise Ratio (PSNR) on the KTH dataset increased to 0.882 and 29.03, respectively. The Correct Skill Index (CSI) on the real weather radar echo CIKM dataset increased to 0.515. The final visualization and quantitative prediction results verify the rationality and effectiveness of the TDI-CRNN model.
Adaptive Detectors for Mismatched Signal under Sea Clutter Background with Generalized Inverse Gaussian Texture
FAN Yifei, CHEN Duo, SU Jia, GUO Zixun, TAO Mingliang, WANG Ling
Available online  , doi: 10.11999/JEIT231440
Considering mismatched problem between theoretical steering vector and actual steering vector causes false-alarm-rate increase in the process of maritime radar detection, the adaptive mismatched detectors are studied under Compound Gaussian Model (CGM). In order to reject mismatched signal, the fictitious signal orthogonal to theoretical steering vector is introduced in the hull hypothesis, and a target detection with mismatched signal is given. The texture component of CGM is represented by generalized inverse distribution, and the Adaptive Beamformer Orthogonal Rejection Test (ABORT) are developed based on two-step Generalized Likelihood Ratio Test (GLRT) and Maximum A Posteriori GLRT (MAP GLRT) criterions respectively. Both the proposed detectors are testified to be Constant False Alarm (CFAR) characteristics for speckle covariance matrix and target doppler steering vector. Experimental results based on simulated and real measured sea clutter data indicate that the proposed mismatched detectors show preferable target detection performance under the matched steering vector condition and anti-mismatch capability under the mismatched steering vector condition.
Flexible Multiple Access Technology for Satellite Internet of Things
PANG Mingliang, WANG Chaowei, WU Tong, CHEN Jiabin, HUANG Sai, JIANG Fan, ZHANG Junyi
Available online  , doi: 10.11999/JEIT231388
Access latency and complexity in the satellite Internet of Things (IoT) are significantly reduced by the grant-free uplink random access based on Slotted ALOHA (S-ALOHA). However, with the increase of the number of IoT users, the collision probability of S-ALOHA is markedly increased, thereby impacting the performance of the system. This paper addresses the scenario of massive device uplink access in satellite IoT, focusing on the investigation of power resource control for IoT terminals to achieve maximization of system throughput and rate. A flexible multiple access scheme based on S-ALOHA is proposed. In the presence of collisions in the system, transmission is carried out using non-orthogonal multiple access technology, which mitigates the issue of repeated transmission of user information and reduces transmission latency. The sequential decision problem of maximizing system throughput and rate under the constraint of terminal power is modeled as a Markov process, and the Advantage Actor-Critic (A2C) method is employed to solve it. The simulation results indicate that the success rate of terminal access in scenarios with a massive number of IoT terminals is effectively ensured by the proposed flexible multiple access technology. Additionally, the resource allocation algorithm based on A2C is shown to outperform traditional resource allocation algorithms.
Channel State Information Restoration and Positioning of massive Multiple Input Multiple Output Integrated Visible Light Communication and Sensing System
LIU Xiaodong, NING Yiting, DONG Fan, TANG Liwei, WANG Yuhao, WANG Jinyuan
Available online  , doi: 10.11999/JEIT231389
Benefiting from rich spectrum and lamps, Integrated Visible Light Communication and Positioning (IVLCP) systems provide powerful technological solution to meet the high performance communication and positioning in indoor wireless networks. Meanwhile, the massive Multiple Input Multiple Output (m-MIMO) effectively enhance both service coverage and quality of IVLCP systems. However, the channel environment is more complex and the priori information rapidly changed in the m-MIMO-enabled IVLCP systems, making traditional methods challenging for fast and accurate channel estimation and positioning. In order to tackle this challenge, a Channel State Information Restoration and Positioning (CSIRP) network is proposed in this paper. The network not only effectively captures complex distribution feature of channel but also addressing the temporal variations in location, thereby enhancing the robustness and dynamic adaptability of channel and location estimation. Specifically, the CSIRP network employs a conditional generative adversarial process to adaptively train the generator and discriminatorr and thus achieves the channel estimation from received signals. Then, the Long Short-Term Memory(LSTM) is introduced to estimate the location of the receiver from the estimated channel. Simulation results demonstrate that the accuracy of both channel and location estimation achieved by the proposed CSIRP network outperforms existing deep learning benchmark schemes. This provides m-MIMO-enabled IVLCP systems with more reliable and accurate channel state information and positioning.
Radar Emitter Identification Based on Dual Radio Frequency Fingerprint Convolutional Neural Network and Feature Fusion
XIAO Yihan, WANG Boyu, YU Xiangzhen, JIANG Yilin
Available online  , doi: 10.11999/JEIT231236
In order to achieve identification of radar emitter unaffected by signal parameters and modulation methods, a method based on Dual Radio Frequency Fingerprint Convolutional Neural Network (Dual RFF-CNN2) and feature fusion is proposed in this paper. Firstly, Raw-I/Q signals are extracted from the received radio frequency signals. Secondly, Axially Integral Bispectrum (AIB) and Square Integral Bispectrum (SIB) dimensionality reduction are performed separately on Raw-In-phase/Quadrature (Raw-I/Q) signals to construct the bispectrum integration matrix. Finally, both the Raw-I/Q signals and the bispectrum integration matrix are fed into the Dual RFF-CNN2 network for feature fusion to achieve identification of radar emitter. Experimental results demonstrate that this method achieves high identification accuracy, and the extracted "fingerprint features" exhibit stability and robustness.
Research on Diffuse Scattering Propagation and Depolarization Modeling for B5G Millimeter-wave Communications at 40~50 GHz
LIAO Xi, CHEN Xinrui, WANG Yang, REN Minghao, CHEN Qianbin
Available online  , doi: 10.11999/JEIT230706
To achieve an accurate characterization and thorough understanding of the millimeter-wave (mmWave) communication channel propagation mechanism, precise characterization of diffuse scattering propagation and polarization is crucial. These aspects are also indispensable for the development of a high-precision mmWave channel model. In response to the insufficient characterization of diffuse scattering propagation and polarization caused by building materials in the mmWave frequency bands, this paper presents a novel diffuse scattering depolarization modeling method based on effective roughness theory. Initially, the electric field of the diffuse scattering radiation produced by the rough surface of building materials is decomposed along the polarization dimension of the electromagnetic wave. Subsequently, the depolarization coefficient is introduced to establish the propagation model. The paper investigates the diffuse scattering propagation and polarization characteristics, encompassing the power angle spectrum, depolarization coefficient, and cross-polarization discrimination ratio, by utilizing measured data of typical materials in the 40~50 GHz frequency range. The obtained results validate that the proposed model effectively captures the polarization characteristics of building materials with both rough and smooth surfaces. The achieved depolarization conversion rates are 40% and 4%, respectively.
Review on Olfactory and Visual Neural Pathways in Drosophila
ZHANG Sheng, ZHENG ShengNan, SHEN Jie, YIN Xinghui, XU Lizhong
Available online  , doi: 10.11999/JEIT230508
The olfactory and visual neural systems in Drosophila are highly sensitive to the olfactory and visual stimuli in the natural environment. The highly sensitive single-modal perception and cross-modal collaboration decision-making mechanisms of the olfactory and visual neural systems provide certain inspiration for bionic applications. Firstly, based on the olfactory and visual neural systems in Drosophila, the current research status of the physiological mechanisms and computational models of single-modal perception decision-making of the olfactory and visual neurons is summarized. The summary is divided into three parts: capturing, processing, and decision-making of the olfactory and visual signals. Meanwhile, the physiological mechanisms and computational models of cross-modal collaboration decision-making of the olfactory and visual neurons in Drosophila are further expounded. Then, the typical bionic applications of single-modal perception and cross-modal collaboration in Drosophila are summarized. Finally, the current challenges of the physiological mechanisms and computational models of the olfactory and visual neural pathways in Drosophila are summarized and the future development trends are outlook for, which lays a foundation for future research work.
Text-to-video Generation: Research Status, Progress and Challenges
DENG Zijun, HE Xiangteng, PENG Yuxin
Available online  , doi: 10.11999/JEIT240074
The generation of video from text aims to produce semantically consistent, photo-realistic, temporal consistent, and logically coherent videos based on provided textual descriptions. Firstly, the current state of research in the field of text-to-video generation is elucidated in this paper, providing a detailed overview of three mainstream approaches: methods based on recurrent networks and Generative Adversarial Networks (GAN), methods based on Transformers, and methods based on diffusion models. Each of these models has its strengths and weaknesses in video generation. The recurrent networks and GAN-based methods can generate videos with higher resolution and duration but struggle with generating complex open-domain videos. Transformer-based methods show proficiency in generating open-domain videos but face challenges related to unidirectional biases and accumulated errors, making it difficult to produce high-fidelity videos. Diffusion models exhibit good generalization but are constrained by inference speed and high memory consumption, making it challenging to generate high-definition and lengthy videos. Subsequently, evaluation benchmarks and metrics in the text-to-video generation domain are explored, and the performance of existing methods is compared. Finally, potential future research directions in the field is outlined.
Simplified Architecture of 5G Millimeter-wave Retrodirective Array and Its Implementation in CMOS Chips
GUO Jiacheng, HU Sanming, SHEN Yizhu, QIAN Yun, HU Chuyou, HUANG Yongming, YOU Xiaohu
Available online  , doi: 10.11999/JEIT240143
For the first time, a simplified architecture for 5G millimeter-wave retrodirective arrays and its implementation in CMOS chips is reported in this paper. Phase conjugation and retrodirective functions are provided by sub-harmonic mixers in the simplified architecture, eliminating the need for phase-shifting circuits and beam-controlling systems, thereby enabling automatic beam tracking for mobile communications. For validation, a domestic 0.18 μm CMOS process is employed to realize a 5G millimeter-wave retrodirective array chip, comprising core modules such as the transceiver front-ends and tracking phase-locked loop. Measured conversion gains of 19.5 dB for transmitting and 18.7 dB for receiving are achieved by the transceiver front-end chip utilizing sub-harmonic mixing and gm-boosting techniques. Dual-mode operation capabilities, supporting both amplitude modulation and phase modulation based on different reference signals, are provided by the implemented tracking phase-locked loop chip, with measured output signal phase noise lower than –125 dBc/Hz@100 kHz. The feasibility of the proposed 5G millimeter-wave retrodirective array communication architecture and its CMOS chip implementation is validated by the test results presented in this paper, thus offering a new solution for 5G/6G millimeter-wave communication characterized by its extremely simplified architecture, low cost, and high scalability.
A Robust Multi-Channel Moving Target Detection Algorithm for Complex Scenes
LIU Kun, HE Xiongpeng, LIAO Guisheng, YU Yue, WANG Qikai
Available online  , doi: 10.11999/JEIT230958
Aiming at the problems of high false alarm and sensitivity to channel error of Robust Principal Component Analysis (RPCA) algorithm in multi-channel Ground Moving Target Indication (GMTI), this paper proposes a data reconstruction and Velocity Synthetic Aperture Radar (VSAR)-RPCA joint processing method. Firstly, the sample selection and joint pixel method are used to complete the accurate reconstruction of inter-channel data; then a new RPCA optimization model is proposed by combining the VSAR detection mode, and the sparse matrix in the spatial frequency domain is obtained by solving the new RPCA optimization model with the alternating projection multiplier method, and then the differences in the distribution characteristics of the moving target and the strong clutter residuals in the spatial frequency domain channel are used to realize the strong clutter residuals rejection and the detection of the moving target; finally, the radial velocity of the target is estimated by the Along-Track Interferometry algorithm to complete the moving target relocation. Compared with the traditional RPCA algorithm, the proposed algorithm significantly reduces the false alarm rate under the background of non-ideal strong clutter. Theoretical analyses and experiments verify the effectiveness of the proposed algorithm.
Overview on the Research Status and Development Route of Fully Homomorphic Encryption Technology
DAI Yiran, ZHANG Jiang, XIANG Binwu, DENG Yi
Available online  , doi: 10.11999/JEIT230703
With the application and popularization of IoT, cloud computing, and artificial intelligence, data security and privacy protection have become the focus of attention. Fully homomorphic encryption, as an effective solution to the privacy security problem, allows performing arbitrary homomorphic computation on encrypted data, and is a powerful encryption tool with a wide range of potential applications. The paper summarizes the proposed fully homomorphic encryption schemes since 2009, and divides them into four technical routes based on the core technologies of the schemes, analyzes and discusses the key constructs, algorithm optimization processes, and future development directions of each type of scheme. The paper firstly introduces fully homomorphic encryption-related mathematical principles, covering the basic assumptions and security features of fully homomorphic encryption schemes. Subsequently, according to the technical routes of the four fully homomorphic encryption schemes, it summarizes the structural general formulas of the encryption schemes, summarizes the core steps of the bootstrap algorithms, discusses the latest research progress, and on the basis of this, comprehensively analyzes and compares the storage efficiencies and computing speeds of various schemes. The paper finally shows the application implementation of homomorphic algorithm library for encryption schemes under each technical route, analyzes the opportunities and challenges of fully homomorphic encryption schemes in the current era, and makes an outlook on the future research prospects.
A Low-Power Network-on-Chip Power-Gating Design with Bypass Mechanism
OUYANG Yiming, CHEN Zhiyuan, XÜ Dongyu, LIANG Huaguo
Available online  , doi: 10.11999/JEIT231257
Static power consumption dominates the power overhead of Network-on-Chip (NoC) as the technology size shrinks. Power gating, a generalized power saving technique, turns off idle modules in NoCs to reduce static power consumption. However, the conventional power gating technique brings problems such as packet wake-up delay, break-even time, etc. To solve the above problems, Partition Bypass Transmission Infrastructure (PBTI) is proposed in the paper, being adopted for packet transmission in place of a power-gated router, and a low-latency, low-power power gating scheme has been designed based upon this bypass mechanism. PBTI uses mutually independent bypasses to process separately the PBTI uses independent bypasses to handle east-west packets separately, and uses common buffers within the bypasses to improve buffer utilization. PBTI can inject, transmit, and eject packets when the router is powered off. Packets can be transmitted from the source node to the destination node even if all routers in the network are power gated. When the traffic increases beyond the transmission capacity of PBTI, the routers perform a uniform wake-up in columns. Experimental results show that compared to the NoC without power gating, the scheme in this paper reduces 83.4% of static power consumption and 17.2% of packet delay, while adding only 6.2% additional area overhead. Compared to the conventional power gating scheme the power gated design in this paper achieves lower power consumption and delay, which is a significant advantage.
