Email alert
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:
Available online ,
doi: 10.11999/JEIT240464
Abstract:
Objective In response to the rapid growth of mobile users and the sparse distribution of ground infrastructure, the research presented in this paper aims to address the challenges faced by vehicular networks. It emphasizes the importance of efficient computation offloading and resource optimization in such networks, highlighting the necessity of leveraging unmanned aerial vehicles (UAVs) and roadside units (RSUs), along with base stations (BSs), to enhance the overall system performance. Methods The research methodology of this paper innovatively proposes an energy harvesting-assisted air-ground cooperative computation offloading architecture, which integrates UAVs, RSUs, and BSs to efficiently handle dynamic task queues generated by vehicles. By incorporating EH technology, UAVs capture and convert ambient renewable energy, ensuring continuous power supply and stable computing power. Addressing the time-varying channel conditions and high mobility of nodes, this study formulates a Mixed Integer Programming (MIP) problem. An iterative process is employed to adjust offloading decisions and computing resource allocations at low cost, aiming to optimize system performance. Technology details are described as follows.Firstly, the paper innovatively proposes an energy harvesting-assisted air-ground cooperative computation offloading framework. This framework integrates UAVs, RSUs, and BSs to collaboratively manage dynamic task queues generated by vehicles. By introducing EH technology, the framework ensures continuous power supply and stable computing capabilities for UAVs, addressing the challenges posed by limited energy resources.Secondly, to address the complexities of the system, including time-varying channel conditions, high node mobility, and dynamic task arrivals, the paper formulates a Mixed Integer Programming (MIP) problem. This problem is aimed at optimizing the system’s performance by finding the best joint offloading decisions and resource allocation strategies. The objective is to minimize global service delay while satisfying various dynamic and long-term energy constraints.Thirdly, to solve the formulated MIP problem, the paper introduces an Improved Actor-Critic Algorithm (IACA) based on reinforcement learning. This algorithm leverages Lyapunov optimization to decompose the problem into frame-level deterministic optimizations, making it more manageable. Additionally, a genetic algorithm is used to compute target Q-values, guiding the reinforcement learning process and improving solution efficiency and global optimality. The IACA algorithm is implemented to iteratively adjust offloading decisions and resource allocations, achieving the desired system performance optimization.By combining these research methods, the paper contributes to the field of air-ground cooperative computation offloading, providing a novel framework and algorithm to address the challenges posed by limited energy resources, time-varying channel conditions, and high node mobility. Results and Discussions The proposed framework and algorithm are evaluated through extensive simulations. The results demonstrate the effectiveness and efficiency of the proposed method in achieving dynamic and efficient offloading and resource optimization in vehicular networks.(Fig.3 ) shows the performance of the IACA algorithm, highlighting its efficient convergence. Through 4,000 training episodes, the agent continuously interacted with the environment, refining its decision-making strategy and updating network parameters. As depicted in Figures 3(a) and 3(b) , the loss function values of both the Actor and Critic networks decreased progressively, reflecting improvements in modeling the real-world environment. Meanwhile, Figure 3(c) indicates a rising trend in reward values with increasing training episodes, ultimately stabilizing, which signifies the discovery of a more effective decision-making strategy by the agent. (Fig.4 ) shows system avg. delay and energy consumption vs. time slots. As slots increase, avg. delay decreases for all algorithms except RA (highest due to random offloading). RLA2C outperforms RLASD with its advantage function. IACA, trained repeatedly in dynamic environments, achieves avg. service delay close to CPLEX's optimal. It also significantly reduces avg. energy consumption by minimizing Lyapunov drift plus penalty, outperforming RA and RLASD. (Fig.5 ) shows the impact of task input data size on system performance. As data increases from 750 kbit to 1,000 kbit, avg. delay and energy consumption rise. The IACA algorithm, with effective environment interaction and an improved genetic algorithm, robustly generates near-ideal optimal solutions, excelling in both energy and delay. In contrast, RLASD and RLA2C gap widens from CPLEX due to unstable training environments for large tasks. RA causes significant avg. delay and energy consumption fluctuations. (Fig.6 ) show Lyapunov parameter V's impact on avg. delay and energy at T=200. With V, performance is finely controlled. As V increases, avg. delay drops while energy rises, stabilizing. IACA, with improved Q-values, excels in delay and energy optimization. What’ more, Fig. 7 shows UAV energy thresholds & counts impact avg. system delay. IACA avoids local optima, adapts to thresholds, outperforming RLA2C, RLASD, RA. More UAVs initially reduce delay but excess can increase it due to limited computing power. Conclusions The proposed EH-assisted collaborative air-ground computing offloading framework and IACA algorithm significantly enhance the performance of vehicular networks by optimizing offloading decisions and resource allocations. The simulation results demonstrate the effectiveness of the proposed method in reducing average delay, improving energy efficiency, and increasing system throughput. Future work could explore the integration of more advanced EH technologies and further refine the proposed algorithm to address the complexities of large-scale vehicular networks. (No specific figures or tables are directly referenced in this summary due to format constraints, but the simulations conducted in the paper provide detailed quantitative results to support the discussed findings.)
Available online ,
doi: 10.11999/JEIT240574
Abstract:
With the rapid development of 6G technology and the evolution of the Industrial Internet of Things (IIoT), federated learning has gained significant attention in the industrial sector. This paper has explored the development and application potential of federated learning in 6G-driven IIoT, analyzing 6G's prospects and how its high speed, low latency, and reliability can support data privacy, resource optimization, and intelligent decision-making. First, existing related work is summarized, and the development requirements along with the vision for applying federated learning technology in 6G industrial IoT scenarios are outlined. Based on this, a new paradigm for industrial federated learning, featuring a hierarchical cross-domain architecture, is proposed to integrate 6G and digital twin technologies, enabling ubiquitous, flexible, and layered federated learning. This supports on-demand and reliable distributed intelligent services in typical Industrial IoT scenarios, achieving the integration of Operational and Communication Information Technology (OCIT). Next, the potential research challenges that federated learning might face towards 6G industrial IoT(6G IIoT-FL) are analyzed and summarized, followed by potential solutions or recommendations. Finally, relevant future directions worth attention in this field are highlighted in the study, with the aim of providing insights for subsequent research to some extent.
With the rapid development of 6G technology and the evolution of the Industrial Internet of Things (IIoT), federated learning has gained significant attention in the industrial sector. This paper has explored the development and application potential of federated learning in 6G-driven IIoT, analyzing 6G's prospects and how its high speed, low latency, and reliability can support data privacy, resource optimization, and intelligent decision-making. First, existing related work is summarized, and the development requirements along with the vision for applying federated learning technology in 6G industrial IoT scenarios are outlined. Based on this, a new paradigm for industrial federated learning, featuring a hierarchical cross-domain architecture, is proposed to integrate 6G and digital twin technologies, enabling ubiquitous, flexible, and layered federated learning. This supports on-demand and reliable distributed intelligent services in typical Industrial IoT scenarios, achieving the integration of Operational and Communication Information Technology (OCIT). Next, the potential research challenges that federated learning might face towards 6G industrial IoT(6G IIoT-FL) are analyzed and summarized, followed by potential solutions or recommendations. Finally, relevant future directions worth attention in this field are highlighted in the study, with the aim of providing insights for subsequent research to some extent.
Available online ,
doi: 10.11999/JEIT240677
Abstract:
As an vital component of the global communication network, satellite communication attracts significant attention for its ability to provide seamless global coverage and establish an integrated space-ground information network. Time Hopping (TH), a commonly employed method in satellite communication, is characterized by its robust anti-jamming capability, flexible spectrum utilization and high security. In pursuit of augmenting data transmission security, a system that employs randomly varying TH patterns is devised. To address the issue of limited transmission power, a multi-hop signal coherent combining strategy is proposed. Additionally, under the constraint of low Signal-to-Noise Ratio (SNR) at the receiver, a Cross-Entropy (CE) iteration aided TH patterns and multi-hop carrier phase joint estimation algorithm is presented, which adaptively adjusts the probability distribution of estimated parameters with the SNR loss of the combined signal serving as the objective function, facilitating rapid convergence towards optimal solutions. Simulations demonstrate the superior performance of the proposed algorithm in terms of iterative convergence speed, parameter estimation error, and combined demodulation Bit Error Rate (BER). Compared with the traditional algorithm, the proposed algorithm achieves near-theoretical BER performance with low complexity, significantly improving the stability and reliability of satellite TH communication systems in complex environments.
As an vital component of the global communication network, satellite communication attracts significant attention for its ability to provide seamless global coverage and establish an integrated space-ground information network. Time Hopping (TH), a commonly employed method in satellite communication, is characterized by its robust anti-jamming capability, flexible spectrum utilization and high security. In pursuit of augmenting data transmission security, a system that employs randomly varying TH patterns is devised. To address the issue of limited transmission power, a multi-hop signal coherent combining strategy is proposed. Additionally, under the constraint of low Signal-to-Noise Ratio (SNR) at the receiver, a Cross-Entropy (CE) iteration aided TH patterns and multi-hop carrier phase joint estimation algorithm is presented, which adaptively adjusts the probability distribution of estimated parameters with the SNR loss of the combined signal serving as the objective function, facilitating rapid convergence towards optimal solutions. Simulations demonstrate the superior performance of the proposed algorithm in terms of iterative convergence speed, parameter estimation error, and combined demodulation Bit Error Rate (BER). Compared with the traditional algorithm, the proposed algorithm achieves near-theoretical BER performance with low complexity, significantly improving the stability and reliability of satellite TH communication systems in complex environments.
Available online ,
doi: 10.11999/JEIT240650
Abstract:
Low Earth Orbit navigation system has a large number of satellites and Doppler frequency deviation, so the search space of the receiver with cold start is huge and the acquisition speed is slow. A Code-phase Shift Key and Linear Frequency Modulation (CSK-LFM) navigation signal waveform is proposed, the LFM modulation improves the Doppler tolerance of the signal, and the multiple access broadcast of different satellites is realized by different pseudo-code phases, which can greatly compress the three-dimensional search space of satellite number, time delay, and Doppler. Simulation and experimental results show that when the signal strength is 40dBHz, the acquisition performance of CSK-LFM signal is about 1dB higher than that of traditional Direct Sequence Spread Spectrum (DSSS) modulation navigation signals under the same conditions, and the signal search space can be reduced to 1/10 of that of DSSS modulation.
Low Earth Orbit navigation system has a large number of satellites and Doppler frequency deviation, so the search space of the receiver with cold start is huge and the acquisition speed is slow. A Code-phase Shift Key and Linear Frequency Modulation (CSK-LFM) navigation signal waveform is proposed, the LFM modulation improves the Doppler tolerance of the signal, and the multiple access broadcast of different satellites is realized by different pseudo-code phases, which can greatly compress the three-dimensional search space of satellite number, time delay, and Doppler. Simulation and experimental results show that when the signal strength is 40dBHz, the acquisition performance of CSK-LFM signal is about 1dB higher than that of traditional Direct Sequence Spread Spectrum (DSSS) modulation navigation signals under the same conditions, and the signal search space can be reduced to 1/10 of that of DSSS modulation.
Available online ,
doi: 10.11999/JEIT240663
Abstract:
Covert communication is considered an important branch in the field of network security, which allows for secure data transmission in monitored environments. However, challenges such as complex communication environments and wide coverage areas are encountered in practical communication systems, making the deployment of covert communication difficult. To address this issue, a wireless covert communication system assisted by Intelligent Reflective Surfaces (IRS) and Unmanned Aerial Vehicle (UAV) is proposed in this paper. In this system, IRS is introduced as relay node to forward signals from the transmitter. UAV is utilized as a friendly node for the transmitter, and artificial noise is transmitted to disrupt malicious users’ detection of covert communication. Under the condition of receiver uncertainty regarding the received noise, the minimum error detection probability is derived, and the optimization problem of the system is established with the objective of maximizing the covert communication rate while considering interruption probability as a constraint. The Dinkelbach algorithm is employed to solve the optimization problem. Simulation results demonstrate that the maximum covert communication rate can be achieved when the phase shift of the IRS elements and the UAV’s transmission power are optimized.
Covert communication is considered an important branch in the field of network security, which allows for secure data transmission in monitored environments. However, challenges such as complex communication environments and wide coverage areas are encountered in practical communication systems, making the deployment of covert communication difficult. To address this issue, a wireless covert communication system assisted by Intelligent Reflective Surfaces (IRS) and Unmanned Aerial Vehicle (UAV) is proposed in this paper. In this system, IRS is introduced as relay node to forward signals from the transmitter. UAV is utilized as a friendly node for the transmitter, and artificial noise is transmitted to disrupt malicious users’ detection of covert communication. Under the condition of receiver uncertainty regarding the received noise, the minimum error detection probability is derived, and the optimization problem of the system is established with the objective of maximizing the covert communication rate while considering interruption probability as a constraint. The Dinkelbach algorithm is employed to solve the optimization problem. Simulation results demonstrate that the maximum covert communication rate can be achieved when the phase shift of the IRS elements and the UAV’s transmission power are optimized.
Available online ,
doi: 10.11999/JEIT240624
Abstract:
The task offloading algorithm based on single-agent reinforcement learning encounters strategy degradation issues due to the mutual influence between agents when addressing task offloading in large-scale Multi-access Edge Computing (MEC) systems. In contrast, traditional multi-agent algorithms, such as the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) suffer from poor scalability as the dimensions of the joint action space increase proportionally with the number of agents in the system. To address these issues, the large-scale MEC task offloading problem is modeled as a Partially Observable Markov Decision Process (POMDP), and a task offloading algorithm based on mean-field multi-agent reinforcement learning is proposed. The introduction of a Long Short-Term Memory (LSTM) network addresses the partial observability problem, while mean-field approximation theory reduces the dimensionality of the joint action space. Simulation results demonstrate that the proposed algorithm outperforms single-agent task offloading algorithms in terms of task delay and task drop rate. Furthermore, even with reduced dimensions of the joint action space, the algorithm maintains performance in terms of task delay and task drop rate consistent with MADDPG.
The task offloading algorithm based on single-agent reinforcement learning encounters strategy degradation issues due to the mutual influence between agents when addressing task offloading in large-scale Multi-access Edge Computing (MEC) systems. In contrast, traditional multi-agent algorithms, such as the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) suffer from poor scalability as the dimensions of the joint action space increase proportionally with the number of agents in the system. To address these issues, the large-scale MEC task offloading problem is modeled as a Partially Observable Markov Decision Process (POMDP), and a task offloading algorithm based on mean-field multi-agent reinforcement learning is proposed. The introduction of a Long Short-Term Memory (LSTM) network addresses the partial observability problem, while mean-field approximation theory reduces the dimensionality of the joint action space. Simulation results demonstrate that the proposed algorithm outperforms single-agent task offloading algorithms in terms of task delay and task drop rate. Furthermore, even with reduced dimensions of the joint action space, the algorithm maintains performance in terms of task delay and task drop rate consistent with MADDPG.
Available online ,
doi: 10.11999/JEIT240308
Abstract:
Objective Inverse Lithography Technology (ILT) provides improved imaging effects and a larger process window compared to traditional Optical Proximity Correction (OPC). As chip manufacturing continually reduces process dimensions, ILT has become the leading lithography mask correction technology. This paper first introduces the basic principles and several common implementation methods of the reverse lithography algorithm. It then reviews current research on using reverse lithography technology to optimize lithography masks, as well as analyzes the advantages and existing challenges of this technology. Methods The general process of generating mask patterns in ILT is exemplified using the level set method. First, the target graphics, light sources, and other inputs are identified. Then, the initial mask pattern is created and a pixelated model is constructed. A photolithography model is then established to calculate the aerial image. The general photoresist threshold model is represented by a sigmoid function, which helps derive the imaging pattern on the photoresist. The key element of the ILT algorithm is the cost function, which measures the difference between the wafer image and the target image. The optimization direction is determined based on the chosen cost function. For instance, the continuous cost function can calculate gradients, enabling the use of gradient descent to find the optimal solution. Finally, when the cost function reaches its minimum, the output mask is generated. Results and Discussions This paper systematically introduces several primary methods for implementing ILT. The level set method's main concept is to convert a two-dimensional closed curve into a three-dimensional surface. Here, the closed curve is viewed as the set of intersection lines between the surface and the zero plane. During the ILT optimization process, the three-dimensional surface shape remains continuous. This continuity allows the ILT problem to be transformed into a multivariate optimization problem, solvable using gradient algorithms, machine learning, and other methods. Examples of the level set method's application can be found in both mask optimization and light source optimization. The level set mathematical framework effectively addresses two-dimensional curve evolution. When designing the ILT algorithm, a lithography model determines the optimization direction and velocity for each mask point, employing the level set for mask evolution. Intel has proposed an algorithm that utilizes a pixelated model to optimize the entire chip. However, this approach incurs significant computational costs, necessitating larger mask pixel sizes. Notably, the pixelated model is consistently used throughout the process, with a defined pixelated cost function applicable to multi-color masks. The frequency domain method for calculating the ILT curve involves transforming the mask from the spatial domain into the frequency domain, followed by lithography model calculations. This approach generates a mask with continuous pixel values, which is then gradually converted into a binary mask through multiple steps. When modifying the cost function in frequency domain optimization, all symmetric and repetitive patterns are altered uniformly, preserving symmetry. The transition of complex convolution calculations into multiplication processes within the frequency domain significantly reduces computational complexity and can be accelerated using GPU technology. Due to the prevalent issue of high computational complexity in various lithography mask optimization algorithms, scholars have long pursued machine learning solutions for mask optimization. Early research often overlooked the physical model of photolithography technology, training neural networks solely based on optimized mask features. This oversight led to challenges such as narrow process windows. Recent studies have, however, integrated machine learning with other techniques, enabling the physical model of lithography technology to influence neural network training, resulting in improved optimization results. While the ILT-optimized mask lithography process window is relatively large, its high computational complexity limits widespread application. Therefore, combining machine learning with the ILT method represents a promising research direction. Conclusions Three primary techniques exist for optimizing masks using ILT: the Level Set Method, Intel Pixelated ILT Method, and Frequency Domain Calculation of Curve ILT. The Level Set Method reformulates the ILT challenge into a multivariate optimization issue, utilizing a continuous cost function. This approach allows for the application of established methods like gradient descent, which has attracted significant attention and is well-documented in the literature. In contrast, the Intel method relies entirely on pixelated models and pixelated cost functions, though relevant literature on this method is limited. Techniques in the frequency domain can leverage GPU operations to substantially enhance computational speed, and advanced algorithms also exist for converting curve masks into Manhattan masks. The integration of ILT with machine learning technologies shows considerable potential for development. Further research is necessary to effectively reduce computational complexity while ensuring optimal results. Currently, ILT technology faces challenges such as high computational demands and obstacles in full layout optimization. Collaboration among experts and scholars in integrated circuit design and related fields is essential to improve ILT computational speed and to integrate it with other technologies. We believe that as research on ILT-related technologies advances, it will play a crucial role in helping China's chip industry overcome technological bottlenecks in the future.