Shutter-less Non-uniformity Correction Methods in Uncooled Infrared Imagery
HUANG Yuanfei, HUANG Hua
Available online  , doi: 10.11999/JEIT231400
Due to the limitations of imaging principles and processing technology, uncooled infrared imagery detectors suffer from serious non-uniformities, damaging the imaging results. To improve the quality of infrared images, non-uniformity correction techniques are of great significance for practical applications. According to the physical formation and spatial characteristics of the non-uniformity in uncooled infrared imagery detectors, this paper divides these common non-uniformities into three categories: low-frequency non-uniformity, shot non-uniformity, and stripe non-uniformity. The physical mechanisms of these non-uniformities are further explored from the procedure in the optical system, thermal materials, and amplifier circuit of the uncooled infrared imagery detector. Then, the existing shutter-less non-uniformity correction methods are systematically summarized. Based on the principles of the methods, statistical-based, filter-based, optimization-based, and learning-based non-uniformity correction methods are categorized. Besides, the specifics of each method in dealing with different non-uniformities are clarified and distinguished. Finally, the existing problems in the current methods are reviewed and summarized, and the development trend of non-uniformity correction methods in future practical applications is prospected.
A Survey on Software-hardware Acceleration for Fully Homomorphic Encryption
BIAN Song, MAO Ran, ZHU Yongqing, FU Yunhao, ZHANG Zhou, DING Lin, ZHANG Jiliang, ZHANG Bo, CHEN Yi, DONG Jin, GUAN Zhenyu
Available online  , doi: 10.11999/JEIT230448
Fully Homomorphic Encryption (FHE) is a multi-party secure computation protocol characterized by its high computational complexity and low interaction requirements. Although there is no need for multiple rounds of interactions and extensive communications between computing participants in protocols based on FHE, the processing time of encrypted data is typically \begin{document}$ {10}^{3} $\end{document} to \begin{document}$ {10}^{6} $\end{document} times of that of plaintext computing, and thus significantly hinders the practical deployment of such protocols. In particular, the large-scale darallel cryptographic operations and the cost of data movement for the ciphertext and key data needed in the operations become the dominating performance bottlenecks. The topic of accelerating FHE in both the software and the hardware layers is discussed in this paper. By systematically categorizing and organizing existing literatures, a survey on the current status and outlook of the research on FHE is presented.
A Reflection Modulation System Based on Reflecting Element Grouping of Active Intelligent Reflecting Surface
XIONG Junzhou, LI Guoquan, WANG Yuetao, LIN Jinzhao
Available online  , doi: 10.11999/JEIT231187
To overcome the “double path loss” in Intelligent Reflecting Surface (IRS) assisted communication system and further enhance reliability and spectral efficiency, a Reflection Modulation (RM) system scheme based on grouping of active IRS reflecting elements is proposed. This scheme utilizes the number of active reflecting element groups to transmit additional information. Then the average pairwise error probability of both the symbols transmitted by base station and the number of active reflecting element groups under the maximum likelihood detection algorithm is derived based on the moment generating function, and an upper bound on the theoretical Bit Error Probability (BEP) as well as the achievable data rate of the system are obtained. Simulation results verify the accuracy of the theoretical derivation and demonstrate the superior error performance and spectral efficiency of the proposed scheme.
A Novel Pattern for Global Ubiquitous Interconnection: Key Technologies and Challenges of Direct-to-Smartphone
HE Yuanzhi, XIAO Yongwei, ZHANG Shijie, FENG Long, LI Zhiqiang
Available online  , doi: 10.11999/JEIT240032
Satellite communication plays a crucial role in addressing blind spots and enhancing ubiquitous coverage for future global ubiquitous communication needs. Direct-to-Smartphone(DS) technology, as a technological means to achieve global integrated space-ground and intelligent connection of all things in the future 6G network, has become a hot development topic worldwide in the past two years and has received widespread attention. The development status and mainstream technical routes of DS technology in this article both domestically and internationally are introduced. The development challenges have been analyzed on DS technology in terms of limited frequency resource usage, broadband service requirements of DS, massive user business with time-varying and non-uniform distribution, high-dynamic effect of low earth orbit satellite, ultra-dense multi-beam influence, and high-density integration of smartphone. Key solutions such as satellite-ground co-frequency sharing, high dynamic air interface design, large array spaceborne multi-beam antenna, multi-dimensional resource management and control of satellite and ground, adapting to high dynamic satellite air interface system, on-demand scheduling of extremely narrow beam, and highly integrated smartphone design are proposed in this paper. Finally, the future development of DS technology is discussed.
Research on Channel State Information Feedback in Underwater Acoustic Adaptive OFDM Communication Based on Sequenced Codebook
LIU Songzuo, HAN Xue, MA Lu, XU Jinjie, YANG Yang
Available online  , doi: 10.11999/JEIT230878
As a result of the characteristics of UnderWater Acoustic (UWA) channel, such as rapid fading of Channel Frequency Response (CFR) due to large delay spreading, the development of UnderWater Acoustic Communication (UWAC) technology is challenged. The acquisition of effective and reliable Channel State Information (CSI) at the transmitter is a prerequisite for adaptive communication. To meet the needs of UWA adaptive OFDM communication, a CSI-Grouping-Sequencing-Fitting-Feedback (CSI-GSFF) based on sequenced codebook algorithm is proposed, which consists of three steps, including grouping, sequencing, and data fitting. Firstly, adjacent pilot subcarriers are divided into several groups and each group is seen as a feedback cell. Then, the pilot subcarriers within each group are sorted according to the channel gains to mitigate adverse effects such as high feedback overhead caused by the rapid fading of CFR. Finally, polynomial fitting is performed, and the sorting operation effectively reduces the fitting order. Through the simulation of time-varying channel data in sea trials, the results show that the CSI-GSFF algorithm can achieve the Bit Error Rate (BER) performance of the UWA adaptive OFDM communication system under the perfect CSI, while the CSI-GSFF algorithm can effectively reduce the feedback overhead.
Progress in The Application and Research of Approximate Computation Techniques Oriented to The Field of Digital Signal Processing
CHEN Ke, WANG Xu, YAN Chenggang, WANG Chenghua, LIU Weiqiang
Available online  , doi: 10.11999/JEIT231245
In the field of signal processing, approximate computing techniques have garnered significant attention. Complex algorithms and massive data impose limitations on processing speed and increase system hardware consumption. Since signals often contain redundancy, precise results are not always necessary, and achieving results acceptable to users is sufficient. Therefore, employing approximate computing techniques can effectively reduce computational complexity, enhance computational efficiency, and improve system performance. This paper takes a hierarchical approach to the design of approximate computing techniques. It first introduces the characteristics of signal processing applications, reviews recent research progress in approximate computing techniques at the algorithm and circuit levels, and investigates approximate computing solutions in signal processing directions such as communication, video imaging, and radar. Finally, it discusses and prospects the development direction of this field, providing insights to promote the application of approximate computing techniques in signal processing.
Low-power Microcontroller Units Design and Realization Using Emerging Tunneling Field Effect Transistors
CAI Hao, TONG Xinfang, YANG Jun
Available online  , doi: 10.11999/JEIT231298
Tunneling Field Effect Transistor (TFET)-based low-power microcontroller design combines devices, circuits, and systems to achieve extremely low leakage power consumption under non-operating conditions through devices with ultra-low subthreshold swing characteristics, avoiding the power bottleneck brought about by the theoretical limit of the subthreshold swing of MOSFETs, and solving the problem of low power consumption of battery-powered microcontrollers. TFETs differ greatly from traditional MOSFETs in their operating mechanism, mainly in that they have lower leakage current after shutdown and can operate at lower voltages, which makes them suitable for IoT application scenarios with low-power requirements for long-dormant battery power supply. The paper investigates the research of TFET devices in low-power circuit design in recent years, introduces the structure of traditional microcontrollers and the source of power consumption, and at the same time explains the working principle, characteristics and design challenges of TFET devices, examines the research and development process of TFETs in the fields of digital circuits, analog circuits, and system design, and analyzes the strengths and weaknesses of each design scheme, and analyzes the advantages and disadvantages of TFETs in low-power circuits, in combination with the research of the literature. The future outlook of TFETs in the field of low-power microcontrollers is analyzed.
A Review of Progress in Super-Resolution Reconstruction of Polarimetric Radar Image Target
LI Mingdian, XIAO Shunping, CHEN Siwei
Available online  , doi: 10.11999/JEIT231249
Radar possesses the capability for all-day, all-weather observation and can generate radar target images through image processing. It serves as an indispensable piece of remote sensing equipment in various civil and military applications, including earth observation, and surveillance. High-resolution radar images can provide a detailed outline and fine structure of the target, which is conducive to subsequent applications such as target classification and recognition. For the acquired radar images, how to use theoretical methods such as signal and information processing to further improve the resolution and break through the Rayleigh limit has important scientific research and practical application value. On the other hand, polarization, a crucial attribute of electromagnetic waves, plays a significant role in the acquisition and analysis of target characteristics, and can provide rich information for super-resolution reconstruction. Accordingly, this work initially elucidates the concept of polarimetric radar image super-resolution reconstruction, summarizes the performance evaluation metrics, and primarily focuses on the methods of polarimetric radar image super-resolution reconstruction and their applications. Lastly, the limitations of existing methods are summarized and potential future trends in technology are forecasted.
Improved Integral Cryptanalysis on Block Cipher uBlock
WANG Chen, CUI Jiamin, LI Muzhou, WANG Meiqin
Available online  , doi: 10.11999/JEIT231231
Integral attack is one of the most powerful cryptanalytic methods after differential and linear cryptanalysis, which was presented by Daemen et al. in 1997 (doi: 10.1007/BFb0052343). As the winning block cipher of China’s National Cipher Designing Competition in 2018, the security strength of uBlock against integral attack has received much attention. To better understand the integral property, this paper constructs the Mixed Integer Linear Programming (MILP) models for monomial prediction to search for the integral distinguishers and uses the partial sum techniques to perform key-recovery attacks. For uBlock-128/128 and uBlock-128/256, this paper gives the first 11 and 12-round attacks based on a 9-round integral distinguisher, respectively. The data complexity is \begin{document}$ {2}^{127} $\end{document} chosen plaintexts. The time complexities are \begin{document}$ {2}^{127.06} $\end{document} and \begin{document}$ {2}^{224} $\end{document} times encryptions, respectively. The memory complexities are \begin{document}$ {2}^{44.58} $\end{document} and \begin{document}$ {2}^{138} $\end{document} Byte, respectively. For uBlock-256/256, this paper gives the first 12-round attack based on a 10-round integral distinguisher. The data complexity is \begin{document}$ {2}^{253} $\end{document} chosen plaintexts. The time and memory complexities are \begin{document}$ {2}^{253.06} $\end{document} times encryptions and \begin{document}$ {2}^{44.46} $\end{document} Byte, respectively. The number of attacked rounds for uBlock-128/128 and uBlock-256/256 are improved by two rounds compared with the previous best ones. Besides, the number of attacked rounds for uBlock-128/256 is improved by three rounds. The results show that uBlock has enough security margin against integral attack.
Joint Multi-UAV Trajectory Design for Power Line Inspection
GAO Yunfei, HU Yulin, LIU Mingliu, HUANG Yuxi, SUN Peng
Available online  , doi: 10.11999/JEIT231199
Unmanned Aerial Vehicles (UAV) technology holds significant importance and offers extensive potential for application in the field of inspection. Taking into account the limited endurance of the UAV, it needs to fly from the nest to the designated inspection area, complete the inspection of the transmission tower, and then return to the nest safely before the battery is exhausted. For large-scale inspection scenarios, a multi-UAV inspection method is proposed to minimize the inspection time. In detail, the k-means++ algorithm is used to optimize task allocation of the UAVs and the modified simulated annealing algorithm is utilized to optimize the inspection trajectory to improve the inspection efficiency. Finally, based on the tower pole distribution data from a simulated real-world environment, the proposed algorithm is employed to assign tasks of the UAVs and design trajectories. The simulation results confirm that the proposed algorithm can significantly reduce the total inspection time through multi-UAV task allocation and trajectory design.
An Overview on Multi-dimensional Expanded Integrated Sensing and Communication for 6G
XU Jinlei, ZHAO Junsheng, LU Huabing, JIANG Xu, ZHAO Nan
Available online  , doi: 10.11999/JEIT231045
Facing the demand for interconnectivity sensing of three-dimensional coverage for the sixth-Generation mobile communication (6G) networks and the spectrum scarcity issue caused by the widespread access of wireless devices, the multi-dimensional expanded Integrated Sensing and Communication (ISAC), based on Unmanned Aerial Vehicles (UAV) and Intelligent Reflecting Surfaces (IRS), is capable of achieving synergistic communication and sensing functions in the three-dimensional network space. This can effectively enhance spectrum efficiency, hardware resource utilization, and align with the wireless network vision of 6G Internet of Everything. This paper provides an overview of the architecture for the 6G multi-dimensional expanded ISAC. Firstly, it summarizes the theoretical foundations of the 6G network vision and ISAC networks, and the application scenarios, development trends, and performance indicators of multi-dimensional expanded ISAC based on UAV and IRS are discussed. Then, it investigates the potential applications of 6G key technologies, such as ultra-massive multiple-input and multiple-output antenna, terahertz, simultaneous wireless information and power transfer, artificial intelligence, covert communication, and active IRS, in multi-dimensional expanded ISAC networks based on UAV and IRS. Finally, we prospect the future development direction and key technical challenges of 6G multi-dimensional expanded ISAC.
Cost-Effective TMR Soft Error Tolerance Technique for Commercial Aerospace: Utilization of Approximate Computing
LI Yan, HU Yueming, ZENG Xiaoyang
Available online  , doi: 10.11999/JEIT231288
Triple Modular Redundancy (TMR), as the most prevalent and effective technique for soft error mitigation technique, inevitably incurs substantial hardware overhead while meeting high fault-tolerance requirements. To achieve the trade-off between area, power and fault coverage and meet the requirement of low-cost and high-reliability circuit design, Approximate Triple Modular Redundancy (ATMR) is investigated and a Dynamic Adjustment Multi-Objective Optimization Framework based on Approximate Gate Library (ApxLib+DAMOO) is investigated. The basic optimization framework employs Non-dominated Sorting Genetic Algorithm II (NSGA-II), achieving rapidly approximation through parity analysis and the pre-established ApxLib. Subsequently, the framework introduces two novel mechanisms: dynamic probability adjustment and parity expansion. The first mechanism dynamically updates the mutation probability of gates in the genetic algorithm based on testability analysis, while the second mechanism performs recognition and reconstruction for binate gates to achieve dual optimization of efficiency and effectiveness in optimization. Experimental results indicate that the proposed optimization framework achieves an additional Soft Error Rate (SER) reduction of up to 10%~20% compared to traditional NSGA-II with the same hardware overhead, while reducing 18.7% of execution time reduction averagely.