Available online ,
doi: 10.11999/JEIT240648
Abstract:
Objective Rotating machinery is essential across various industrial sectors, including energy, aerospace, and manufacturing. However, these machines operate under complex and variable conditions, making timely and accurate fault detection a significant challenge. Traditional diagnostic methods, which use a single sensor and modality, often miss critical features, particularly subtle fault signatures. This can result in reduced reliability, increased downtime, and higher maintenance costs. To address these issues, this study proposes a novel modal fusion deep clustering approach for multi-sensor fault diagnosis in rotating machinery. The main objectives are to: (1) improve feature extraction through time-frequency transformations that reveal important temporal-spectral patterns, (2) implement an attention-based modality fusion strategy that integrates complementary information from various sensors, and (3) use a deep clustering framework to identify fault types without needing labeled training data. Methods The proposed approach utilizes a multi-stage pipeline for thorough feature extraction and analysis. First, raw multi-sensor signals, such as vibration data collected under different load and speed conditions, are preprocessed and transformed with the Short-Time Fourier Transform (STFT). This converts time-domain signals into time-frequency representations, highlighting distinct frequency components related to various fault conditions. Next, Gated Recurrent Units (GRUs) model temporal dependencies and capture long-range correlations, while Convolutional Autoencoders (CAEs) learn hierarchical spatial features from the transformed data. By combining GRUs and CAEs, the framework encodes both temporal and structural patterns, creating richer and more robust representations than traditional methods that rely solely on either technique or handcrafted features. A key innovation is the modality fusion attention mechanism. In multi-sensor environments, individual sensors typically capture complementary aspects of system behavior. Simply concatenating their outputs can lead to suboptimal results due to noise and irrelevant information. The proposed attention-based fusion calculates modality-specific affinity matrices to assess the relationship and importance of each sensor modality. With learnable attention weights, the framework prioritizes the most informative modalities while diminishing the impact of less relevant ones. This ensures the fused representation captures complementary information, resulting in improved discriminative power. Finally, an unsupervised clustering module is integrated into the deep learning pipeline. Rather than depending on labeled data, the model assigns samples to clusters by refining cluster assignments iteratively using a Kullback-Leibler (KL) divergence-based objective. Initially, a soft cluster distribution is created from the learned features. A target distribution is then computed to sharpen and define cluster boundaries. By continuously minimizing the KL divergence between these distributions, the model self-optimizes over time, producing well-separated clusters corresponding to distinct fault types without supervision. Results and Discussions The proposed approach’s effectiveness is illustrated using multi-sensor bearing and gearbox datasets. Compared to conventional unsupervised methods—like traditional clustering algorithms or single-domain feature extraction techniques—this framework significantly enhances clustering accuracy and fault recognition rates. Experimental results show recognition accuracies of approximately 99.16% on gearbox data and 98.63% on bearing data, representing a notable advancement over existing state-of-the-art techniques. These impressive results stem from the synergistic effects of advanced feature extraction, modality fusion, and iterative clustering refinement. By extracting time-frequency features through STFT, the method captures a richer representation than relying solely on raw time-domain signals. The use of GRUs incorporates temporal information, enabling the capture of dynamic signal changes that may indicate evolving fault patterns. Additionally, CAEs reveal meaningful spatial structures from time-frequency data, resulting in low-dimensional yet highly informative embeddings. The modality fusion attention mechanism further enhances these benefits by emphasizing relevant modalities, such as vibration data from various sensor placements or distinct physical principles, thus leveraging their complementary strengths. Through the iterative minimization of KL divergence, the clustering process becomes more discriminative. Initially broad and overlapping cluster boundaries are progressively refined, allowing the model to converge toward stable and well-defined fault groupings. This unsupervised approach is particularly valuable in practical scenarios, where obtaining labeled data is costly and time-consuming. The model’s ability to learn directly from unlabeled signals enables continuous monitoring and adaptation, facilitating timely interventions and reducing the risk of unexpected machine failures. The discussion emphasizes the adaptability of the proposed method. Industrial systems continuously evolve, and fault patterns can change over time due to aging, maintenance, or shifts in operational conditions. The unsupervised method can be periodically retrained or updated with new unlabeled data. This allows it to monitor changes in machinery health and quickly detect new fault conditions without the need for manual annotation. Additionally, the attention-based modality fusion is flexible enough to support the inclusion of new sensor types or measurement channels, potentially enhancing diagnostic performance as richer data sources become available. Conclusions This study presents a modal fusion deep clustering framework designed for the multi-sensor fault diagnosis of rotating machinery. By combining time-frequency transformations with GRU- and CAE-based deep feature encoders, attention-driven modality fusion, and KL divergence-based unsupervised clustering, this approach outperforms traditional methods in accuracy, robustness, and scalability. Key contributions include a comprehensive multi-domain feature extraction pipeline, an adaptive modality fusion strategy for heterogeneous sensor data integration, and a refined deep clustering mechanism that achieves high diagnostic accuracy without relying on labeled training samples. Looking ahead, there are several promising directions. Adding more modalities—like acoustic emissions, temperature signals, or electrical measurements—could lead to richer feature sets. Exploring semi-supervised or few-shot extensions may further enhance performance by utilizing minimal labeled guidance when available. Implementing the proposed model in an industrial setting, potentially for real-time use, would also validate its practical benefits for maintenance decision-making, helping to reduce operational costs and extend equipment life.
Available online ,
doi: 10.11999/JEIT240595
Abstract:
In the complex Marine environment, the known information of the target is seriously disturbed by environmental noise and reverberation, which leads to poor target tracking effect, and it is difficult to extract the utilizable features of the target from these disturbances. This paper proposes an improved extended Kalman filter tracking method based on active waveguide invariant distribution by integrating the coupling characteristics of the target and environment into the target tracking algorithm. Firstly, based on the basic theory of target scattering in shallow sea waveguides, the mathematical model of invariant representation of active waveguide under the condition of receiving and receiving separation is derived, and the constraint relation of distance, frequency, and invariant distribution of active waveguide is obtained. Then this constraint is added to the state vector of the extended Kalman filter, and the fit degree between the model and the real trajectory of the target is improved by adding new constraints to enhance the precision of target tracking. Finally, the tracking performance of the proposed method is verified by simulation experiments and measured data. The results show that: compared with the conventional extended Kalman filter tracking method, the proposed method can improve the tracking accuracy of the target better. The optimization rate of the simulation results can reach about 50%, and the optimization rate of the measured data processing results is about 60%.
In the complex Marine environment, the known information of the target is seriously disturbed by environmental noise and reverberation, which leads to poor target tracking effect, and it is difficult to extract the utilizable features of the target from these disturbances. This paper proposes an improved extended Kalman filter tracking method based on active waveguide invariant distribution by integrating the coupling characteristics of the target and environment into the target tracking algorithm. Firstly, based on the basic theory of target scattering in shallow sea waveguides, the mathematical model of invariant representation of active waveguide under the condition of receiving and receiving separation is derived, and the constraint relation of distance, frequency, and invariant distribution of active waveguide is obtained. Then this constraint is added to the state vector of the extended Kalman filter, and the fit degree between the model and the real trajectory of the target is improved by adding new constraints to enhance the precision of target tracking. Finally, the tracking performance of the proposed method is verified by simulation experiments and measured data. The results show that: compared with the conventional extended Kalman filter tracking method, the proposed method can improve the tracking accuracy of the target better. The optimization rate of the simulation results can reach about 50%, and the optimization rate of the measured data processing results is about 60%.
Available online ,
doi: 10.11999/JEIT240469
Abstract:
An adaptive target tracking method based on marginalized cubature Kalman filter is proposed for the target tracking problem in the presence of sensor measurement biases and unknown time-varying measurement noise. In this method, the constant measurement biases are eliminated by measurement differencing and the abrupt measurement biases can be identified by constructing the beta-Bernoulli indicator variable. The target states at adjacent moments are augmented to meet real-time filtering. The inverse Wishart distribution is used to model the covariance matrix of unknown measurement noise. Consequently, the joint distribution of the target state, indicator variable, and noise covariance matrix can be established, and the approximate posterior of each parameter is solved by variational Bayesian inference. To reduce the computational burden, the augmented state vector is marginalized, and the target tracking based marginal cubature Kalman filter is realized by combining with cubature Kalman filter. Simulation results demonstrate that the proposed method effectively handles the abrupt measurement biases and unknown time-varying measurement noise, achieving accurate target tracking.
An adaptive target tracking method based on marginalized cubature Kalman filter is proposed for the target tracking problem in the presence of sensor measurement biases and unknown time-varying measurement noise. In this method, the constant measurement biases are eliminated by measurement differencing and the abrupt measurement biases can be identified by constructing the beta-Bernoulli indicator variable. The target states at adjacent moments are augmented to meet real-time filtering. The inverse Wishart distribution is used to model the covariance matrix of unknown measurement noise. Consequently, the joint distribution of the target state, indicator variable, and noise covariance matrix can be established, and the approximate posterior of each parameter is solved by variational Bayesian inference. To reduce the computational burden, the augmented state vector is marginalized, and the target tracking based marginal cubature Kalman filter is realized by combining with cubature Kalman filter. Simulation results demonstrate that the proposed method effectively handles the abrupt measurement biases and unknown time-varying measurement noise, achieving accurate target tracking.
Available online ,
doi: 10.11999/JEIT240735
Abstract:
To improve the performance of object segmentation without increasing the quantity of parameters, a self-distillation object segmentation method based on Transformer feature pyramid is proposed, which enhances the utility of Transformer segmentation model. First, a pixel-wise object segmentation model is constructed using Swin Transformer as the backbone network. Then, the auxiliary branch is designed as a combination of Densely connected Atrous Spatial Pyramid Pooling (DenseASPP), Adjacent Feature Fusion Modules (AFFM) and the scoring module, which guide the main network through self-distillation. Finally, a top-down learning strategy is used to guide model learning to ensure consistency in self-distillation. The experiments on four famous public datasets show that the proposed method can effectively improve the accuracy of object segmentation on four public datasets, with a near 1.6% increase in Fβ compared to the Transformer Knowledge Distillation (TKD) method on the Camouflage Object Detection (COD) dataset.
To improve the performance of object segmentation without increasing the quantity of parameters, a self-distillation object segmentation method based on Transformer feature pyramid is proposed, which enhances the utility of Transformer segmentation model. First, a pixel-wise object segmentation model is constructed using Swin Transformer as the backbone network. Then, the auxiliary branch is designed as a combination of Densely connected Atrous Spatial Pyramid Pooling (DenseASPP), Adjacent Feature Fusion Modules (AFFM) and the scoring module, which guide the main network through self-distillation. Finally, a top-down learning strategy is used to guide model learning to ensure consistency in self-distillation. The experiments on four famous public datasets show that the proposed method can effectively improve the accuracy of object segmentation on four public datasets, with a near 1.6% increase in Fβ compared to the Transformer Knowledge Distillation (TKD) method on the Camouflage Object Detection (COD) dataset.
Available online ,
doi: 10.11999/JEIT240640
Abstract:
Integrated Sensing And Communication (ISAC) as a key technology for 6G integrates communication and sensing functions into Wi-Fi devices, providing an effective method for indoor human breath rate sensing. Addressing current challenges of low robustness and blind spots in ISAC-based breath rate sensing, a Variational Mode Decomposition (VMD)-Hilbert-Huang Transform (HHT) based algorithm for breath rate sensing is proposed in this paper. First, Wi-Fi links with high environmental sensitivity are selected to construct the Channel State Information (CSI) ratio model. Then, the subcarriers of the filtered CSI ratio time series are projected, and amplitude and phase information are combined to generate a candidate set of different breathing mode signals. Next, for each subcarrier, the candidate sequence with the highest short-term breath noise ratio is selected as the final breath pattern based on periodicity in the candidates. Then, a threshold is set to select subcarriers, followed by performing time-frequency analysis using VMD and HHT to remove modal components other than the human breath frequency, and reconstructing the remaining modal components. Subsequently, Principal Component Analysis (PCA) is employed to reduce the dimensionality of all reconstructed subcarriers, selecting principal components that contribute over 99% of the variance. The ReliefF algorithm is then used to reconstruct the breath signal as a fused signal. Finally, the breath rate is calculated using a peak detection algorithm on the fused signal. Experimental results show that the proposed detection method achieves the mean estimation accuracy of over 97% in both conference room and corridor scenarios, significantly enhancing robustness and overcoming the "blind spots" problem, outperforming other existing detection schemes.
Integrated Sensing And Communication (ISAC) as a key technology for 6G integrates communication and sensing functions into Wi-Fi devices, providing an effective method for indoor human breath rate sensing. Addressing current challenges of low robustness and blind spots in ISAC-based breath rate sensing, a Variational Mode Decomposition (VMD)-Hilbert-Huang Transform (HHT) based algorithm for breath rate sensing is proposed in this paper. First, Wi-Fi links with high environmental sensitivity are selected to construct the Channel State Information (CSI) ratio model. Then, the subcarriers of the filtered CSI ratio time series are projected, and amplitude and phase information are combined to generate a candidate set of different breathing mode signals. Next, for each subcarrier, the candidate sequence with the highest short-term breath noise ratio is selected as the final breath pattern based on periodicity in the candidates. Then, a threshold is set to select subcarriers, followed by performing time-frequency analysis using VMD and HHT to remove modal components other than the human breath frequency, and reconstructing the remaining modal components. Subsequently, Principal Component Analysis (PCA) is employed to reduce the dimensionality of all reconstructed subcarriers, selecting principal components that contribute over 99% of the variance. The ReliefF algorithm is then used to reconstruct the breath signal as a fused signal. Finally, the breath rate is calculated using a peak detection algorithm on the fused signal. Experimental results show that the proposed detection method achieves the mean estimation accuracy of over 97% in both conference room and corridor scenarios, significantly enhancing robustness and overcoming the "blind spots" problem, outperforming other existing detection schemes.
Available online ,
doi: 10.11999/JEIT240590
Abstract:
In response to the temporary and emergent issue of poor communication in rural and remote areas, an adaptive multi-Unmanned Aerial Vehicle (UAV)-assisted Integrated Sensing And Communication (ISAC) mechanism is proposed in this paper. In scenarios where ground users and sensing targets are randomly distributed in clusters, the mechanism achieves comprehensive communication coverage by rationally scheduling multiple UAVs, providing a novel solution and scheme for UAV-enabled ISAC systems. The spatial deployment of UAVs and their beamforming directed towards ground equipment are primarily addressed in this paper. Under the constraints of the air-ground association policy, the system can maximize the lower bound of the users’ transmission reachable rate by optimizing the set of communication and sensing beamforming variables for the UAVs, while ensuring the basic requirements of ISAC. To solve the considered non-convex optimization problems, the Mean Shift (MS) algorithm based on Gaussian kernels to manage the mixed-integer linear issues within the association strategy is first employed. Additionally, combining the quadratic transformation and Successive Convex Approximation (SCA), the optimization of beamforming is conducted via the Block Coordinate Descent (BCD) method, thereby securing a suboptimal solution. Numerical results validate the effectiveness of the adaptive mechanism.
In response to the temporary and emergent issue of poor communication in rural and remote areas, an adaptive multi-Unmanned Aerial Vehicle (UAV)-assisted Integrated Sensing And Communication (ISAC) mechanism is proposed in this paper. In scenarios where ground users and sensing targets are randomly distributed in clusters, the mechanism achieves comprehensive communication coverage by rationally scheduling multiple UAVs, providing a novel solution and scheme for UAV-enabled ISAC systems. The spatial deployment of UAVs and their beamforming directed towards ground equipment are primarily addressed in this paper. Under the constraints of the air-ground association policy, the system can maximize the lower bound of the users’ transmission reachable rate by optimizing the set of communication and sensing beamforming variables for the UAVs, while ensuring the basic requirements of ISAC. To solve the considered non-convex optimization problems, the Mean Shift (MS) algorithm based on Gaussian kernels to manage the mixed-integer linear issues within the association strategy is first employed. Additionally, combining the quadratic transformation and Successive Convex Approximation (SCA), the optimization of beamforming is conducted via the Block Coordinate Descent (BCD) method, thereby securing a suboptimal solution. Numerical results validate the effectiveness of the adaptive mechanism.
Available online ,
doi: 10.11999/JEIT240012
Abstract:
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 are analyzed.
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 are analyzed.
Available online ,
doi: 10.11999/JEIT240601
Abstract:
Due to the sharing of communication and sensing waveforms, Integrated Sensing And Communication (ISAC) systems are more vulnerable to the risk of information leakage. The Movable Element Simultaneously Transmitting And Reflecting Reconfigurable Intelligent Surface (ME-STAR-RIS) assisted ISAC system from the perspective of covert communication is investigated in this paper. The ME-STAR-RIS array elements can be moved within a certain range to obtain more favorable channel conditions. Based on the discrete element position model, the joint beamforming optimization problem is formulated which aims to jointly design the active beamforming at the ISAC Base Station (BS) and the flexible passive beamforming (including array element positions, phase shifts, and amplitude coefficients) at the ME-STAR-RIS to maximize the probing beam gain at the sensing target within covert communication quality constraints. A two-layer iterative algorithm is proposed to efficiently solve the active and flexible passive beamforming problem. The simulation results verify the effectiveness of the proposed algorithm and show that by moving the elements, a narrower and stronger detection beam can be obtained, which is conducive to improving the system’s performance.