Optimized Design of Low Complexity SCMA System Assisted by Compressed Sensing
YU Lisu, ZHONG Run, LU Xinxin, WANG Yuhao, WANG Zhenghai
Available online  , doi: 10.11999/JEIT231226
Sparse Code Multiple Access (SCMA) technology is a highly valued code domain-based Non-Orthogonal Multiple Access (NOMA) technology. In order to solve the problem that the existing SCMA codebook design fails to combine the properties of data and decoder and the high complexity of MPA, a compressed sensing-assisted low-complexity SCMA system optimization design scheme is proposed. First, a codebook self-updating method is designed based on the system bit error rate optimization goal, which uses the gradient descent method to achieve self-updating of the codebook during the sparse vector reconstruction training process. Second, a compressed sensing-assisted multi-user detection algorithm is designed: Sign Decision Orthogonal Matching Pursuit (SD-OMP) algorithm. By sparse processing of the transmitted signal at the transmitting end, the compressed sensing technology is used at the receiving end to efficiently detect and reconstruct multi-user sparse signals, this results in a reduction of conflicts between users and a reduction in system complexity. The simulation results show that under Gaussian channel conditions, the compressed sensing-assisted low-complexity SCMA system optimization and design scheme can effectively reduce the complexity of multi-user detection, and can show better bit error rate performance when the system user part is active.
Executer Synchronization in Highly Reliable Information System with Dissimilar Redundancy Architecture
YU Hong, LIU Qinrang, WEI Shuai, LAN Julong
Available online  , doi: 10.11999/JEIT231048
Dissimilar redundancy architecture is widely used in information systems to improve their security and reliability. When the system operates normally, the executers behave consistently, but when faced with malicious attacks, the executers exhibit inconsistency. The architecture improves the security and reliability of the system by comparing the performance of the executers to monitor the system and perceive threats. The synchronization of executers is a challenge that all dissimilar redundancy architectures need to address. There is currently no systematic description and summary of synchronization technology. This article is a review of executer synchronization techniques in dissimilar redundancy architectures. First, the importance of synchronization in dissimilar redundancy systems is explained and a standardized description of synchronization is provided. Then, a synchronization technology classification method based on synchronization points is proposed and the basic process, popularity, advantages and disadvantages of each class are summarized separately. This article also proposes three important indicators that affect synchronization performance, namely synchronization point, false alarm rate, and performance, and provides a mathematical model for synchronization technology, which can be used for design evaluation. Finally, this article combines the development of cyber resilience and software defined system on wafer, and points out the potential and possible directions for the future development of synchronous technology.
Broadband High-Efficiency Continuous Inverse Class-F Power Amplifier Based on Input Harmonic Phase Control
HUANG Chaoyi, NIE Zening, XIONG Min
Available online  , doi: 10.11999/JEIT231202
The integration of satellite communication and ground mobile communication in a complementary manner has emerged as a prevailing trend, which means the wireless radio frequency front-end with Power Amplifier (PA) as the core need to tackle the dual challenges of high efficiency and large bandwidth. In this paper, the proposed input harmonic phase control method effectively overcomes the bottleneck of mutual restriction between bandwidth and efficiency. By employing a continuous inverse Class-F operating mode, it enables the reconstruction of transistor drain waveform through precise control of the input second harmonic phase. This approach ensures high efficiency, while significantly enhancing the impedance design space. Based on the expanded design space, a continuous inverse Class-F PA is designed and fabricated over the frequency band of 1.7-3.0 GHz. Experimental results demonstrate an output power of 40.6-42.8 dBm, accompanied by a drain efficiency ranging from 72.2% to 78.6%. Additionally, the gain of the designed PA ranges from 10.6 dB to 14.8 dB.
A Privacy-preserving Self-Sovereign Identity Scheme for Vehicular Ad hoc NETworks
GUO Xian, YUAN Jianpeng, FENG Tao, JIANG Yongbo, FANG Junli, WANG Jing
Available online  , doi: 10.11999/JEIT231092
A decentralized, revocable, and privacy-preserving Self-Sovereign Identity(SSI) solution based on blockchain is proposed to address digital identity management challenges for users in the context of the Vehicular Ad hoc NETworks (VANETs).The Road Side Unit (RSU) that authorized by a Trusted Authority (TA) form a committee are responsible for user registration,credential issuer and management.The threshold BLS signature and the Practical Byzantine Fault Tolerance(PBFT) consensus mechanism are uesd to create digital identity credentials to resolve the issues resulted in the centralized certification authorities. The combining secret sharing and zero-knowledge proof addresses privacy concerns during identity credential issuance and verification. The cryptographic accumulator is employed to tackle the revocation of user identity credentials in distributed storage scenarios. Finally, our comprehensive security analysis demonstrates the novel scheme can meet the proposed security objectives. The novel solution is implemented on an Ethereum private blockchain by using smart contracts, and experimental results show reliability, feasibility and effectiveness of our scheme.
Entropy-based Federated Incremental Learning and Optimization in Industrial Internet of Things
YANG Ruizhe, XIE Xinru, TENG Yinglei, LI Meng, SUN Yanhua, ZHANG Dajun
Available online  , doi: 10.11999/JEIT231240
In the face of large-scale, diverse, and time-evolving data, as well as machine learning tasks in industrial production processes, a Federated Incremental Learning(FIL) and optimization method based on information entropy is proposed in thispaper. Within the federated framework, local computing nodes utilize local data for model training, and compute the average entropy to be transmitted to the server to assist in identifying class-incremental tasks. The global server then selects local nodes for current round training based on the locally provided average entropy and makes decisions on task incrementality, followed by global model deployment and aggregation updates. The proposed method combines average entropy and thresholds for nodes selection in various situations, achieving stable model learning under low average entropy and incremental model expansion under high average entropy. Additionally, convex optimization is employed to adaptively adjust aggregation frequency and resource allocation in resource-constrained scenarios, ultimately achieving effective model convergence. Simulation results demonstrate that the proposed method accelerates model convergence and enhances training accuracy in different scenarios.
3D Coordinate-coupled Variable Structure Multiple Model Estimator for Maneuvering Target Tracking
ZHANG Hongwei, GAO Zhijian, ZHANG Yi
Available online  , doi: 10.11999/JEIT231290
In the 3D maneuvering target tracking, unknown prior and coordinate coupling errors can cause model-mode mismatch and state estimation bias. In this paper, the state transition matrices are modified based on the target velocity-orthogonal condition, the spherical feasible domain is approximated by using the primal-dual regularization, and the adaptive turn rate is combined in the frame of Unscented Kalman Filtering (UKF) to estimate the model-conditioned state, attaining the consistent output processing. 3D Variable Structure Multi-Model UKF (VSMMUKF) algorithm is derived. Simulation results show that, compared to the Multimode Importance UKF (MIUKF) algorithm, VSMMUKF can more accurately fit the maneuvering motion of 3D spatial point target with the comparable computational complexity; Compared to the Interactive Multi-Model Maximum Minimum Particle Filtering (IMM-MPF) algorithm, the filtering accuracy of VSMMUKF for tracking a fixed-wing Unmanned Aerial Vehicle (UAV) has improved by 2.8%~59.9%, and the overall computation burden has reduced an order of magnitude.
A 3D Multi Targets Track before Detect Algorithm with Self-Feedback Optimization of Dual Accumulation
BO Juntian, ZHANG Jiahao, WANG Guohong, YU Hongbo, ZHANG Xiangyu, WANG Wantian, WANG Hengfeng
Available online  , doi: 10.11999/JEIT240057
Considering the problem of 3D weak multi target detection, a 3-level Parallel-line-coordinate Transformation (PT) Track Before Detect (TBD) algorithm based on the dual accumulation self-feedback optimized is proposed in this paper. By introducing PT into TBD technology, the measurement points are transformed and accumulated sequentially on the normalized radial distance-time, azimuth angle-time and elevation angle-time planes, then the power accumulation are used to feedback optimize the binary accumulation, effectively mitigating the mutual interference between strong targets overwhelming weak targets and formation targets. Simulation results show that when the overall signal-to-clutter ratio reaches 10 dB, the overall detection probability of the proposed algorithm is close to 80%, demonstrating the effectiveness of the algorithm.
Research on Construction Methods of Low Correlation zone Complementary Sequence Sets
LIU Tao, WANG Yuhan, LI Yubo
Available online  , doi: 10.11999/JEIT231332
Perfect complementary sequence is a kind of signal with ideal correlation function, which is widely used in multiple access communication system, radar waveform design and so on. However, the set size of perfect complementary sequences is at most equal to the number of its subsequences. In order to expand the number of complementary sequences, the construction methods of aperiodic low correlation zone complementary sequence set are studied in this paper. First, two kinds of mapping functions on finite fields are proposed, and then two kinds of low correlation zone complementary sequence set with asymptotically optimal parameters are obtained. The number of these kinds of low correlation zone complementary sequence set are more than the perfect complementary sequence set, and which could support more users in the communication system.
Direct Acyclic Graph Blockchain-based Personalized Federated Mutual Distillation Learning in Internet of Vehicles
HUANG Xiaoge, WU Yuhang, YIN Hongbo, LIANG Chengchao, CHEN Qianbin
Available online  , doi: 10.11999/JEIT230976
Federated Learning (FL) emerges as a distributed training method in the Internet of Vehicle (IoV), allowing Connected and Automated Vehicles (CAVs) to train a global model by exchanging models instead of raw data, protecting data privacy. Due to the limitation of model accuracy and communication overhead in FL, in this paper, a Directed Acyclic Graph (DAG) blockchain-based IoV is proposed that comprises a DAG layer and a CAV layer for model sharing and training, respectively. Furthermore, a DAG blockchain-based Asynchronous Federated Mutual Distillation Learning (DAFML) algorithm is introduced to improve the model performance, which utilizes a teacher model and a student model to mutual distillation in the local training. Specifically, the teacher model with a lightweight network could achieve higher model accuracy, while the student model with a professional network could reduce the communication overhead in contrast. Moreover, to further improve the model accuracy, the personalized weight based on global epoch and model accuracy is designed to adjust the mutual distillation in the model updating. Simulation results demonstrate that the proposed DAFML algorithm outperforms other benchmarks in terms of the model accuracy and distillation ratio.
Status and Prospect of Hardware Design on Integrated Sensing and Communication
LIN Yuewei, ZHANG Qixun, WEI Zhiqing, LI Xingwang, LIU Fan, FAN Shaoshuai, WANG Yi
Available online  
The Integrated Sensing And Communication (ISAC) requires that communication and sensing share the same radio frequency band and hardware resource. The characteristics of multi bands, large bandwidth, communication and sensing’s different requirements for hardware put forward higher requirements for ISAC hardware design. The hardware designs, verification technologies and systemic hardware verification platforms of beyond 5G, 6G and WiFi ISACs are summarized. The relevant hardware designs and verification researches at home and abroad in recent years are summarized also. The hardware design challenges such as the hardware requirement contradictions between communication and sensing systems, the In Band Full Duplex (IBFD) Self-Interference Cancellation (SIC), the Power Amplifier (PA) efficiency, and the more accurate modeling required by circuit performance are paid attention to. First of all, the design of ISAC transceiver architectures in existing researches are summarized and compared. Then, the existing ISAC IBFD self-interference suppression schemes, the low Peak to Average Power Ratio (PAPR) waveform or high-performance PA designs, the high precision device modeling methods and the systemic hardware verification platforms are introduced and analyzed. At last, the full text is summarized, the future open issues for ISAC hardware design is analyzed.
Broadband Fusion of Multiband Radar Signals Based on Optimal Dictionary Selection
LU Ruimin, LI Weidong, WANG Rui, ZHANG Fan, LI Muyang, HU Cheng
Available online  , doi: 10.11999/JEIT231309
Multiband Fusion is an effective way to broaden bandwidth of radar, which plays a key role in the detection and recognition of small-scale target. However, the existing multiband fusion algorithms still face the problems of slow operation and low precision. Therefore, a super-resolution technique of multiband fusion based on optimal dictionary selection and orthogonal matching pursuit is proposed in this paper. Firstly, the parametric model of multiband radar signal is conducted. Next, Snake Optimizer (SO) is applied to the coherent processing. Then, an Orthogonal Matching Pursuit (OMP) algorithm based on the optimal Geometrical Theory of Diffraction (GTD) dictionary selection is used to extrapolate the vacant spectrum. Experiment results of simulated and measured data are given. Experimental results show that the proposed method can effectively achieve super-resolution. This method combines simplified model rough estimation with complete model fine estimation, effectively reducing the amount of computation and realizing fast and accurate multiband fusion extrapolation processing.
Infrared and Visible Light Image Fusion Network with Multi-Relation Perception
LI Xiaoling, CHEN Houjin, LI Yanfeng, SUN Jia, WANG Minjun, CHEN Luyifu
Available online  , doi: 10.11999/JEIT231062
A multi-relation perception network for infrared and visible image fusion is proposed in this paper to fully integrate consistent features and complementary features between infrared and visible images. First, a dual-branch encoder module is used to extract features from the source images. The extracted features are then fed into the fusion strategy module based on multi-relation perception. Finally, a decoder module is used to reconstruct the fused features and generate the final fused image. In this fusion strategy module, the feature relationship perception and the weight relationship perception are constructed by exploring the interactions between the shared relationship, the differential relationship, and the cumulative relationship across different modalities, so as to integrate consistent features and complementary features between different modalities and obtain fused features. To constrain network training and preserve the intrinsic features of the source images, a wavelet transform-based loss function is developed to assist in preserving low-frequency components and high-frequency components of the source images during the fusion process. Experiments indicate that, compared to the state-of-the-art deep learning-based image fusion methods, the proposed method can fully integrate consistent features and complementary features between source images, thereby successfully preserving the background information of visible images and the thermal targets of infrared images. Overall, the fusion performance of the proposed method surpasses that of the compared methods.
Broadband Spatial Self-Interference Cancellation for Full Duplexing Array
LIN Lang, ZHAO Hongzhi, SHAO Shihai, TANG Youxi
Available online  , doi: 10.11999/JEIT231036
The multi-functional integrated platform with simultaneous transmit and receive capability faces the strong Self-Interference (SI) coupled between the adjacent transmit and receive arrays. In this paper, a wideband SI cancellation method in the space domain for fully digital phased array systems is designed. A non-convex optimization problem is formulated to minimize the residual SI and noise power while constraining the loss of beamforming gain in the desired direction, and an alternate optimization method is proposed to jointly determine the transmit and receive beamforming weights, and the SI cancellation performance of the proposed algorithm is analyzed. Theoretical analysis and simulation results show that a 60-element array can achieve an Effective Isotropic Isolation (EII) of 168 dB when the central frequency is 2.4 GHz, the bandwidth is 100 MHz, and the beamforming gain loss is limited to 3 dB, which is 7 dB below the EII upper bound.
Shortest Delay Routing Protocol for UAV Formation with Discrete Time Aggregation Graph
LI Bo, WANG Gaifang, YANG Hongjuan, RU Xuefei, ZHANG Jingchun, WANG Gang
Available online  , doi: 10.11999/JEIT230707
Aiming at the problems that the traditional UAV formation routing algorithm cannot effectively utilize the advance predictability of topology changes, and the high cost is caused by acquiring the link connection by sending detection packets, a UAV formation shortest delay routing protocol based on discrete time aggregation graph is proposed by introducing the time-varying graph model. Firstly, using the prior knowledge of the UAV formation network, such as the movement trajectory of nodes and the network topology changes, the network link resources and network topology are characterized by using the discrete time aggregation graph. Secondly, the routing decision algorithm is designed based on the graph model. The delay in the process of route discovery is used as the link weight to solve the shortest delay route from the source node to the destination node of the network. Finally, the simulation performance shows that the routing protocol improves the packet delivery rate, reduces the end-to-end delay and diminishes the network control overhead compared with the traditional Ad-hoc On-Demand Distance Vector routing protocol.