Due to the sharing of communication and sensing waveforms, Integrated Sensing And Communication (ISAC) systems are more vulnerable to the risk of information leakage. The Movable Element Simultaneously Transmitting And Reflecting Reconfigurable Intelligent Surface (ME-STAR-RIS) assisted ISAC system from the perspective of covert communication is investigated in this paper. The ME-STAR-RIS array elements can be moved within a certain range to obtain more favorable channel conditions. Based on the discrete element position model, the joint beamforming optimization problem is formulated which aims to jointly design the active beamforming at the ISAC Base Station (BS) and the flexible passive beamforming (including array element positions, phase shifts, and amplitude coefficients) at the ME-STAR-RIS to maximize the probing beam gain at the sensing target within covert communication quality constraints. A two-layer iterative algorithm is proposed to efficiently solve the active and flexible passive beamforming problem. The simulation results verify the effectiveness of the proposed algorithm and show that by moving the elements, a narrower and stronger detection beam can be obtained, which is conducive to improving the system’s performance.
Display Method:
2024, 46(11): 4081-4091.
doi: 10.11999/JEIT240284
Abstract:
Computing-in-Memory (CiM) architectures based on Resistive Random Access Memory (ReRAM) have been recognized as a promising solution to accelerate deep learning applications. As intelligent applications continue to evolve, deep learning models become larger and larger, which imposes higher demands on the computational and storage resources on processing platforms. However, due to the non-idealism of ReRAM, large-scale ReRAM-based computing systems face severe challenges of low yield and reliability. Chiplet-based architectures assemble multiple small chiplets into a single package, providing higher fabrication yield and lower manufacturing costs, which has become a primary trend in chip design. However, compared to on-chip wiring, the expensive inter-chiplet communication becomes a performance bottleneck for chiplet-based systems which limits the chip’s scalability. As the countermeasure, a novel scaling framework for chiplet-based CiM accelerators, SMCA (SMT-based CiM chiplet Acceleration) is proposed in this paper. This framework comprises an adaptive deep learning task partition strategy and an automated SMT-based workload deployment to generate the most energy-efficient DNN workload scheduling strategy with the minimum data transmission on chiplet-based deep learning accelerators, achieving effective improvement in system performance and efficiency. Experimental results show that compared to existing strategies, the SMCA-generated automatically schedule strategy can reduce the energy costs of inter-chiplet communication by 35%.
Computing-in-Memory (CiM) architectures based on Resistive Random Access Memory (ReRAM) have been recognized as a promising solution to accelerate deep learning applications. As intelligent applications continue to evolve, deep learning models become larger and larger, which imposes higher demands on the computational and storage resources on processing platforms. However, due to the non-idealism of ReRAM, large-scale ReRAM-based computing systems face severe challenges of low yield and reliability. Chiplet-based architectures assemble multiple small chiplets into a single package, providing higher fabrication yield and lower manufacturing costs, which has become a primary trend in chip design. However, compared to on-chip wiring, the expensive inter-chiplet communication becomes a performance bottleneck for chiplet-based systems which limits the chip’s scalability. As the countermeasure, a novel scaling framework for chiplet-based CiM accelerators, SMCA (SMT-based CiM chiplet Acceleration) is proposed in this paper. This framework comprises an adaptive deep learning task partition strategy and an automated SMT-based workload deployment to generate the most energy-efficient DNN workload scheduling strategy with the minimum data transmission on chiplet-based deep learning accelerators, achieving effective improvement in system performance and efficiency. Experimental results show that compared to existing strategies, the SMCA-generated automatically schedule strategy can reduce the energy costs of inter-chiplet communication by 35%.
2024, 46(11): 4092-4100.
doi: 10.11999/JEIT240162
Abstract:
As chip manufacturing has advanced to the sub-micro-nanometer scale, shrinking technology nodes are accelerating link failures in on-chip network, and the growth of failure links reduces the number of available routing paths and might lead to severe traffic congestion or even system crashes. The difficulty in maintaining the correctness of the on-chip system dramatically rises as the technology node shrinks. Previous schemes typically utilize deflection algorithms to bypass packets. However, they incur additional transmission latency due to hop count and raise the probability of deadlock. In order to achieve normal packet transmission when encountering faulty links, a self-Adaptive Fault-tolerant Link NoC design (AFL_NoC) is proposed, which redirects packets encountering a faulty link to another reversible link. The scheme contains a specific implementation of the reversible link and the associated distributed control protocol. The dynamic fault-tolerant link design fully utilizes the idle, available link and ensures that the network communication is not interrupted in case of link failures. Compared with the advanced fault-tolerant deflection routing algorithm QFCAR-W, AFL_NoC can reduce the average delay by 10%, the area overhead by 14.2%, and the power overhead by 9.3%.
As chip manufacturing has advanced to the sub-micro-nanometer scale, shrinking technology nodes are accelerating link failures in on-chip network, and the growth of failure links reduces the number of available routing paths and might lead to severe traffic congestion or even system crashes. The difficulty in maintaining the correctness of the on-chip system dramatically rises as the technology node shrinks. Previous schemes typically utilize deflection algorithms to bypass packets. However, they incur additional transmission latency due to hop count and raise the probability of deadlock. In order to achieve normal packet transmission when encountering faulty links, a self-Adaptive Fault-tolerant Link NoC design (AFL_NoC) is proposed, which redirects packets encountering a faulty link to another reversible link. The scheme contains a specific implementation of the reversible link and the associated distributed control protocol. The dynamic fault-tolerant link design fully utilizes the idle, available link and ensures that the network communication is not interrupted in case of link failures. Compared with the advanced fault-tolerant deflection routing algorithm QFCAR-W, AFL_NoC can reduce the average delay by 10%, the area overhead by 14.2%, and the power overhead by 9.3%.
2024, 46(11): 4101-4111.
doi: 10.11999/JEIT240300
Abstract:
Physical Unclonable Functions (PUFs), as well as Exclusive OR (XOR) operations, play an important role in the field of information security. In order to break through the functional barrier between PUF and logic operation, an integrated design scheme of PUF and multi-bit parallel XOR operation circuit based on the random process deviation of Differential Cascode Voltage Switch Logic (DCVSL) XOR gate cascade unit is proposed by studying the working mechanism of PUF and DCVSL. By adding a pre-charge tube at the differential output of the DCVSL XOR gate and setting a control gate at the ground end, three operating modes of the PUF feature information extraction, XOR/ Negated Exclusive OR (XNOR) operation and power control can be switched freely. Meanwhile, for the PUF response stability problem, the unstable bit hybrid screening technique with extreme and golden operating point participation labeling was proposed. Based on TSMC process of 65 nm, a fully customized layout design for a 10-bit input bit-wide circuit with an area of 38.76 μm2 was carried out. The experimental results show that the1024 -bit output response can be generated in PUF mode, and a stable key of more than 512 bit can be obtained after hybrid screening, which has good randomness and uniqueness; In the operation mode, 10-bit parallel XOR and XNOR operations can be achieved simultaneously, with power consumption and delay of 2.67 μW and 593.52 ps, respectively. In power control mode, the standby power consumption is only 70.5 nW. The proposed method provides a novel way to break the function-wall of PUF.
Physical Unclonable Functions (PUFs), as well as Exclusive OR (XOR) operations, play an important role in the field of information security. In order to break through the functional barrier between PUF and logic operation, an integrated design scheme of PUF and multi-bit parallel XOR operation circuit based on the random process deviation of Differential Cascode Voltage Switch Logic (DCVSL) XOR gate cascade unit is proposed by studying the working mechanism of PUF and DCVSL. By adding a pre-charge tube at the differential output of the DCVSL XOR gate and setting a control gate at the ground end, three operating modes of the PUF feature information extraction, XOR/ Negated Exclusive OR (XNOR) operation and power control can be switched freely. Meanwhile, for the PUF response stability problem, the unstable bit hybrid screening technique with extreme and golden operating point participation labeling was proposed. Based on TSMC process of 65 nm, a fully customized layout design for a 10-bit input bit-wide circuit with an area of 38.76 μm2 was carried out. The experimental results show that the
2024, 46(11): 4112-4122.
doi: 10.11999/JEIT240090
Abstract:
The modular high-voltage power supply, characterized by high efficiency, reliability, and reconfigurability, has found widespread application in high-power high-voltage devices. Among them, the input series output series topology based on the series-parallel resonant converter is suitable for high-frequency high-voltage operating environments, offering advantages such as reduced power losses, winding dielectric losses, and utilizing parasitic parameters of multi-stage transformer. It has broad prospects for application. Current research on this topology primarily focuses on theoretical analysis and efficiency optimization. In practical high-voltage environments, the high-voltage isolation issues between windings of multi-stage transformers have not been effectively addressed. In this paper, a design of shared primary windings for multi-stage transformers is proposed to simplify the high-voltage isolation issues inherent in traditional transformer single-stage winding methods. However, this winding scheme can lead to non-uniform voltage distribution and voltage divergence in multi-stage transformers. Therefore, based on utilizing the parasitic parameters of diodes in transformers and voltage doubling rectifier circuits, an improved topology design is proposed to effectively address the uneven voltage distribution issue. Simulation and experimental validations were conducted, and the results from both simulations and experiments confirm the effectiveness of the proposed high-voltage isolation structure with shared primary windings and the improved topology.