6G New Time-delay Doppler Communication Paradigm: Technical Advantages, Design Challenges, Applications and Prospects of OTFS
LIAO Yong, LUO Yu, JING Yahao
Available online  , doi: 10.11999/JEIT231133
In the future communication network, the sixth generation mobile communication system technology(6G), which is widely expected, will face many challenges, including the issue of ultra-reliable communication in high-speed mobile scenarios. Orthogonal Time Frequency Space (OTFS) modulation technology overcomes the multi-path and Doppler effects of traditional communication systems in high-speed mobile environments, and provides a new possibility for realizing 6G ultra-reliable communication. This paper first introduces the basic principle, mathematical model, interference and advantage analysis of OTFS. Then, the research status of OTFS technology in synchronization, channel estimation and signal detection is summarized and analyzed. Then, the application trend of OTFS is analyzed from four typical application scenarios of vehicle networking, unmanned aerial vehicle, satellite communication and marine communication. Finally, the difficulties and challenges to be overcome in future OTFS research are discussed from four aspects: reducing multi-dimensional matching filter, phase demodulation and channel estimation, hardware implementation complexity and improving the high utilization of time-frequency resources.
Resource Allocation Algorithm of Space-Air-Ground Integrated Network for Dense Scenarios
ZHANG Hong, LIAO Yuxin, WANG Ruyan, WU Dapeng, DU Huimin
Available online  , doi: 10.11999/JEIT231086
Space-air-ground integrated network has the advantages of extensive coverage, high throughput, and strong elasticity. A resource allocation algorithm for dense scenarios is proposed to solve the problems of network congestion and deterioration of service quality caused by concurrent access of many users and network load imbalance. Firstly, the user utility function is constructed based on the user demand and the preferences of different types of user tasks. Then, load balancing is realized based on the matching game network selection algorithm and the power control algorithm combined with the dual ascending method, and the resource allocation scheme is optimized. Experimental results show that compared with the traditional strategy, the proposed strategy increases the overall user access rate by at least 35%, and improves the performance of delay and throughput by more than 50%. Load balancing is more effective in dense scenarios and network performance is improved.
Research on the Double Layer Coupling Dynamic Information Propagation Model of the Internet of Things
ZHANG Yuexia, CHANG Fengde
Available online  , doi: 10.11999/JEIT231291
The study of information dissemination models is an important component of the Internet of Things field, which helps to improve the performance and efficiency of IoT systems, promote the further development of IoT technology. In response to the complex and unstable factors that affect information dissemination in IoT communication, a double-layer coupled information dissemination model SIVR-UAD (Susceptible, Infection, Variant, Recovered-Unknown, Aware, Disinterest) is proposed, which analyzes the impact of devices and users in different states on information dissemination in the Internet of Things, Six coupling states were established, and the Markov method was used to analyze the state change process of the coupling nodes, finding the information dissemination equilibrium point. Finally, the uniqueness and stability of the equilibrium point of the model were proved through theoretical analysis. The simulation results show that under three different initial coupling node numbers, the number of six coupling nodes in the SIVR-UAD model always tends to the same stable level, proving the equilibrium point and stability of the model.
Multitask Collaborative Multi-modal Remote Sensing Target Segmentation Algorithm
MAO Xiuhua, ZHANG Qiang, RUAN Hang, YANG Yuang
Available online  , doi: 10.11999/JEIT231267
The use of semantic segmentation technology to extract high-resolution remote sensing image object segmentation has important application prospects. With the rapid development of multi-sensor technology, the good complementary advantages between multimodal remote sensing images have received widespread attention, and joint analysis of them has become a research hotspot. This article analyzes both optical remote sensing images and elevation data, and proposes a multi-task collaborative model based on multimodal remote sensing data (United Refined PSPNet, UR-PSPNet) to address the issue of insufficient fusion classification accuracy of the two types of data due to insufficient fully registered elevation data in real scenarios. This model extracts deep features of optical images, predicts semantic labels and elevation values, and embeds elevation data as supervised information, to improve the accuracy of target segmentation. This article designs a comparative experiment based on ISPRS, which proves that this algorithm can better fuse multimodal data features and improve the accuracy of object segmentation in optical remote sensing images.
Communication and sensing performance analysis of RIS-assisted SWIPT-NOMA system under non-ideal conditions
LI Xingwang, WANG Xinying, TIAN Xinji, WANG Xinshui, QIN Panke, CHEN Hui
Available online  , doi: 10.11999/JEIT231395
To meet the escalating demands for efficient communication and reliable sensing, a Reconfigurable Intelligent Surface(RIS)-assisted Simultaneous Wireless Information and Power Transfer(SWIPT)-Non-Orthogonal Multiple Access(NOMA) system is proposed in this paper. This system is designed to concurrently achieve target sensing and information transmission. Considering the imperfections of Successive Interference Cancellation (SIC) and Channel Estimation Error (CEE), a comprehensive analysis of the system’s reliability, effectiveness, and radar sensing performance is conducted. Analytical expressions for the Outage Probability (OP), Ergodic Rate (ER), Probability of Detection (PoD), and Radar Estimation Information. Rate (REIR) of the system are derived to provide insights into its performance. The analysis results reveal the following findings: the presence of imperfect SIC and CEE adversely impacts the system’s performance; the OP diminishes as the transmitted power of base station increases, eventually converging to a constant value in the high Signal-to-Noise Ratio (SNR) region; both the ER and the REIR increase with the base station’s transmitted power and eventually stabilize at an upper limit value in the high SNR region; the PoD increases with the base station’s transmit power at different detection thresholds; the Joint Radar Detection and Communication Coverage Probability (JRDCCP) decrease with the outage threshold and detection threshold, respectively.
Switched-Capacitor DC-DC Converter: Evolution from Transformer Model to Circuitry
HUANG Mo, CHEN Zhongjun, XIA Tian, YANG Zaitian
Available online  , doi: 10.11999/JEIT231216
SC DC-DC converters have wide applications. Previous works proposed multiple topologies for a high voltage conversion ratio scenario, such as Dickson, Cockcroft-Walton, Series-Parallel, Ladder, Fibonacci and Divider. They have their own features, fitting different applications. However, it is unclear how these topologies are generated, what the main differences are between them, and what the advantages and disadvantages are. Therefore, this paper starts from the transformer model of the SC converters, analyzing the difference among them. Then, it is demonstrated how the SC converters evolve from the model to the real circuitries, where multiple intuitive understanding can be obtained.
Research Progress in Multi-Mode Integration and Dynamic Regulation of Microwave Band Vortex Beams
YUAN Yueyi, YANG Desheng, LIU Yunfei, ZHANG Kuang
Available online  , doi: 10.11999/JEIT231211
This article reviews and summarizes the recent researches on vortex beam multimode integration and dynamic regulation. Starting from the passive metasurface lens, utilizing the comprehensive control effect of propagation phase and geometric phase, fractional modes of vortex beam with high-purity is realized on a single metasurface platform. Furthermore, based on the theory and method about multimode vortex beam integration by using passive metasurfaces, active tunable electromagnetic devices such as varactors are loaded into the metasurface unit cell to adopt dynamic switching and manual regulation of vortex beams. On this basis, a theoretical analysis and evaluation of the performance of vortex communication systems based on metasurface is conducted through channel modeling, laying a theoretical foundation for improving the channel capacity and information transmission rate of modern communication systems.
UAV Path Planning Method for Passive Radar Transmitter Localization
WAN Xianrong, WU Bingqian, YI Jianxin, HU Shibo
Available online  , doi: 10.11999/JEIT231293
In the broad and unknown environments, mobile deployment of passive radar often faces challenges in promptly obtaining the precise location information of third-party transmitter stations. To address this issue, a transmitter localization method based on cooperative Unmanned Aerial Vehicle (UAV) path planning is proposed. Firstly, a single UAV is used as a cooperative target to establish the localization model and measurement equation in a two-dimensional scenario, and the Levenberg-Marquardt (LM) algorithm is employed for solution. Then, an optimization function is constructed by integrating Fisher information and control parameter constraints to dynamically plan the UAV trajectory, thereby improving the accuracy of transmitter localization and the practicality of this method. Finally, simulation experiments show that under the maximum control distance constraint, the positioning result of the proposed method is better than that of straight-line track and typical optimized track, and the final positioning accuracy is less than the standard deviation of the bistatic distance difference measurements, which can meet the application requirements of the passive radar system.
Design of High Throughput True Random Number Generator Based on Metastability Superposition Cells
NI Tianming, YU Junyong, PENG Qingsong, NIE Mu
Available online  , doi: 10.11999/JEIT231166
True Random Number Generator (TRNG), as an important hardware security primitive, is used in key generation, initialization vector and identity authentication in protocols. In order to design a lightweight TRNG with high throughput, the method of generating metastability is studied by using the switching characteristics of MUltipleXer (MUX) and XOR gate, and a TRNG design based on Metastability Superposition (MS-TRNG) cell (MS-cell) is proposed. It superimposes MUX and XOR gate guided metastases, thereby increasing the entropy of TRNG. The proposed TRNG is implemented in Xilinx Virtex-7 and Xilinx Artix-7 FPGA development boards, respectively, without the need for post-processing circuits. Compared to other advanced TRNGS, the proposed TRNG has the highest throughput and extremely low hardware overhead, and the random sequences it generates pass NIST testing and a series of performance tests.
High-precision Direction Finding Based on Time Modulation Array with Single Radio Frequency Channel and Composite Baselines
LIN Yulong, WANG Wuji, WU Junwei, CHENG Qiang
Available online  , doi: 10.11999/JEIT231137
With the rapid developments of positioning systems, high-precision and low-cost direction-finding technologies are urgently needed. The hardware complexity and economic cost of traditional direction-finding methods have hindered their wide applications. Recently, direction finding based on Time-Modulated Arrays (TMAs) has overcome the shortcomings of traditional direction-finding methods. Nevertheless, to ensure measurement accuracy, one has to keep an adequate number of array elements in common TMAs. Consequently, a question arises, i.e., is it possible to reduce the number of array elements in TMAs, thus making the hardware complexity as low as possible? A novel direction-finding method based on the TMA with a single radio frequency channel and composite baselines is proposed in this paper. In the method, four antennas are meticulously arranged at specific intervals to form double-long baselines, and accurate and low-cost direction finding is realized with the ingenious usage of Field Programmable Gate Array (FPGA) and single receiving channel. To verify the effectiveness of the method, a prototype system in the S band is designed, fabricated, and measured. Detailed comparisons with the existing methods are provided. The work will benefit the development and application of high-precision and low-cost direction-finding systems.
Depression Intensity Recognition Based on Perceptually Locally-enhanced Global Depression Features and Fused Global-local Semantic Correlation Features on Faces
SUN Qiang, LI Zheng, HE Lang
Available online  , doi: 10.11999/JEIT231330
For automatic recognition of the depression intensity in patients, the existing deep learning based methods typically face two main challenges: (1) It is difficult for deep models to effectively capture the global context information relevant to the level of depression intensity from facial expressions, and (2) the semantic consistency between the global semantic information and the local one associated with depression intensity is often ignored. One new deep neural network for recognizing the severity of depressive symptoms, by combining the Perceptually Locally-Enhanced Global Depression Features and the Fused Global-Local Semantic Correlation Features (PLEGDF-FGLSCF), is proposed in this paper. Firstly, the PLEGDF module for the extraction of global depression features with local perceptual enhancement, is designed to extract the semantic correlations among local facial regions, to promote the interactions between depression-relevant information in different local regions, and thus to enhance the expressiveness of the global depression features driven by the local ones. Secondly, in order to achieve full integration of global and local semantic features related to depression severity, the FGLSCF module is proposed, aiming to capture the correlation of global and local semantic information and thus to ensure the semantic consistency in describing the depression intensity by means of global and local semantic features. Finally, on the AVEC2013 and AVEC2014 datasets, the PLEGDF-FGLSCF model achieved recognition results in terms of the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE) with the values of 7.75/5.96 and 7.49/5.99, respectively, demonstrating its superiority to most existing benchmark methods, verifying the rationality and effectiveness of our approach.
Research on High-resolution 3D Imaging and Point Cloud Clustering of Array SAR
JI Ang, PEI Hao, ZHANG Bangjie, XU Gang
Available online  , doi: 10.11999/JEIT231223
Compared with traditional Two-Dimensional (2D) Synthetic Aperture Radar (SAR) imaging, Three-Dimensional (3D) SAR imaging technology can overcome problems such as overlay and geometric distortion, thus having broad development space. As a typical 3D imaging system, the elevation resolution of array SAR is generally limited by the array aperture in theory, which is much lower than the range and azimuth resolution. To address this issue, an assumption of consistency in elevation between neighboring pixels is introduced and a re-weighted locally joint sparsity based Compressed Sensing (CS) approach is proposed for the array super-resolution imaging in the height dimension. Then, typical clustering methods such as K-means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) are used to achieve clustering analysis of specific targets (such as buildings and vehicles) in the observation scene. Finally, the experimental analysis using measured data is performed to confirm the effectiveness of the proposed algorithm.
Age of Information Analysis and Optimization in Unmanned Aerial Vehicles-assisted Integrated Sensing and Communication Systems
YU Baoquan, YANG Weiwei, WANG Quan, ZHANG Ruoyu, CAI Yueming
Available online  , doi: 10.11999/JEIT231175
In many monitoring and control tasks, it is difficult for the control center to get the real-time status information directly because of the distance between the monitored target and the control center. The Unmanned Aerial Vehicles (UAV) can make full use of its advantages of high mobility, reduce the sensing and communication distance, and then improve the sensing and communication capabilities, which provides a new idea for real-time acquisition of remote target status information. In this paper, the optimization problem of Age of Information (AoI) analysis in UAV-assisted integrated sensing and communication system is studied. Firstly, the status update process of control center is analyzed, and then the closed-form expression of average peak AoI is derived. Further, in the multi-UAV multi-target scenario, the average peak AoI of the system is further reduced by optimizing the perception position and communication position of the UAV in the air, as well as the matching relationship between the UAV and the target, and the real-time status update is improved. The simulation results verify the correctness of the theoretical analysis, and show that the proposed optimization method can effectively improve the AoI performance of the system compared with the benchmark methods.
Low-intercept Waveform Sequence Design Based on Iterative Quadratic Optimization Algorithm
LIU Qiang, ZHANG Min, GUO FuCheng, YIN JiaPeng, HU WeiDong
Available online  , doi: 10.11999/JEIT231333
In modern radar technology, a key research area is the design of special waveforms to prevent non-cooperative electronic reconnaissance systems from intercepting and detecting radar signals. This paper focuses on reducing the power interception probability of electronic reconnaissance systems while maintaining the radiation energy. Specifically, waveform design techniques are explored for passive countermeasures, considering the time-frequency distribution of energy and the characteristics of Short-Time Fourier Transform (STFT) wideband digital reconnaissance receivers. To address this, a low-intercept model for STFT wideband digital reconnaissance receiver is established, and then the low-intercept problem is converted into a constant envelope sequence iterative optimization problem using a quadratic optimization model. To improve autocorrelation performance, an auxiliary scalar is employed to transform the optimization model into a quadratic form and a sequence of low-interception waveforms are generated through an iterative algorithm. Furthermore, the computational complexity of our proposed method is discussed. The simulation results, demonstrate that our sequence exhibits superior low-interception capability compared to commonly used phase-coded signals at the same receive Signal-to-Noise Ratio (SNR). Additionally, we introduce Pareto weights are introduced to control the autocorrelation characteristics of the proposed sequence, thereby enhancing the design flexibility.
Shared-aperture Jammer Assisted Covert Communication Using Time Modulated Array
MA Yue, MA Ruiqian, YANG Weiwei, LIN Zhi, MIAO Chen, WU Wen
Available online  , doi: 10.11999/JEIT231115
The short packet covert communication using a shared-aperture jammer assisted Time-Modulated Array (TMA) is investigated for the first time in this paper. Firstly, a TMA architecture for shared-aperture jammer is proposed and an optimization method is introduced that maximizes the gain of the target direction while forming interference in non-target directions. Based on this model, closed-form expressions for the covertness constraint and covert throughput are derived. Furthermore, the transmission power and blocklength are optimized to maximize the covert throughput. Simulation results show that there exists an optimum blocklength that maximizes the covert throughput, and the proposed scheme outperforms the benchmark scheme in terms of covert communication performance.
Range-Doppler Imaging Algorithm for Multireceiver Synthetic Aperture Sonar
ZHANG Xuebo, WANG Yanmei, YANG Jiachong, SHEN Wenyan, SUN Haixin
Available online  , doi: 10.11999/JEIT231160
Traditional multireceiver Synthetic Aperture Sonar (SAS) imaging algorithms based on Phase Center Approximation (PCA) neglect the spatial variance of approximation error in the azimuth dimension. The distortion would be introduced in the focused results of distributed. To solve this problem, a two-way slant range considering the azimuth variance of approximation error is deduced based on the geometry models of transmitter/receiver bistatic sampling and PCA sampling. The system function in the 2D frequency domain is further decomposed into transmitter/receiver bistatic deformation term and quasi monostatic term. Based on that, the complex multiplication and interpolation are adopted to compensate the bistatic deformation term. Then, the range-Doppler imaging algorithm is used to focus the targets. Compared to traditional methods, much smaller appropriation error across the whole mapping swath is obtained by using the proposed. Besides, the position deviation in the azimuth dimension is not introduced by the proposed method. The imaging result which is identical to practical target position can be obtained.
Survey on Optimised Design of Robust Chaotic Transmission Systems for Impulsive Noise under Power Line Communication Channels
MIAO Meiyuan, TIAN Feng, WANG Lin, DAI Zhou
Available online  , doi: 10.11999/JEIT231142
With the drastic increase in the number of users, the existing wireless resources have become unsustainable. Therefore, the reactivation of Power Line Communication (PLC) has attracted the attention of major research institutes and industries. The development of PLC has been slow due to the complexity of the channel environment and the complexity and high cost of existing processing solutions. The most extensive work has been done on impulse noise, and it is particularly important to achieve robustness of data transmission against impulse noise at low cost. Firstly, the mainstream noise in PLC environment and its classification are introduced in this paper, and then the Differential Chaos Shift Keying (DCSK) and M-ary DCSK (MDCSK) modulation techniques with low cost and low complexity are described. The characteristics of this system in PLCs are presented and analysed, as well as the advantages and improvements that exist for various types of impulse noise. Secondly, some relevant new coding and modulation schemes are introduced in order to improve the transmission quality in band-limited environments. The results show that these optimisations significantly improve the system performance. Subsequently, modulation and coded modulation transmission optimisation schemes for PLC overall channel characteristics system parameters will be a hot topic for future work.
ErlangShen: Efficient Transaction Execution Mechanism for Graphical Blockchain Based on Pipeline with Low Access Cost
XIAO Jiang, WU Enping, ZHANG Shijie, FU Zihao, JIN Hai
Available online  , doi: 10.11999/JEIT230874
Directed Acyclic Graph(DAG)-based blockchain can significantly improve system performance and have become a research topic in both academia and industry. Compared with the traditional chain-based blockchains with serialization, DAG-based blockchains can process multiple blocks concurrently to package significant transactions into the chain. With the surge in transaction throughput, DAG-based blockchain faces the issue of low transaction execution efficiency, i.e., the demand for state data access for massive transaction execution increases dramatically, resulting in high Input/Output(I/O) overhead. Enabling low I/O state access mainly encounters two new challenges. On the one hand, if DAG-based blockchain directly adopts the traditional state prefetch mechanism, it will introduce a large number of stale reads due to inconsistent execution logic. On the other hand, state access for different accounts causes duplicate I/O overhead in the upper nodes of the Merkle tree. To this end, an efficient transaction execution mechanism based on pipelining – ErlangShen is designed, including the epoch granularity state prefetch mechanism and Merkle high-level path buffer mechanism to reduce the number of stale reads and duplicate I/O overhead, respectively. Specifically, ErlangShen leverages the complicated logic and severe conflicts of transactions accessing hotspot states to parallelize the execution of hotspot transactions and the prefetch of states accessed by cold transactions, to avoid the implication of the state prefetching on the transaction execution. Furthermore, the customized concurrency control methods is designed according to the data access pattern of hotspot and cold states to further improve the system throughput. Experimental results show that ErlangShen can reduce the number of stale reads by about 90% and improve transaction processing performance by 3~4x compared to Nezha, the state-of-the-art DAG-based blockchain transaction processing solution.
Overview of Holographic Multiple-Input Multiple-Output Technology for 6G Wireless Networks
CHEN Xiaoming, WEI Jianchuan, HUANG Chongwen
Available online  , doi: 10.11999/JEIT231140
The future Sixth-Generation (6G) wireless communication systems are required to support ultra-large-scale user demands, with increasing demands for spectrum efficiency and energy efficiency. In this context, Holographic Multiple-Input Multiple-Output (HMIMO) technology has gained increasing attention due to its potential for intelligent reconfigurability, electromagnetic tunability, high directional gain, cost-effectiveness, and flexible deployment. In holographic MIMO system, large amount small and cheap antenna units are integrated tightly, thus realize high directional gain at a low hardware cost and flexible adjustment of electromagnetic wave at the same time, thereby effectively enhance the performance of wireless communication. A brief introduction to holographic MIMO technology is provided at the start of this paper, covering its current status, development process, classification, and key characteristics. Subsequently, the channel model for holographic MIMO in line-of-sight scenarios and non-line-of-sight scenarios with spatially smooth scattering is presented. Finally, the challenges and future trends faced by holographic MIMO technology are described, and the article is concluded.
Survey of Satellite-ground Channel Models for Low Earth Orbit Satellites
SU Zhaoyang, LIU Liu, AI Bo, ZHOU Tao, HAN Zijie, DUAN Xianglong, ZHANG Jiachi
Available online  , doi: 10.11999/JEIT230941
Low Earth Orbit (LEO) satellite has the characteristics of low communication delay, low deployment cost and wide coverage, and has become an important part of the construction of the future space earth integrated network. However, satellite communication has large end-to-end propagation distance, complex fading and fast terminal movement speed, thus the channel characteristics are very different from the terrestrial cellular network. Based on this, in order to have a more comprehensive understanding of the characteristics and channel model of LEO satellite-ground channel, the current standardization progress of the satellite-ground channel by the international standards organization are summarized, the fading characteristics of the satellite ground channel at different propagation positions are discussed, the existing important channel models are classified and shown according to the modeling method, and finally the prospects for future work are proposed.
Low-power Communication and Control Joint Optimization for Service Continuity Assurance in Aerial-Ground Integrated Networks
CAI Ziwei, SHENG Min, LIU Junyu, ZHAO Chenxi, LI Jiandong
Available online  , doi: 10.11999/JEIT231192
The Aerial-Ground Integrated Networks (AGIN) take full advantage of the flexible deployment of Aerial Base Stations (ABSs) to provide on-demand coverage and high-quality services in hotspot areas. However, the high dynamics of ABSs pose a great challenge to service continuity assurance in AGIN. Furthermore, given the energy constraints of ABSs, ensuring service continuity with low power consumption becomes an increasingly formidable challenge. This is attributed to the inherent contradiction between enhancing service continuity and reducing power consumption, which typically necessitates distinct flight actions. Focusing on the problem mentionde above, a communication and control joint optimization approach based on Federated Deep Reinforcement Learning (FDRL) is proposed to obtain low-power service continuity assurance in AGIN. The proposed approach ensures service continuity by jointly optimizing the flight actions of ABSs, user associations, and power allocation. To cope with the high dynamics of ABSs, an environmental state experience pool is designed to capture the spatiotemporal correlation of channels, and the rate variance is introduced into the reward function to ensure service continuity. Taking into account the power consumption differences associated with various flight actions, the proposed approach optimizes the flight actions of ABSs to reduce their power consumption. Simulation results demonstrate that, under the premise of satisfying requirements for user rate and rate variance, the proposed approach can effectively reduce network power consumption. Additionally, the performance of FDRL is close to that of centralized reinforcement learning.
Robust Resource Allocation Algorithm for Reconfigurable Intelligent Surface-assisted Backscatter Communication Systems Based on Statistical Channel State Information
XU Yongjun, XU Juan, TIAN Qinyu, HUANG Chongwen
Available online  , doi: 10.11999/JEIT231169
In order to solve the problems of short-distance communication, lower system throughput and the effects of channel uncertainties in traditional Backscatter Communication (BackCom) systems, a robust resource allocation algorithm for a Reconfigurable Intelligent Surface (RIS)-assisted backscatter communication system with statistical Channel State Information (CSI) is proposed in this paper. A system weighting and sum throughput-maximization robust resource allocation model is formulated by considering the maximum transmit power constraint of the power station, the energy outage constraint and throughput outage constraint of backscatter nodes, the reflection coefficient constraint, the phase shift constraint of the RIS and the information transmission time constraint; Then, the original non-convex problem is transformed into a convex optimization problem by using the methods of Bernstein-type inequality, the alternating optimization, and the semi-definite relaxation technique. An iteration-based robust throughput maximization algorithm is designed. Simulation results show that the proposed algorithm had stronger robustness and higher throughput compared it with the traditional non-robust resource allocation algorithm and the resource allocation algorithm without RIS.
Design of Strong Physical Unclonable Function Circuit Against Machine Learning Attacks Based on Chaos Mapping
WANG Pengjun, FANG Haoran, LI Gang
Available online  , doi: 10.11999/JEIT231129
Physical Unclonable Function (PUF) has broad application prospects in the field of hardware security, but it is susceptible to modeling attacks based on machine learning. By studying the strong PUF circuit structure and chaotic mapping mechanism, a PUF circuit that can effectively resist machine learning modeling attacks is proposed. This circuit takes the original excitation as the initial value of the chaotic mapping, utilizes the internal relationship between the PUF excitation response mapping time and the iteration depth of the chaotic algorithm to generate unpredictable chaotic values, and uses PUF intermediate response feedback to encrypt the excitation. It can further improve the complexity of excitation and response mapping, thereby enhancing the resistance of PUF to machine learning attacks. The PUF is implemented using Artix-7 FPGA. The test results show that even with up to 1 million sets of excitation response pairs selected, the attack prediction rate based on logistic regression, support vector machine, and artificial neural network is still close to the ideal value of 50%. And the PUF has good randomness, uniqueness, and stability.
A Survey of Collaborative of Swarm Intelligence for Evolutionary Computation
GONG Maoguo, LUO Tianshi, LI Hao, HE Yajing
Available online  , doi: 10.11999/JEIT231195
The rapid development of swarm intelligence, represented by evolutionary computation, has triggered a new wave of technological transformation in the field of artificial intelligence. To meet the diverse application needs of complex systems, artificial intelligence is increasingly moving towards cross-level intelligent and collaborative research. In this paper, the concept of swarm intelligence cooperation oriented towards evolutionary computation is proposed. Based on the hierarchical levels of swarm intelligence cooperation, artificial intelligence research across different levels is categorized into micro-level cooperation, meso-level cooperation, and macro-level cooperation. From the perspective of swarm intelligence cooperation, a summary is provided on recent research in the aforementioned branches. Firstly, the micro-level cooperation is discussed by analyzing decision variable level cooperation and global/local level cooperation. Secondly, the meso-level cooperation is summarized from the dimensions of objective-level cooperation and task-level cooperation. Furthermore, an analysis of macro-level cooperation is conducted through the examination of space-air-ground-sea cooperation, vehicle-road-cloud cooperation, and edge-cloud cooperation in intelligent collaborative systems. Finally, the research challenges in the field of swarm intelligence cooperation oriented towards evolutionary computation are identified, and future directions for related fields are proposed.
A Review of the Artificial Intelligence-based Image Classification of Fishes in the Global Oceans
ZHOU Peng, LI Changyong, BU Yuxin, ZHOU Zhinuo, WANG Chunsheng, SHEN Hongbin, PAN Xiaoyong
Available online  , doi: 10.11999/JEIT231365
Understanding the species composition, abundance and temporal and spatial distribution of fish on a global scale will help their biodiversity conservation. Underwater image acquisition is one of the main means to survey fish species diversity, but image data analysis is time-consuming and labor-intensive. Since 2015, a series of progress has been made in updating the datasets of marine fish images and optimizing the algorithm of deep learning models, but the performance of fine-grained classification is still insufficient, and the production practice application of research results is relatively weak. Therefore, the need for automated fish image classification in marine investigations is firstly studied. Then a comprehensive introduction to fish image datasets and deep learning algorithm applications is provided, and the main challenges and the corresponding solutions are analyzed. Finally, the importance of automated classification of marine fish images for related image information processing research is discussed, and its prospects in the field of marine monitoring are summarized.