The modular high-voltage power supply, characterized by high efficiency, reliability, and reconfigurability, has found widespread application in high-power high-voltage devices. Among them, the input series output series topology based on the series-parallel resonant converter is suitable for high-frequency high-voltage operating environments, offering advantages such as reduced power losses, winding dielectric losses, and utilizing parasitic parameters of multi-stage transformer. It has broad prospects for application. Current research on this topology primarily focuses on theoretical analysis and efficiency optimization. In practical high-voltage environments, the high-voltage isolation issues between windings of multi-stage transformers have not been effectively addressed. In this paper, a design of shared primary windings for multi-stage transformers is proposed to simplify the high-voltage isolation issues inherent in traditional transformer single-stage winding methods. However, this winding scheme can lead to non-uniform voltage distribution and voltage divergence in multi-stage transformers. Therefore, based on utilizing the parasitic parameters of diodes in transformers and voltage doubling rectifier circuits, an improved topology design is proposed to effectively address the uneven voltage distribution issue. Simulation and experimental validations were conducted, and the results from both simulations and experiments confirm the effectiveness of the proposed high-voltage isolation structure with shared primary windings and the improved topology.
2024, 46(11): 4123-4131.
doi: 10.11999/JEIT240224
Abstract:
Blind signal detection is of great significance in large-scale communication networks and has been widely used. How to quickly obtain blind signal detection results is an urgent need for the new generation of real-time communication networks. Considering this demand, a Complex-valued Hopfield Neural Network (CHNN) circuit is designed that can accelerate blind signal detection from an analog circuit perspective, the proposed circuit can accelerate the blind signal detection by rapidly performing massively parallel calculation in one step. At the same time, the circuit can be programmable by adjusting the conductance and input voltage of the memristor. The Pspice simulation results show that the computing accuracy of the proposed circuit can exceed 99%. Compared with Matlab software simulation, the proposed circuit is three orders of magnitude faster in terms of computing time. And the accuracy can be maintained at more than 99% even under the interference of 20% noise.
Blind signal detection is of great significance in large-scale communication networks and has been widely used. How to quickly obtain blind signal detection results is an urgent need for the new generation of real-time communication networks. Considering this demand, a Complex-valued Hopfield Neural Network (CHNN) circuit is designed that can accelerate blind signal detection from an analog circuit perspective, the proposed circuit can accelerate the blind signal detection by rapidly performing massively parallel calculation in one step. At the same time, the circuit can be programmable by adjusting the conductance and input voltage of the memristor. The Pspice simulation results show that the computing accuracy of the proposed circuit can exceed 99%. Compared with Matlab software simulation, the proposed circuit is three orders of magnitude faster in terms of computing time. And the accuracy can be maintained at more than 99% even under the interference of 20% noise.
2024, 46(11): 4132-4140.
doi: 10.11999/JEIT240210
Abstract:
With the advancement of robot automatic navigation technology, software-based path planning algorithms can no longer satisfy the needs in scenarios of many real-time applications. Fast and efficient hardware customization of the algorithm is required to achieve low-latency performance acceleration. In this work, High Level Synthesis (HLS) of classic A* algorithm is studied. Hardware-oriented data structure and function optimization, varying design constraints are explored to pick the right architecture, which is then followed by FPGA synthesis. Experimental results show that, compared to the conventional Register Transfer Level (RTL) method, the HLS-based FPGA implementation of the A* algorithm can achieve better productivity, improved hardware performance and resource utilization efficiency, which demonstrates the advantages of high level synthesis in hardware customization in algorithm-centric applications.
With the advancement of robot automatic navigation technology, software-based path planning algorithms can no longer satisfy the needs in scenarios of many real-time applications. Fast and efficient hardware customization of the algorithm is required to achieve low-latency performance acceleration. In this work, High Level Synthesis (HLS) of classic A* algorithm is studied. Hardware-oriented data structure and function optimization, varying design constraints are explored to pick the right architecture, which is then followed by FPGA synthesis. Experimental results show that, compared to the conventional Register Transfer Level (RTL) method, the HLS-based FPGA implementation of the A* algorithm can achieve better productivity, improved hardware performance and resource utilization efficiency, which demonstrates the advantages of high level synthesis in hardware customization in algorithm-centric applications.
2024, 46(11): 4141-4150.
doi: 10.11999/JEIT240049
Abstract:
As a new generation of flow-based microfluidics, Fully Programmable Valve Array (FPVA) biochips have become a popular biochemical experimental platform that provide higher flexibility and programmability. Due to environmental and human factors, however, there are usually some physical faults in the manufacturing process such as channel blockage and leakage, which, undoubtedly, can affect the results of bioassays. In addition, as the primary stage of architecture synthesis, high-level synthesis directly affects the quality of sub-sequent design. The fault tolerance problem in the high-level synthesis stage of FPVA biochips is focused on for the first time in this paper, and dynamic fault-tolerant techniques, including a cell function conversion method, a bidirectional redundancy scheme, and a fault mapping method, are presented, providing technical guarantee for realizing efficient fault-tolerant design. By integrating these techniques into the high-level synthesis stage, a high-quality fault-tolerance-oriented high-level synthesis algorithm for FPVA biochips is further realized in this paper, including a fault-aware real-time binding strategy and a fault-aware priority scheduling strategy, which lays a good foundation for the robustness of chip architecture and the correctness of assay outcomes. Experimental results confirm that a high-quality and fault-tolerant high-level synthesis scheme of FPVA biochips can be obtained by the proposed algorithm, providing a strong guarantee for the subsequent realization of a fault-tolerant physical design scheme.
As a new generation of flow-based microfluidics, Fully Programmable Valve Array (FPVA) biochips have become a popular biochemical experimental platform that provide higher flexibility and programmability. Due to environmental and human factors, however, there are usually some physical faults in the manufacturing process such as channel blockage and leakage, which, undoubtedly, can affect the results of bioassays. In addition, as the primary stage of architecture synthesis, high-level synthesis directly affects the quality of sub-sequent design. The fault tolerance problem in the high-level synthesis stage of FPVA biochips is focused on for the first time in this paper, and dynamic fault-tolerant techniques, including a cell function conversion method, a bidirectional redundancy scheme, and a fault mapping method, are presented, providing technical guarantee for realizing efficient fault-tolerant design. By integrating these techniques into the high-level synthesis stage, a high-quality fault-tolerance-oriented high-level synthesis algorithm for FPVA biochips is further realized in this paper, including a fault-aware real-time binding strategy and a fault-aware priority scheduling strategy, which lays a good foundation for the robustness of chip architecture and the correctness of assay outcomes. Experimental results confirm that a high-quality and fault-tolerant high-level synthesis scheme of FPVA biochips can be obtained by the proposed algorithm, providing a strong guarantee for the subsequent realization of a fault-tolerant physical design scheme.
2024, 46(11): 4151-4160.
doi: 10.11999/JEIT240219
Abstract:
With the rapid development of integrated circuit technology, chips are easily implanted with malicious hardware Trojan logic in the process of design, production and packaging. Current security detection methods for IP soft core are logically complex, prone to errors and omissions, and unable to detect encrypted IP soft core. The paper uses the feature differences of non-controllable IP soft core and hardware Trojan Register Transfer Level (RTL) code grayscale map, proposing a hardware Trojan detection method for IP soft cores based on graph feature analysis, through the map conversion and map enhancement to get the standard map, using the texture feature extraction matching algorithm to achieve hardware Trojan detection. The experimental subjects are functional logic units with seven types of typical Trojans implanted during the design phase, and the detection results show that the detection correct rate of seven types of typical hardware Trojans has reached more than 90%, and the average growth rate of the number of successful feature point matches after the image enhancement has reached 13.24%, effectively improving the effectiveness of hardware Trojan detection.
With the rapid development of integrated circuit technology, chips are easily implanted with malicious hardware Trojan logic in the process of design, production and packaging. Current security detection methods for IP soft core are logically complex, prone to errors and omissions, and unable to detect encrypted IP soft core. The paper uses the feature differences of non-controllable IP soft core and hardware Trojan Register Transfer Level (RTL) code grayscale map, proposing a hardware Trojan detection method for IP soft cores based on graph feature analysis, through the map conversion and map enhancement to get the standard map, using the texture feature extraction matching algorithm to achieve hardware Trojan detection. The experimental subjects are functional logic units with seven types of typical Trojans implanted during the design phase, and the detection results show that the detection correct rate of seven types of typical hardware Trojans has reached more than 90%, and the average growth rate of the number of successful feature point matches after the image enhancement has reached 13.24%, effectively improving the effectiveness of hardware Trojan detection.
2024, 46(11): 4161-4169.
doi: 10.11999/JEIT240183
Abstract:
The XEX-based Tweaked-codebook mode with ciphertext Stealing (XTS) is widely used in storage encryption. With the emergence and application of big data computing and novel side-channel analysis methods, the security of the XTS encryption mode has become a matter of concern. Recent studies have attempted side-channel analysis on the XTS mode, aiming to narrow down the key search space by identifying partial keys and tweak values, but a comprehensive analysis of the XTS mode system has not been achieved. In this paper, a side-channel analysis technique targeting the SM4-XTS circuit is proposed. By combining traditional Correlation Power Analysis (CPA) with a multi-stage fusion CPA technique, the technique addresses the binary number shifting issue caused by the iterative modulation multiplication of the tweak values, enabling precise extraction of both the tweak values and keys. To validate the effectiveness of this analytical technique, an SM4-XTS encryption module is implemented on an FPGA to simulate real-world encryption memory scenarios. Experimental results demonstrate that the technique can successfully extract partial tweak values and keys from the target encryption circuit using only 10 000 power traces.
The XEX-based Tweaked-codebook mode with ciphertext Stealing (XTS) is widely used in storage encryption. With the emergence and application of big data computing and novel side-channel analysis methods, the security of the XTS encryption mode has become a matter of concern. Recent studies have attempted side-channel analysis on the XTS mode, aiming to narrow down the key search space by identifying partial keys and tweak values, but a comprehensive analysis of the XTS mode system has not been achieved. In this paper, a side-channel analysis technique targeting the SM4-XTS circuit is proposed. By combining traditional Correlation Power Analysis (CPA) with a multi-stage fusion CPA technique, the technique addresses the binary number shifting issue caused by the iterative modulation multiplication of the tweak values, enabling precise extraction of both the tweak values and keys. To validate the effectiveness of this analytical technique, an SM4-XTS encryption module is implemented on an FPGA to simulate real-world encryption memory scenarios. Experimental results demonstrate that the technique can successfully extract partial tweak values and keys from the target encryption circuit using only 10 000 power traces.
2024, 46(11): 4170-4177.
doi: 10.11999/JEIT240161
Abstract:
Most of the existing lipreading models use a combination of single-layer 3D convolution and 2D convolutional neural networks to extract spatio-temporal joint features from lip video sequences. However, due to the limitations of single-layer 3D convolutions in capturing temporal information and the restricted capability of 2D convolutional neural networks in exploring fine-grained lipreading features, a Multi-Scale Lipreading Network (MS-LipNet) is proposed to improve lip reading tasks. In this paper, 3D spatio-temporal convolution is used to replace traditional two-dimensional convolution in Res2Net network to better extract spatio-temporal joint features, and a spatio-temporal coordinate attention module is proposed to make the network focus on task-related important regional features. The effectiveness of the proposed method was verified through experiments conducted on the LRW and LRW-1000 datasets.
Most of the existing lipreading models use a combination of single-layer 3D convolution and 2D convolutional neural networks to extract spatio-temporal joint features from lip video sequences. However, due to the limitations of single-layer 3D convolutions in capturing temporal information and the restricted capability of 2D convolutional neural networks in exploring fine-grained lipreading features, a Multi-Scale Lipreading Network (MS-LipNet) is proposed to improve lip reading tasks. In this paper, 3D spatio-temporal convolution is used to replace traditional two-dimensional convolution in Res2Net network to better extract spatio-temporal joint features, and a spatio-temporal coordinate attention module is proposed to make the network focus on task-related important regional features. The effectiveness of the proposed method was verified through experiments conducted on the LRW and LRW-1000 datasets.
2024, 46(11): 4178-4187.
doi: 10.11999/JEIT240316
Abstract:
Currently, traditional explicit scene representation Simultaneous Localization And Mapping (SLAM) systems discretize the scene and are not suitable for continuous scene reconstruction. A RGB-D SLAM system based on hybrid scene representation of Neural Radiation Fields (NeRF) is proposed in this paper. The extended explicit octree Signed Distance Functions (SDF) prior is used to roughly represent the scene, and multi-resolution hash coding is used to represent the scene with different details levels, enabling fast initialization of scene geometry and making scene geometry easier to learn. In addition, the appearance color decomposition method is used to decompose the color into diffuse reflection color and specular reflection color based on the view direction to achieve reconstruction of lighting consistency, making the reconstruction result more realistic. Through experiments on the Replica and TUM RGB-D dataset, the scene reconstruction completion rate of the Replica dataset reaches 93.65%. Compared with the Vox-Fusion positioning accuracy, it leads on average by 87.50% on the Replica dataset and by 81.99% on the TUM RGB-D dataset.
Currently, traditional explicit scene representation Simultaneous Localization And Mapping (SLAM) systems discretize the scene and are not suitable for continuous scene reconstruction. A RGB-D SLAM system based on hybrid scene representation of Neural Radiation Fields (NeRF) is proposed in this paper. The extended explicit octree Signed Distance Functions (SDF) prior is used to roughly represent the scene, and multi-resolution hash coding is used to represent the scene with different details levels, enabling fast initialization of scene geometry and making scene geometry easier to learn. In addition, the appearance color decomposition method is used to decompose the color into diffuse reflection color and specular reflection color based on the view direction to achieve reconstruction of lighting consistency, making the reconstruction result more realistic. Through experiments on the Replica and TUM RGB-D dataset, the scene reconstruction completion rate of the Replica dataset reaches 93.65%. Compared with the Vox-Fusion positioning accuracy, it leads on average by 87.50% on the Replica dataset and by 81.99% on the TUM RGB-D dataset.
2024, 46(11): 4188-4197.
doi: 10.11999/JEIT240359
Abstract:
Influenced by factors such as observation conditions and acquisition scenarios, underwater optical image data usually presents the characteristics of high-dimensional small samples and is easily accompanied with noise interference, resulting in many dimension reduction methods lacking robust performance in their recognition process. To solve this problem, a novel 2DPCA method for underwater image recognition, called Dual Flexible Metric Adaptive Weighted 2DPCA (DFMAW-2DPCA), is proposed. DFMAW-2DPCA not only utilizes a flexible robust distance metric mechanism in establishing a dual-layer relationship between reconstruction error and variance, but also adaptively learn matching weights based on the actual state of each sample, which effectively enhances the robustness of the model in underwater noise interference environments and improves recognition accuracy. In this paper, a fast nongreedy algorithm for obtaining the optimal solution is designed and has good convergence. The extensive experimental results on three underwater image databases show that DFMAW-2DPCA has more outstanding overall performance than other 2DPCA-based methods.
Influenced by factors such as observation conditions and acquisition scenarios, underwater optical image data usually presents the characteristics of high-dimensional small samples and is easily accompanied with noise interference, resulting in many dimension reduction methods lacking robust performance in their recognition process. To solve this problem, a novel 2DPCA method for underwater image recognition, called Dual Flexible Metric Adaptive Weighted 2DPCA (DFMAW-2DPCA), is proposed. DFMAW-2DPCA not only utilizes a flexible robust distance metric mechanism in establishing a dual-layer relationship between reconstruction error and variance, but also adaptively learn matching weights based on the actual state of each sample, which effectively enhances the robustness of the model in underwater noise interference environments and improves recognition accuracy. In this paper, a fast nongreedy algorithm for obtaining the optimal solution is designed and has good convergence. The extensive experimental results on three underwater image databases show that DFMAW-2DPCA has more outstanding overall performance than other 2DPCA-based methods.
2024, 46(11): 4198-4207.
doi: 10.11999/JEIT231394
Abstract:
To address the issues of insufficient multi-scale feature expression ability and insufficient utilization of shallow features in memory network algorithms, a Video Object Segmentation (VOS) algorithm based on multi-scale feature enhancement and global local feature aggregation is proposed in this paper. Firstly, the multi-scale feature enhancement module fuses different scale feature information from reference mask branches and reference RGB branches to enhance the expression ability of multi-scale features; At the same time, a global local feature aggregation module is established, which utilizes convolution operations of different sizes of receptive fields to extract features, through the feature aggregation module, the features of the global and local regions are adaptively fused. This fusion method can better capture the global features and detailed information of the target, improving the accuracy of segmentation; Finally, a cross layer fusion module is designed to improve the accuracy of masks segmentation by utilizing the spatial details of shallow features. By fusing shallow features with deep features, it can better capture the details and edge information of the target. The experimental results show that on the public datasets DAVIS2016, DAVIS2017, and YouTube 2018, the comprehensive performance of our algorithm reaches 91.8%, 84.5%, and 83.0%, respectively, and can run in real-time on both single and multi-objective segmentation tasks.
To address the issues of insufficient multi-scale feature expression ability and insufficient utilization of shallow features in memory network algorithms, a Video Object Segmentation (VOS) algorithm based on multi-scale feature enhancement and global local feature aggregation is proposed in this paper. Firstly, the multi-scale feature enhancement module fuses different scale feature information from reference mask branches and reference RGB branches to enhance the expression ability of multi-scale features; At the same time, a global local feature aggregation module is established, which utilizes convolution operations of different sizes of receptive fields to extract features, through the feature aggregation module, the features of the global and local regions are adaptively fused. This fusion method can better capture the global features and detailed information of the target, improving the accuracy of segmentation; Finally, a cross layer fusion module is designed to improve the accuracy of masks segmentation by utilizing the spatial details of shallow features. By fusing shallow features with deep features, it can better capture the details and edge information of the target. The experimental results show that on the public datasets DAVIS2016, DAVIS2017, and YouTube 2018, the comprehensive performance of our algorithm reaches 91.8%, 84.5%, and 83.0%, respectively, and can run in real-time on both single and multi-objective segmentation tasks.