Electromagnetic Channel Modeling Theory and Approaches for Holographic MIMO Wireless Communications
HUANG Chongwen, JI Ran, WEI Li, GONG Tierui, CHEN Xiaoming, SHA Wei, YANG Jun, ZHANG Zhaoyang, Yuen Chau
Available online  , doi: 10.11999/JEIT231219
Holographic Multiple-Input Multiple-Output (HMIMO) is an emerging technology for 6G communications. This type of array is composed of densely distributed antenna elements within a fixed aperture area. It is an extension of Massive MIMO technology under the practical constraints of antenna aperture. HMIMO systems have great potential in significantly improving wireless communication performance. However, due to the presence of closely spaced antennas, and the distane between antennas is less than half of the length, severe coupling effects are inevitable and traditional assumption of independent and identically distributed channel is invalid. Thus, designing an effective and practical channel model becomes one of the most challenging problems in HMIMO researches. To address these challenges, this paper investigates four channel modeling approaches based on electromagnetic field theory. The first approach is based on the plane Green’s function and models the integral of Green’s functions between planes with high complexity. The second and third approaches approximate the communication channel in HMIMO using plane wave expansion and spherical wave expansion, respectively, with lower complexity. The channel modeling based on plane wave expansion is relatively simple and is more suitable for far field, but would underestimate the maximum capacity of the system under strong coupling between antennas. The channel modeling based on spherical wave expansion better captures the characteristics of the electromagnetic wave channel but comes with higher complexity. Finally, a channel modeling method based on random Green’s functions is introduced, primarily describing the random characteristics of electromagnetic waves in rich scattering environments or Rayleigh channels.
Wireless Multimodal Communications for 6G
REN Chao, DING Siying, ZHANG Xiaoqi, ZHANG Haijun
Available online  , doi: 10.11999/JEIT231201
An overview of multimodal communication as an important information transfer mode that can simultaneously interact with multiple modal forms in different application scenarios is proposed in this paper. The future development prospects of multimodal communication in 6G wireless communication technology is also discussed. Firstly, multimodal communication is classified into three categories, and its key roles in these fields are explored. Furthermore, a deep analysis is conducted on the communication, sensation, computation, and storage resource limitations, as well as cross-domain resource management issues that 6G wireless communication systems may face. It points out that future 6G wireless multimodal communication will achieve deep integration of communication perception, computation, and storage, as well as enhance communication capabilities. In the process of implementing multimodal communication, various aspects must be considered, including multi-transmitter processing, transmission technology, and receiver processing, in order to address challenges in multimodal corpus construction, multimodal information compression, transmission, interference handling, noise reduction, alignment, fusion, and expansion, as well as resource management issues. Finally, the importance of cross-domain multimodal information transfer, complementarity, and collaboration in the 6G network is emphasized. This will better integrate and apply a massive amount of heterogeneous information to meet the future communication demands of high-speed, low-latency, and intelligent interconnection.
Convolutional Neural Network and Vision Transformer-driven Cross-layer Multi-scale Fusion Network for Hyperspectral Image Classification
ZHAO Feng, GENG Miaomiao, LIU Hanqiang, ZHANG Junjie, YU Jun
Available online  , doi: 10.11999/JEIT231209
HyperSpectral Image (HSI) classification is one of the most prominent research topics in geoscience and remote sensing image processing tasks. In recent years, the combination of Convolutional Neural Network (CNN) and vision transformer has achieved success in HSI classification tasks by comprehensively considering local-global information. Nevertheless, the ground objects of HSIs vary in scale, containing rich texture information and complex structures. The current methods based on the combination of CNN and vision transformer usually have limited capability to extract texture and structural information of multi-scale ground objects. To overcome the above limitations, a CNN and vision transformer-driven cross-layer multi-scale fusion network is proposed for HSI classification. Firstly, from the perspective of combining CNN and visual transformer, a cross-layer multi-scale local-global feature extraction module branch is constructed, which is composed of a convolution embedded vision transformer architecture and a cross-layer feature fusion module. Specifically, to enhance attention to multi-scale ground objects in HSIs, the convolution embedded vision transformer captures multi-scale local-global features effectively by organically combining multi-scale CNN and vision transformer. Furthermore, the cross-layer feature fusion module aggregates hierarchical multi-scale local-global features, thereby combining shallow texture information and deep structural information of ground objects. Secondly, a group multi-scale convolution module branch is designed to explore the potential multi-scale features from abundant spectral bands in HSIs. Finally, to mine local spectral details and global spectral information in HSIs, a residual group convolution module is designed to extract local-global spectral features. Experimental results on Indian Pines, Houston 2013, and Salinas Valley datasets confirm the effectiveness of the proposed method.
Hybrid Reconfigurable Intelligent Surface Assisted Integrated Sensing and Communication: Energy Efficient Beamforming Design
CHU Hongyun, YANG Mengyao, HUANG Hang, ZHENG Ling, PAN Xue, XIAO Ge
Available online  , doi: 10.11999/JEIT230699
Energy Efficiency (EE) is an important design metric for 5G+/6G wireless communications, and Reconfigurable Intelligent Surface (RIS) is widely recognized as a potential means to improve EE. Unlike passive RIS, hybrid RIS consists of both active and passive components, which can amplify the signal strength while phase-shifting the incoming wave, and can effectively overcome the “multiplicative fading” effect caused by fully passive RIS. In view of this, a hybrid RIS-assisted Integrated Sensing and Communication (ISAC) downlink transmission system is proposed in this paper. In order to investigate the intrinsic correlation between data transmission capacity and energy consumption, the paper jointly optimizes the beamforming and phase-shifting of hybrid RIS at the Base Station (BS) under the constraints of BS transmit power, beampattern gain, and hybrid RIS power and amplitude with the goal of maximizing the global EE in a multiuser network. To solve this complex fractional programming problem, an algorithm based on Alternating Optimization (AO) is proposed to solve it. To overcome the problem of high algorithm complexity caused by the introduction of auxiliary variables in the AO algorithm, a solution algorithm based on a cascaded deep learning network is proposed using the association of coupled optimization variables. Simulation results show that the proposed hybrid RIS-assisted ISAC scheme outperforms existing schemes in terms of sum rate and EE, and the algorithm converges quickly.
Intelligent Weighted Energy Consumption and Delay Optimization for UAV-Assisted MEC Under Malicious Jamming
YANG Helin, ZHENG Mengting, LIU Shuai, XIAO Liang, XIE Xianzhong, XIONG Zehui
Available online  , doi: 10.11999/JEIT230986
In recent years, mounting Mobile Edge Computing (MEC) servers on Unmanned Aerial Vehicle (UAV) to provide services for mobile ground users has been widely researched in academia and industry. However, in malicious jamming environments, how to effectively schedule resources to reduce system delay and energy consumption becomes a key challenge. Therefore, this paper considers a UAV-assisted MEC system under a malicious jammer, where an optimization model is established to minimize the weighted energy consumption and delay by jointly optimizing UAV flight trajectories, resource scheduling, and task allocation. As the optimization problem is difficult to be solved and the malicious jamming behavior is dynamic, a Twin Delayed Deep Deterministic policy gradient algorithm (TD3) is proposed to search for the optimal policy. At the same time, the Prioritized Experience Replay (PER) technique is added to improve the convergence speed and stability of the algorithm, which is highly effective against malicious interference attacks. The simulation results show that the proposed algorithm can effectively reduce the delay and energy consumption, and achieve good convergence and stability compared with other algorithms.
Collaborative Electromagnetic Suppression Method for Electromagnetic Security Control of Major Events
SHI Jia, LI Antong, LI Zan, XIAO Shigui, WEI Qing
Available online  , doi: 10.11999/JEIT231318
The electromagnetic security cooperative suppression technology in the security area of major events under the complex urban environment is presented in this paper. Firstly, the complex urban electromagnetic environment is modeled by using the radio wave propagation model suitable for dense urban environment. Secondly, aiming at the problem of efficient electromagnetic suppression and effective avoidance of harmful interference, the potential game method is used to design the cooperative deployment algorithm of electromagnetic suppression equipment. Building upon this, the power optimization method of suppression equipment based on genetic algorithm is proposed to achieve the efficient delivery of interference power under the cooperative work of electromagnetic suppression equipment. The simulation results indicate that the proposed electromagnetic suppression equipment deployment algorithm can obtain outstanding performance similar to the theoretical optimal method (i.e., traversal algorithm), with lower computational complexity. Moreover, under identical interference effectiveness, the proposed power optimization algorithm reduces transmission power by over 50% compared to the traditional interference power allocation methods, thereby achieving precise collaborative control.
Joint Detection Threshold and Power Allocation Optimization Strategy for Multi-Target Tracking in Radar Networks
SHI Zhao, SHI Chenguang, WANG Fei, ZHOU Jianjiang
Available online  , doi: 10.11999/JEIT231242
In order to enhance the radio frequency stealth performance of radar networks, a Joint Detection Threshold and Power Allocation Optimization (JDTPAO) Strategy for Multi-Target Tracking (MTT) in radar networks is studied in this paper. Firstly, based on the integrated structure of detection and tracking, the average detection probability in associated gate and the predicted Bayesian Cramér-Rao Lower Bound are respectively derived as the performance metrics for target detection and MTT. Subsequently, a joint detection threshold and power allocation optimization model for minimizing the total power consumption is formulated, in which the node selection, detection threshold and power allocation are to be optimized, and the predetermined detection and MTT performance requirements, as well as the limited transmit resource are considered as the constraints. To address this problem, an approach combining improved probabilistic data association algorithm and sequential quadratic programming is proposed. Simulation results indicate that the proposed strategy effectively reduces the power consumption of radar network while meeting the requirements for target detection and tracking, thereby improving the radio frequency stealth performance.
A Multi-party Vertically Partitioned Data Synthesis Mechanism with Personalized Differential Privacy
ZHU Youwen, WANG Ke, ZHOU Yuqian
Available online  , doi: 10.11999/JEIT231158
In today's era, with the rapid development of big data technology and the continuous increase in data volume, large amounts of data are constantly collected by different companies or institutions, aggregating and publishing data owned by different companies or institutions helps to better provide services and support decision-making. However, their respective data may contain privacy information with different degrees of sensitivity, thus personalized privacy protection requirements need to be met while aggregating and publishing data from all parties. To solve the problem of multi-party data publication while ensuring that different privacy protection needs of all parties are met, a Multi-party Vertically partitioned Data Synthesis mechanism with Personalized Differential Privacy (PDP-MVDS) is proposed. Low-dimensional marginal distributions are firstly generated to reduce the dimension of high-dimensional data, then a randomly initialized dataset with these marginal distributions are updated, and finally a synthesized dataset whose distribution is similar to that of the real aggregated dataset from all parties is published. Personalized differential privacy protection is achieved by dividing the privacy budget; Secure scalar product protocol and threshold Paillier encryption algorithm are used to ensure the privacy of each party's data in the aggregation process; Distributed Laplace perturbation mechanism is used to effectively protect the privacy of marginal distributions that aggregated from those parties. Through rigorous theoretical analysis, it is proved that PDP-MVDS can ensure the security of each participant’s data and the finally published dataset. Furthermore, the experimental results on public datasets show that PDP-MVDS mechanism can obtain a multi-party synthesized dataset with high utility under low overhead.
Sonar Image Underwater Target Recognition: A Comprehensive Overview and Prospects
HUANG Haining, LI Baoqi, LIU Jiyuan, LIU Zhengjun, WEI Linzhe, ZHAO Shuang
Available online  , doi: 10.11999/JEIT231207
With the increasing development of marine resources and underwater operations, sonar image-based underwater target recognition has become a hot research area. This article provides a comprehensive review of the current status and future trends in this field. Initially, the background and significance of sonar image-based underwater target recognition are emphasized, noting that the complexity of the underwater environment and the scarcity of samples increase the task difficulty. Subsequently, typical imaging sonar technologies are delved, including forward-looking sonar, side-scan sonar, synthetic aperture sonar, multibeam echo sounder, interferometric synthetic aperture sonar, and forward-looking 3D sonar. Following that, 2D and 3D sonar image-based underwater target recognition methods are systematically examined, the strengths and weaknesses of different algorithms are compared, and methods for the correlated recognition of sonar image sequences are discussed. Finally, the major challenges in the current field and future research directions are summarized, aiming to foster the development of the underwater sonar target recognition field.
Remote Sensing Images Small Object Detection Algorithm With Adaptive Fusion and Hybrid Anchor Detector
WANG Kun, DING Qilong
Available online  , doi: 10.11999/JEIT230966
A hybrid detector AEM-YOLO based on the adaptive fusion of different scale features is proposed, aiming at the problems of difficult detection of small objects in remote sensing images caused by the high background noise, dense arrangement of small objects, and wide-scale distribution. Firstly, a two-axes k-means clustering algorithm combining width and height information with scale and ratio information is proposed to generate anchors with high matching degrees with remote sensing datasets. Secondly, an adaptive enhance module is designed to address information conflicts caused by direct fusion between different scale features. A lower feature layer is introduced to broadcast small object details along the bottom-up path. By using multi-task learning and scale guidance factor, the recall for objects with a high aspect ratio can be effectively improved. Finally, the experiments on the DIOR dataset show that compared with the original model, the AP of AEM-YOLO is improved by 7.8%, and increased by 5.4%, 7.2%, and 8.6% in small, medium, and large object detection, respectively.
Physical Layer Security for Hybrid Reconfigurable Intelligent Surface and Artificial Noise Assisted Communication
DENG Zhixiang, DAI Chenqing, ZHANG Zhiwei
Available online  , doi: 10.11999/JEIT231235
A hybrid active-passive Reconfigurable Intelligent reflecting Surface (RIS) and Artificial Noise (AN) based transmission scheme is proposed for the secret communication of the RIS assisted wireless communication system. Aiming at maximizing the secrecy rate, a joint optimization problem over the transmit beamforming and AN vector of the base station and the reflecting coefficient matrix of the RIS is formulated. Then, the Alternating Optimization (AO) method, the weighted Minimum Mean Square Error (MMSE) algorithm and the semi-definite relaxation algorithm are proposed to solve this non-convex optimization problem with highly-coupled variables. The simulation results show that the proposed hybrid RIS and AN based scheme can efficiently improve the secrecy rate of the considered system and overcome the secrecy rate decrease due to the "double fading" effect of the passive RIS. Compared with the full active RIS, the proposed scheme achieves higher energy efficiency.
Polarized Beam Online Reconfiguration Technique For Flexible Deformation Antennas
CHEN Zhikun, CUI Jinhe, WANG Wei, CHEN Zhibin, GUO Yunfei
Available online  , doi: 10.11999/JEIT240070
In response to the challenges posed by the deformation of flexible polarized array antennas, which results in difficulties in beam reconstruction and compromised beam performance, polarization beam online reconstruction technique based on flexible deformation polarized antennas is proposed in this paper. Firstly, the deformation state of the array is modeled based on a wing model, and real-time deformation data is obtained using modal analysis to reconstruct the antenna array model online. Secondly, the element response of vector array antenna is utilized to construct a flexible array antenna signal model in three-dimensional space. Finally, a deep integration of the Cyclic Algorithm (CA) and Second-Order Cone Programming (SOCP) is employed to solve the dynamic optimization problem of this optimal polarization beam reconstruction. Simulation results demonstrate that within a certain range of deformation and under different arc and angle requirements from environmental loads, the proposed method can achieve online antenna array reconstruction and real-time optimal polarization beam reconstruction based on the dynamic antenna array model. The directional gain, beamwidth, and polarization matching design all meet the requirements for practical engineering applications.
3DSARBuSim 1.0: High-Resolution Space Borne SAR 3D Imaging Simulation Dataset of Man-Made Buildings
JIAO Runzhi, DENG Jia, HAN Yaquan, HUANG Haifeng, WANG Qingsong, LAI Tao, WANG Xiaoqing
Available online  , doi: 10.11999/JEIT230882
Tomographic Synthetic Aperture Radar (TomoSAR) can effectively recover the information of ground objects in steep terrain, and is one of the research hotspots in urban mapping. However, the current public data sets lack the true values of the object models, and cannot quantitatively verify the TomoSAR algorithm. To solve this problem and further promote the development of TomoSAR technology, this paper first proposes an Ray Tracing Based Space Borne Radar Advanced Simulator (RT-SBRAS), which can quickly and stably simulate the spaceborne SAR images of complex buildings compared with previous methods. Based on this, the 1.0 version of the 3D SAR Building Simulation (3DSARBuSim) data set is constructed, which contains the full-link simulation data of eight typical building scenes in dual-band and multi-pass. Finally, Orthogonal Matching Pursuit (OMP) and dual-frequency OMP algorithms are verified on the proposed data set, and the data set can provide clear and accurate quantitative comparison for the algorithms.
Research on Symmetrically Resonant VLF Transmit/Receive Magnetoelectric Antenna Coupling Performance
WANG Xiaoyu, ZHANG Boyan, ZHAO Xiangchen, YANG Xijie, FENG Qing, CAO Zhenxin
Available online  , doi: 10.11999/JEIT230247
Very low frequency has great potential for long distance signal transmission and military communications due to its low propagation loss characteristics. Magneto-Electric (ME) antennas, based on the acoustic resonance principle, can push the limits of size and are easily impedance matched, offering unique advantages for transmission in the very low frequency band. Based on this, a new ME antenna system consisting of a transmitting antenna of P/T/P structure and a receiving antenna of T/P/T structure is designed. The structural pattern of the antenna in receiving/transmitting electromagnetic waves is analyzed based on the magneto-mechanical coupling model. The magnetic field distribution of the antenna in the near-field range is investigated based on the radiation model. An experiment on the transmission/receiving of ME antennas in the very low frequency band is realized with acoustic wave mediated excitation. Experimentally obtained at resonant frequencies, the ME transmit/receive antenna is improved to 82.6% in output voltage and to 42.2% in communication range before the structure optimization compared to after the optimization when the piezoelectricity ratio is 0.66 and 0.34, respectively. Magnitude higher radiation efficiency is improved by three orders compared to the same size electric small antenna. Modulated communication with a transmission rate of 5 bit/s is possible and the performance of the antenna is improved based on structural optimization.
Anomaly Detection of Small Targets on Sea Surface Based on Deep Graph Infomax
XU Shuwen, HE Qi, RU Hongtao
Available online  , doi: 10.11999/JEIT230887
Due to the complex marine environment, it is difficult for a maritime radar to achieve high-performance detection of slow and small targets on the sea surface. For such targets, the traditional energy-based statistical detection algorithms suffer from serious performance loss. Confronted with this problem, a detection algorithm of small targets based on Deep Graph Infomax framework is proposed to realize unsupervised target anomaly detection in the background of sea clutter. In the traditional neural networks, there is an assumption that the samples are independent and identically distributed, which, however, the high-resolution radar echo does not meet. Therefore, this paper re-models the data from the perspective of graph and constructs the graph topological structure according to the correlation characteristics of the echo. Moreover, this paper puts forward the relative maximum node degree, and combines it with the relative average amplitude and the relative Doppler vector entropy to be the initial representation vectors of the graph nodes. With the graph modeling done, the graph attention network is used as the encoder in the Deep Graph Infomax framework to learn representation vectors. Finally, the anomaly detection algorithm is used to detect the targets, and the false alarm can be controlled. The detection result on the measured datasets shows that the performance of the proposed detector is improved by 9.2% compared to the three-feature detector when using the fast convex hull learning algorithm. Compared to the time-frequency three-feature detector, the performance is improved by 7.9%. When the network outputs a higher-dimensional representation vectors, the performance of the detector using the isolated forest algorithm is improved by 27.4%.
A Privacy-preserving Data Alignment Framework for Vertical Federated Learning
GAO Ying, XIE Yuxin, DENG Huanghao, ZHU Zukun, ZHANG Yiyu
Available online  , doi: 10.11999/JEIT231234
In vertical federated learning, the datasets of the clients have overlapping sample IDs and features of different dimensions, thus the data alignment is necessary for model training. As the intersection of the sample IDs is public in current data alignment technologies, how to align the data without any leakage of the intersection becomes a key issue. The proposing private-preserving data alignment framework is based on interchangeable encryption and homomorphic encryption technologies, mainly including data encryption, ciphertext blinding, private intersecting, and feature splicing. The sample IDs are encrypted twice based on an interchangeable encryption algorithm, where the same ciphertexts correspond to the same plaintexts, and the sample features are encrypted and then randomly blinded based on a homomorphic encryption algorithm. The intersection of the encrypted sample IDs is obtained, and the corresponding features are then spliced and secretly shared with the participants. Compared to the existing technologies, the privacy of the ID intersection is protected, and the samples corresponding to the IDs outside intersection can be removed safely in our framework. The security proof shows that each participant cannot obtain any knowledge of each other except for the data size, which guarantees the effectiveness of the private-preserving strategies. The simulation experiments demonstrate that the runtime is shortened about 1.3 seconds and the model accuracy keeps higher than 85% with every 10% reduction of the redundant data. The simulation experimental results show that using the ALIGN framework for vertical federated learning data alignment is beneficial for improving the efficiency and accuracy of subsequent model training.
Zero-shot 3D Shape Classification Based on Semantic-enhanced Language-Image Pre-training Model
DING Bo, ZHANG Libao, QIN Jian, HE Yongjun
Available online  , doi: 10.11999/JEIT231161
Currently, the Contrastive Language-Image Pre-training (CLIP) has shown great potential in zero-shot 3D shape classification. However, there is a large modality gap between 3D shapes and texts, which limits further improvement of classification accuracy. To address the problem, a zero-shot 3D shape classification method based on semantic-enhanced CLIP is proposed in this paper. Firstly, 3D shapes are represented as views. Then, in order to improve recognition ability of unknown categories in zero-shot learning, the semantic descriptive text of each view and its corresponding category are obtained through a visual language generative model, and it is used as the semantic bridge between views and category prompt texts. The semantic descriptive texts are obtained through image captioning and visual question answering. Finally, the finely-adjusted semantic encoder is used to concretize the semantic descriptive texts to the semantic descriptions of each category, which have rich semantic information and strong interpretability, and effectively reduce the semantic gap between views and category prompt texts. Experiments show that our method outperforms existing zero-shot classification methods on the ModelNet10 and ModelNet40 datasets.
Privacy Preseving Attribute Based Searchable Encryption Scheme in Intelligent Transportation System
NIU Shufen, GE Peng, DONG Runyuan, LIU Qi, LIU Wei
Available online  , doi: 10.11999/JEIT231074
In order to solve the problem that the travel information of vehicle users in Intelligent Transportation System (ITS) is easy to be illegally stolen and the traffic data stored in the cloud server of transportation system is abused by malicious users, a new Attribute Based Searchable Encryption (ABSE) scheme is proposed in this paper, which has the functions of privacy protection, key aggregation and lightweight calculation. The scheme realizes full privacy protection in key generation stage, access control stage and partial decryption stage. The search keyword is embedded into the access structure, which can realize partial policy hiding and keyword security. Through key aggregation technology, all file identities that meet the search conditions and access policies are aggregated into one aggregate key, which reduces the burden of key storage for users, and further ensures the security of file keys and data. The security analysis shows that the scheme has the advantages of hidden access structure security, keyword ciphertext indistinguishable security and trapdoor indistinguishable security. The theoretical analysis and numerical simulation showed the proposed scheme was efficient and practical in terms of communication and computing overhead.
Research Progress in Logic Synthesis Based on Semi-Tensor Product
CHU Zhufei, MA Chengyu, YAN Ming, PAN Jiaxiang, PAN Hongyang, WANG Lunyao, XIA Yinshui
Available online  , doi: 10.11999/JEIT231457
Logic synthesis plays a crucial role in the modern electronic design automation process. With the continuous enhancement of computational capabilities and the emergence of new computing paradigms, various efficient Boolean SATisfiability (SAT) solvers and circuit simulators have been developed and applied in the context of logic synthesis. First, the overview of the Boolean Satisfiability problem and circuit logic simulator is briefly described. Subsequently, the historical development of the matrix semi-tensor product is reviewed, and based on the fundamental principles of the semi-tensor product, its research progress in inference engines and logic synthesis is expounded. Finally, a prospective analysis is conducted on emerging technologies that may significantly impact logic synthesis in the future.
A Method for Radio Frequency Interference Space Angle Sparse Bayesian Estimating in Synthetic Aperture Microwave Radiometer
ZHANG Juan, ZHUANG Lehui, LI Yinan, LI Hong, DOU Haofeng
Available online  , doi: 10.11999/JEIT231367
A sparse Bayesian estimation for spatial Radio Frequency Interference (RFI) of synthetic aperture microwave radiometers is proposed in this paper. Firstly, an interferometry measurement model of the visibility function for synthetic aperture microwave radiometers is established. The observed data are expressed as the product of the observation matrix of the aperture synthesis antenna baseline correlation steering vector and the brightness temperature of the field of view. Due to the orthogonality of the observation matrix and the sparsity of the RFI spatial angle distribution, the transformation coefficients of brightness temperature in the support domain are sparse. Under the Sparse Bayesian Learning (SBL) framework, brightness temperature is sparsely reconstructed. Notably, this method can obtain high reconstruction performance without the prior information of sparsity and regularization parameters. The effectiveness of this method is verified through computer simulations.
Research on Opportunistic Localization with 5G Signals in Co-channel Interference Environments
SUN Qian, DING Tianyu, JIAN Xin, LI Yibing, YU Fei
Available online  , doi: 10.11999/JEIT231423
In response to the challenge of ensuring positioning accuracy in environments where the Global Navigation Satellite System (GNSS) is denied, a positioning scheme based on opportunistic New Radio (NR) signals is devised and an Interference Cancellation Subspace Pursuit (ICSP) algorithm is proposed in this paper. This algorithm aims to resolve the issue of inadequate precision in the extraction of positioning observations due to co-channel interference within Ultra-Dense Networks (UDNs) and Heterogeneous Networks (HetNets). The effectiveness of the ICSP algorithm in optimizing the performance of 5G opportunistic signal receivers and enhancing positioning accuracy in complex network environments has been validated through simulation experiments and semi-physical simulations utilizing the Universal Software Radio Peripheral (USRP).
Screen-Shooting Resilient Watermarking Scheme Combining Invertible Neural Network and Inverse Gradient Attention
LI Xiehua, LOU Qin, YANG Junxue, LIAO Xin
Available online  , doi: 10.11999/JEIT230953
With the growing use of smart devices, the ease of sharing digital media content has been enhanced. Concerns have been raised about unauthorized access, particularly via screen shooting. In this paper, a novel end-to-end watermarking framework is proposed, employing invertible neural networks and inverse gradient attention, to tackle the copyright infringement challenges related to screen content leakage. A single invertible neural network is employed by the proposed method for watermark embedding and extraction, ensuring information integrity during network propagation. Additionally, robustness and visual quality are enhanced by an inverse gradient attention module, which emphasizes pixel values and embeds the watermark in imperceptible areas for better invisibility and model resilience. Model parameters are optimized using the Learnable Perceptual Image Patch Similarity (LPIPS) loss function, minimizing perception differences in watermarked images. The superiority of this approach over existing learning-based screen-shooting resilient watermarking methods in terms of robustness and visual quality is demonstrated by experimental results.
Spiking Sequence Label-Based Spatio-Temporal Back-Propagation Algorithm for Training Deep Spiking Neural Networks
WANG Zihua, YE Ying, LIU Hongyun, XU Yan, FAN Yubo, WANG Weidong
Available online  , doi: 10.11999/JEIT230705
Spiking Neural Networks (SNN) have a signal processing mode close to the cerebral cortex, which is considered to be an important approach to realize brain-inspired computing. However, the lack of effective supervised learning algorithms for deep spiking neural networks has been a great challenge for spiking sequence label-based brain-inspired computing tasks. A supervised learning algorithm for training deep spiking neural network is proposed in this paper. It is an error backpropagation algorithm that uses surrogate gradient to solve the problem of non-differentiable spike generation function, and define the postsynaptic potential and membrane potential reversal iteration factors represent the spatial and temporal dependencies of pulsed neurons, respectively. It differs from existing learning algorithms based on firing rate encoding, fully reflects analytically the temporal dynamic properties of the spiking neuron. Therefore, the algorithm proposed in this paper is well-suited for application to tasks that require longer time sequences rather than spiking firing rates, such as behavior control. Proposed algorithm is validated on the static image datasets CIFAR10, and the neuromorphic dataset NMNIST. It shows good performance on all these datasets, which helps to further investigate spike-based brain-inspired computation.
Action Recognition Network Combining Spatio-Temporal Adaptive Graph Convolution and Transformer
HAN Zongwang, YANG Han, WU Shiqing, CHEN Long
Available online  , doi: 10.11999/JEIT230551
In a human-centered smart factory, perceiving and understanding workers’ behavior is crucial, as different job categories are often associated with work time and tasks. In this paper, the accuracy of the model's recognition is improved by combining two approaches, namely adaptive graphs and Transformers, to focus more on the spatiotemporal information of the skeletal structure. Firstly, an adaptive graph method is employed to capture the connectivity relationships beyond the human body skeleton. Furthermore, the Transformer framework is utilized to capture the dynamic temporal variations of the worker's skeleton. To evaluate the model's performance, six typical worker action datasets are created for intelligent production line assembly tasks and validated. The results indicate that the model proposed in this article has a Top-1 accuracy comparable to mainstream action recognition models. Finally, the proposed model is compared with several mainstream methods on the publicly available NTU-RGBD and Skeleton-Kinetics datasets, and the experimental results demonstrate the robustness of the model proposed in this paper.
Radio Environment Map Construction Method for Complex Scenes Based on Inverse Obstacle Distance Weighted
TAO Shifei, WU Yujiang, LUO Jia, DING Hao, WANG Yuanhe
Available online  , doi: 10.11999/JEIT231374
Addressing the issues of inadequate performance in constructing Radio Environment Maps (REMs) in complex scenarios due to non-penetrable obstacles for electromagnetic waves, and the arbitrary selection of interpolation neighborhoods imposed by Inverse Distance Weighted (IDW), a Voronoi-based Inverse Obstacle Distance Weighted algorithm (VIODW) is proposed in this paper. This algorithm adaptively defines interpolation neighborhoods for each interpolation point by creating Voronoi diagrams incorporating obstacles for numerical computation. Then, using the ANY-Angle (ANYA) Algorithm to calculate the obstacle distance between the interpolation point and each monitoring station within the interpolation neighborhood. Finally, by calculating the weighted mean with the inverse power of the obstacle distance as the weight, the value at the point is obtained, achieving high-precision construction of REMs in complex scenarios. Both theoretical analysis and simulation results demonstrate that this method offers excellent construction accuracy and can accurately model the power distribution of electromagnetic waves in complex scenarios. Hence, it provides an effective approach for high-precision REM construction in complex scenarios.
Research on Multi-User Detection Algorithm for Non-Orthogonal Multiple Access Short Message Based on Low Complexity Adder Network
WANG Ji, LI Zilong, XIAO Jian, LI Huanzhe, XIE Wenwu, YU Chao
Available online  , doi: 10.11999/JEIT231186
A joint constellation trace diagram and deep learning-based blind modulation detection scheme is proposed for Non-Orthogonal Multiple Access (NOMA) systems, which can avoid the required expensive signaling overhead in successive interference cancellation algorithms, especially for NOMA-based short packet transmission. Considering the high computational complexity and energy consumption for communication equipment in the deployment of neural network, the original convolutional network is replaced by the adder network. The modulation detection accuracy, computing delay and energy consumption are fully compared for two kinds of network architectures. Meanwhile, time-domain oversampling technology is used to improve the recognition rate under low signal-to-noise ratio. Finally, the influence of power allocation and data packet length on detection performance is analyzed and verified.
A Cloud Server Anomaly Detection Model Based on Time Series Decomposition and Spatiotemporal Information Extraction
TANG Lun, ZHAO Yuchen, XUE Chengcheng, CHEN Qianbin
Available online  , doi: 10.11999/JEIT230679
Anomaly detection is an important task to maintain cloud data center performance. A large number of cloud servers are running in cloud data centers to implement various cloud computing functions. Since the performance of cloud data centers depends on the normal operation of cloud services, it is crucial to detect and analyze anomalies in cloud servers. To this end, a cloud server anomaly detection model based on time series decomposition and spatiotemporal information extraction-Multi-Channel Bidirectional Wasserstein Generative Adversarial Networks with Graph-Time Network (MCBiWGAN-GTN) is proposed in this paper. Firstly, the Bidirectional Wasserstein GAN with Graph-Time Network (BiWGAN-GTN) algorithm is proposed. This algorithm is built upon the Bidirectional Wasserstein GAN with Gradient Penalty (BiWGAN-GP) algorithm. In this modification, the generator and encoder are replaced by a spatiotemporal information extraction module— Graph-Time Network (GTN) composed of Graph Convolutional Networks (GCN) and Temporal Convolutional Networks (TCN). This modification aims to extract spatiotemporal information from the data, enhancing the capabilities of the algorithm. Secondly, the semi-supervised BiWGAN-GTN algorithm is proposed to identify anomalies in multi-dimensional time series to avoid the risk of abnormal data intrusion during the training process and enhance model robustness. Finally, the MCBiWGAN-GTN is designed to achieve the goal of reducing data complexity and improving model learning efficiency. The Complete Ensemble Empirical Mode Decomposition with Adaptive Noise algorithm (CEEMDAN) is used to decompose the time series data, and then different components are sent to the BiWGAN-GTN algorithm under the corresponding channel for training. The effectiveness and stability of the proposed model are verified on two real-world cloud data center datasets, Clearwater and MBD, using three evaluation metrics: precision, recall and F1 score. Experimental results show that the performance of MCBiWGAN-GTN on these two datasets is stable and better than the compared methods.
Backscatter-NOMA Enabled Hybrid Multicast-Unicast Cooperative Transmission Scheme
KUO Yonghong, XUE Yanwen, LÜ Lu, HE Bingtao, CHEN Jian
Available online  , doi: 10.11999/JEIT230672
In order to address the low spectral efficiency and inefficient link utilization problem in cooperative relay communication system, a Backscatter-NOMA enabled hybrid multicast-unicast cooperative transmission scheme is proposed for the scenario of coexistence of multicast and unicast services. A multicast user is opportunistically selected as a cooperative node, which used a part of the power of the received signal for its own decoding, and backscatter the residual power to enhance the reception quality of other users. To improve system performance, the minimum achievable rate for unicast users is maximized by jointly optimizing the base station power allocation coefficients, cooperative user backscatter coefficient and cooperative node selection variable, while guaranteeing the quality of service for multicast. To solve the above highly non-convex joint optimization problem, a cooperative user selection criterion was designed and an iterative algorithm was proposed to obtain the optimal solution to the original problem. The simulation results verify the fast convergence of the proposed iterative algorithm, which can improve the minimum achievable rate of unicast users by 11.5% compared to the non-cooperative transmission scheme, and effectively ensure the quality of multi-service.
A Fusion Network for Infrared and Visible Images Based on Pre-trained Fixed Parameters and Deep Feature Modulation
XU Shaoping, ZHOU Changfei, XIAO Jian, TAO Wuyong, DAI TianYu
Available online  , doi: 10.11999/JEIT231283
To better leverage complementary image information from infrared and visible light images and generate fused images that align with human perception characteristics, a two-stage training strategy is proposed to obtain a novel infrared-visible image fusion Network based on pre-trained fixed Parameters and Deep feature modulation (PDNet). Specifically, in the self-supervised pre-training stage, a substantial dataset of clear natural images is employed as both inputs and outputs for the UNet backbone network, and pre-training is accomplished with autoencoder technology. As such, the resulting encoder module can proficiently extract multi-scale depth features from the input image, while the decoder module can faithfully reconstruct it into an output image with minimal deviation from the input. In the unsupervised fusion training stage, the pre-trained encoder and decoder module parameters remain fixed, and a fusion module featuring a Transformer structure is introduced between them. Within the Transformer structure, the multi-head self-attention mechanism allocates deep feature weights, extracted by the encoder from both infrared and visible light images, in a rational manner. This process fuses and modulates the deep image features at various scales into the manifold space of deep features of clear natural image, thereby ensuring the visual perception quality of the fused image after reconstruction by the decoder. Extensive experimental results demonstrate that, in comparison to current mainstream fusion models (algorithms), the proposed PDNet model exhibits substantial advantages across various objective evaluation metrics. Furthermore, in subjective visual evaluations, it aligns more closely with human visual perception characteristics.
General Low-complexity Beamforming Designs for Reconfigurable Intelligent Surface-aided Multi-user Systems
CHEN Xiao, SHI Jianfeng, ZHU Jianyue, PAN Cunhua
Available online  , doi: 10.11999/JEIT240051
General low-complexity joint beamforming designs are proposed for Reconfigurable Intelligent Surface (RIS) assisted multi-user systems. First, the non-convex optimization problem of joint beamforming design is analyzed to maximize sum data rate for RIS-aided multi-user systems. Second, the RIS reflection matrix is designed by using the approximation orthogonality of the beam steering vectors, and the transmit beamforming at the base station is derived from the zero forcing method, and the power allocation is optimized for multiple users. Finally, it is found that the proposed scheme has wide applicability and an order of magnitude reduction on computational complexity than that of existing work. Numerical results show that the proposed beamforming design can achieve high sum data rate, which can be further improved by employing the optimal power allocation. Besides, both the simulation results and theoretical analysis indicate that the sum data rate changes with the RIS location, which provides reference standards for the selection of RIS location.
Baseband Modulation Signal Generation and Phase Synchronization Method of Space High Speed Optical Communication
WANG Dizhu, JIN Yi, ZUO Jinzhong, XU Changzhi, LIANG Huijian, GOU Baowei
Available online  , doi: 10.11999/JEIT231460
The high-quality generation and precise phase synchronization of high-speed modulated baseband signals are key technologies of space optical communication ranging system. Traditional approaches relying on FPGA or Digital Signal Processor (DSP) and high-speed Digital to Analog Convertor (DAC) technology often suffer from limited phase synchronization accuracy and high hardware complexity. A method for high-speed optical communication baseband signal generation and phase synchronization is proposed and a phase-locked dynamic control loop is designed in this paper. By dynamically adjusting the phase of the high-speed signal transmission clock in real time, the deterministic relationship between the I/Q high-speed baseband signal phase and the external reference clock phase can be achieved. The experimental results demonstrate impressive performance metrics: When the code rate is of the Quadrature Phase Shift Keying (QPSK) optical modulated signal is 2.5 Gbit/s, the phase synchronization accuracy is less than 2 ps and the Error Vector Magnitude (EVM) is less than 8%; the bit error rate is 10–7 at a 5 Gbit/s optical communication rate, the receiver sensitivity is better than –47 dBm, and the ranging accuracy is better than 2 mm. Compared with traditional methods, both sensitivity and ranging accuracy are significantly improved.
Airborne Target Recognition of Narrowband Radar Short Time Observation Echoes Based on Feature Fusion
GUO Zekun, LIU Zheng, XIE Rong, RAN Lei, XU Hanzheng
Available online  , doi: 10.11999/JEIT231232
Narrowband radar is widely used in the field of air defense guidance due to its advantages of low cost and long operating range. With the development of high-speed mobile platforms, traditional target recognition methods based on feature modeling of long-term observation echo sequences are no longer applicable. In response to the problem of poor feature recognition ability of narrowband radar for Observe Echoes for a Short period of Time (OEST) sequences and susceptibility to bait target interference, resulting in low reliability of recognition results, a narrowband radar OEST sequence air target recognition method using multi feature adaptive fusion is proposed in this paper. Firstly, the encoder and classification layers are constructed with channel-spatial attention modules and trained to adaptively enhance features with high separability. Then, the maximum edge orthogonal loss function is proposed to increase the feature spacing between different classes, reduce the feature spacing between the same classes, and make the feature vectors orthogonal between different classes; Finally, the parameters of the encoder layer and classification layer are fixed, and the decoder layer is trained using reconstruction loss value to ensure that the model has accurate identification ability for decoy targets. Under the condition of an observation sequence length of 100, the classification accuracy and discrimination rate of the experimental part reached 94.37% and 96.78%, respectively. It can be concluded that the proposed method can effectively improve the classification performance of narrowband radar and the discrimination ability against bait targets, thereby improving the reliability of recognition results.
Adaptive Attention Mechanism Fusion for Real-Time Semantic Segmentation in Complex Scenes
CHEN Dan, LIU Le, WANG Chenhao, BAI Xiru, WANG Zichen
Available online  , doi: 10.11999/JEIT231338
Realizing high accuracy and low computational burden is a serious challenge faced by Convolutional Neural Network (CNN) for real-time semantic segmentation. In this paper, an efficient real-time semantic segmentation Adaptive Attention mechanism Fusion Network(AAFNet) is designed for complex urban street scenes with numerous types of targets and large changes in lighting. Image spatial details and semantic information are respectively extracted by the network, and then, through Feature Fusion Network(FFN), accurate semantic images are obtained. Dilated Deep-Wise separable convolution (DDW) is adopted by AAFNet to increase the receptive field of semantic feature extraction, an Adaptive Attention mechanism Fusion Module (AAFM) is proposed, which combines Adaptive average pooling(Avp) and Adaptive max pooling(Amp) to refine the edge segmentation effect of the target and reduce the leakage rate of small targets. Finally, semantic segmentation experiments are performed on the Cityscapes and CamVid datasets for complex urban street scenes. The designed AAFNet achieves 73.0% and 69.8% mean Intersection over Union (mIoU) at inference speeds of 32 fps (Cityscapes) and 52 fps (CamVid). Compared with Dilated Spatial Attention Network (DSANet), Multi-Scale Context Fusion Network (MSCFNet), and Lightweight Bilateral Asymmetric Residual Network (LBARNet), AAFNet has the highest segmentation accuracy.
Local Adaptive Federated Learning with Channel Personalized Normalization
ZHAO Yu, CHEN Siguang
Available online  , doi: 10.11999/JEIT231165
To relieve the impact of data heterogeneity problems caused by full overlapping attribute skew between clients in Federated Learning (FL), a local adaptive FL algorithm that incorporates channel personalized normalization is proposed in this paper. Specifically, an FL model oriented to data attribute skew is constructed, and a series of random enhancement operations are performed on the images data set in the client before training begins. Next, the client calculates the mean and standard deviation of the data set separately by color channel to achieve channel personalized normalization. Furthermore, a local adaptive update FL algorithm is designed, that is, the global model and the local model are adaptively aggregated for local initialization. The uniqueness of this aggregation method is that it not only retains the personalized characteristics of the client model, but also can capture necessary information in the global model to improve the generalization performance of the model. Finally, the experimental results demonstrate that the proposed algorithm obtains competitive convergence speed compared with existing representative works and the accuracy is 3%~19% higher.
A Multimodal Sentiment Analysis Model Enhanced with Non-verbal Information and Contrastive Learning
LIU Jia, SONG Hong, CHEN Da-Peng, WANG Bin, ZHANG Zeng-Wei
Available online  , doi: 10.11999/JEIT231274
Deep learning methods have gained popularity in multimodal sentiment analysis due to their impressive representation and fusion capabilities in recent years. Existing studies often analyze the emotions of individuals using multimodal information such as text, facial expressions, and speech intonation, primarily employing complex fusion methods. However, existing models inadequately consider the dynamic changes in emotions over long time sequences, resulting in suboptimal performance in sentiment analysis. In response to this issue, a Multimodal Sentiment Analysis Model Enhanced with Non-verbal Information and Contrastive Learning is proposed in this paper. Firstly, the paper employs long-term textual information to enable the model to learn dynamic changes in audio and video across extended time sequences. Subsequently, a gating mechanism is employed to eliminate redundant information and semantic ambiguity between modalities. Finally, contrastive learning is applied to strengthen the interaction between modalities, enhancing the model’s generalization. Experimental results demonstrate that on the CMU-MOSI dataset, the model improves the Pearson Correlation coefficient (Corr) and F1 score by 3.7% and 2.1%, respectively. On the CMU-MOSEI dataset, the model increases “Corr” and “F1 score” by 1.4% and 1.1%, respectively. Therefore, the proposed model effectively utilizes intermodal interaction information while eliminating information redundancy.
A Camouflaged Target Detection Method with Improved YOLOv5 Algorithm
PENG Ruihui, LAI Jie, SUN Dianxing, LI Mang, YANG Ruyu, LI Xue
Available online  , doi: 10.11999/JEIT231170
To comprehensively explore the information content of camouflaged target features, leverage the potential of target detection algorithms, and address issues such as low camouflage target detection accuracy and high false positive rates, a camouflage target detection algorithm named CAFM-YOLOv5 (Cross Attention Fusion Module Based on YOLOv5) is proposed. Firstly, a camouflaged target multispectral dataset is constructed for the performance validation of the multimodal image fusion method; secondly, a dual-stream convolution channel is constructed for visible and infrared image feature extraction; and finally, a cross-attention fusion module is proposed based on the channel-attention mechanism and spatial-attention mechanism in order to realise the effective fusion of two different features.Experimental results demonstrate that the model achieves a detection accuracy of 96.4% and a recognition probability of 88.1%, surpassing