2024, 46(11): 4208-4218.
doi: 10.11999/JEIT240330
Abstract:
Many traditional imbalanced learning algorithms suitable for low-dimensional data do not perform well on image data. Although the oversampling algorithm based on Generative Adversarial Networks (GAN) can generate high-quality images, it is prone to mode collapse in the case of class imbalance. Oversampling algorithms based on AutoEncoders (AE) are easy to train, but the generated images are of lower quality. In order to improve the quality of samples generated by the oversampling algorithm in imbalanced images and the stability of training, a Balanced oversampling method with AutoEncoders and Generative Adversarial Networks (BAEGAN) is proposed in this paper, which is based on the idea of GAN and AE. First, a conditional embedding layer is introduced in the Autoencoder, and the pre-trained conditional Autoencoder is used to initialize the GAN to stabilize the model training; then the output structure of the discriminator is improved, and a loss function that combines Focal Loss and gradient penalty is proposed to alleviate the impact of class imbalance; and finally the Synthetic Minority Oversampling TEchnique (SMOTE) is used to generate high-quality images from the distribution map of latent vectors. Experimental results on four image data sets show that the proposed algorithm is superior to oversampling methods such as Auxiliary Classifier Generative Adversarial Networks (ACGAN) and BAlancing Generative Adversarial Networks (BAGAN) in terms of image quality and classification performance after oversampling and can effectively solve the class imbalance problem in image data.
Many traditional imbalanced learning algorithms suitable for low-dimensional data do not perform well on image data. Although the oversampling algorithm based on Generative Adversarial Networks (GAN) can generate high-quality images, it is prone to mode collapse in the case of class imbalance. Oversampling algorithms based on AutoEncoders (AE) are easy to train, but the generated images are of lower quality. In order to improve the quality of samples generated by the oversampling algorithm in imbalanced images and the stability of training, a Balanced oversampling method with AutoEncoders and Generative Adversarial Networks (BAEGAN) is proposed in this paper, which is based on the idea of GAN and AE. First, a conditional embedding layer is introduced in the Autoencoder, and the pre-trained conditional Autoencoder is used to initialize the GAN to stabilize the model training; then the output structure of the discriminator is improved, and a loss function that combines Focal Loss and gradient penalty is proposed to alleviate the impact of class imbalance; and finally the Synthetic Minority Oversampling TEchnique (SMOTE) is used to generate high-quality images from the distribution map of latent vectors. Experimental results on four image data sets show that the proposed algorithm is superior to oversampling methods such as Auxiliary Classifier Generative Adversarial Networks (ACGAN) and BAlancing Generative Adversarial Networks (BAGAN) in terms of image quality and classification performance after oversampling and can effectively solve the class imbalance problem in image data.
2024, 46(11): 4219-4228.
doi: 10.11999/JEIT240113
Abstract:
Multi-exposure image fusion is used to enhance the dynamic range of images, resulting in higher-quality outputs. However, for blurred long-exposure images captured in fast-motion scenes, such as autonomous driving, the image quality achieved by directly fusing them with low-exposure images using generalized fusion methods is often suboptimal. Currently, end-to-end fusion methods for combining long and short exposure images with motion blur are lacking. To address this issue, a Deblur Fusion Network (DF-Net) is proposed to solve the problem of fusing long and short exposure images with motion blur in an end-to-end manner. A residual module combined with wavelet transform is proposed for constructing the encoder and decoder, where a single encoder is designed for the feature extraction of short exposure images, a multilevel structure based on encoder and decoder is built for feature extraction of long exposure images with blurring, a residual mean excitation fusion module is designed for the fusion of the long and short exposure features, and finally the image is reconstructed by the decoder. Due to the lack of a benchmark dataset, a multi-exposure fusion dataset with motion blur based on the dataset SICE is created for model training and testing. Finally, the designed model and method are experimentally compared with other state-of-the-art step-by-step optimization methods for image deblurring and multi-exposure fusion from both qualitative and quantitative perspectives to verify the superiority of the model and method in this paper for multi-exposure image fusion with motion blur. The validation is also conducted on a multi-exposure dataset acquired from a moving vehicle, and the effectiveness of the proposed method in solving practical problems is demonstrated by the results.
Multi-exposure image fusion is used to enhance the dynamic range of images, resulting in higher-quality outputs. However, for blurred long-exposure images captured in fast-motion scenes, such as autonomous driving, the image quality achieved by directly fusing them with low-exposure images using generalized fusion methods is often suboptimal. Currently, end-to-end fusion methods for combining long and short exposure images with motion blur are lacking. To address this issue, a Deblur Fusion Network (DF-Net) is proposed to solve the problem of fusing long and short exposure images with motion blur in an end-to-end manner. A residual module combined with wavelet transform is proposed for constructing the encoder and decoder, where a single encoder is designed for the feature extraction of short exposure images, a multilevel structure based on encoder and decoder is built for feature extraction of long exposure images with blurring, a residual mean excitation fusion module is designed for the fusion of the long and short exposure features, and finally the image is reconstructed by the decoder. Due to the lack of a benchmark dataset, a multi-exposure fusion dataset with motion blur based on the dataset SICE is created for model training and testing. Finally, the designed model and method are experimentally compared with other state-of-the-art step-by-step optimization methods for image deblurring and multi-exposure fusion from both qualitative and quantitative perspectives to verify the superiority of the model and method in this paper for multi-exposure image fusion with motion blur. The validation is also conducted on a multi-exposure dataset acquired from a moving vehicle, and the effectiveness of the proposed method in solving practical problems is demonstrated by the results.
2024, 46(11): 4229-4235.
doi: 10.11999/JEIT240114
Abstract:
Given that the performance of the Deep Image Prior (DIP) denoising model highly depends on the search space determined by the target image, a new improved denoising model called RS-DIP (Relatively clean image Space-based DIP) is proposed by comprehensively improving its network input, backbone network, and loss function.Initially, two state-of-the-art supervised denoising models are employed to preprocess two noisy images from the same scene, which are referred to as relatively clean images. Furthermore, these two relatively clean images are combined as the network input using a random sampling fusion method. At the same time, the noisy images are replaced with two relatively clean images, which serve as dual-target images. This strategy narrows the search space, allowing exploration of potential images that closely resemble the ground-truth image. Finally, the multi-scale U-shaped backbone network in the original DIP model is simplified to a single scale. Additionally, the inclusion of Transformer modules enhances the network’s ability to effectively model distant pixels. This augmentation bolsters the model’s performance while preserving the network’s search capability. Experimental results demonstrate that the proposed denoising model exhibits significant advantages over the original DIP model in terms of both denoising effectiveness and execution efficiency. Moreover, regarding denoising effectiveness, it surpasses mainstream supervised denoising models.
Given that the performance of the Deep Image Prior (DIP) denoising model highly depends on the search space determined by the target image, a new improved denoising model called RS-DIP (Relatively clean image Space-based DIP) is proposed by comprehensively improving its network input, backbone network, and loss function.Initially, two state-of-the-art supervised denoising models are employed to preprocess two noisy images from the same scene, which are referred to as relatively clean images. Furthermore, these two relatively clean images are combined as the network input using a random sampling fusion method. At the same time, the noisy images are replaced with two relatively clean images, which serve as dual-target images. This strategy narrows the search space, allowing exploration of potential images that closely resemble the ground-truth image. Finally, the multi-scale U-shaped backbone network in the original DIP model is simplified to a single scale. Additionally, the inclusion of Transformer modules enhances the network’s ability to effectively model distant pixels. This augmentation bolsters the model’s performance while preserving the network’s search capability. Experimental results demonstrate that the proposed denoising model exhibits significant advantages over the original DIP model in terms of both denoising effectiveness and execution efficiency. Moreover, regarding denoising effectiveness, it surpasses mainstream supervised denoising models.
2024, 46(11): 4236-4246.
doi: 10.11999/JEIT240257
Abstract:
Considering the issues of limited receptive field and insufficient feature interaction in vision-language tracking framework combineing Bi-level routing Perception and Scattering Visual Trans-formation (BPSVTrack) is proposed in this paper. Initially, a Bi-level Routing Perception Module (BRPM) is designed which combines Efficient Additive Attention(EAA) and Dual Dynamic Adaptive Module(DDAM) in parallel to enable bidirectional interaction for expanding the receptive field. Consequently, enhancing the model’s ability to integrate features between different windows and sizes efficiently, thereby improving the model’s ability to perceive objects in complex scenes. Secondly, the Scattering Vision Transform Module(SVTM) based on Dual-Tree Complex Wavelet Transform(DTCWT) is introduced to decompose the image into low frequency and high frequency information, aiming to capture the target structure and fine-grained details in the image, thus improving the robustness and accuracy of the model in complex environments. The proposed framework achieves accuracies of 86.1%, 64.4%, and 63.2% on OTB99, LaSOT and TNL2K tracking datasets respectively. Moreover, it attains an accuracy of 70.21% on the RefCOCOg dataset, the performance in tracking and locating surpasses that of the baseline model.
Considering the issues of limited receptive field and insufficient feature interaction in vision-language tracking framework combineing Bi-level routing Perception and Scattering Visual Trans-formation (BPSVTrack) is proposed in this paper. Initially, a Bi-level Routing Perception Module (BRPM) is designed which combines Efficient Additive Attention(EAA) and Dual Dynamic Adaptive Module(DDAM) in parallel to enable bidirectional interaction for expanding the receptive field. Consequently, enhancing the model’s ability to integrate features between different windows and sizes efficiently, thereby improving the model’s ability to perceive objects in complex scenes. Secondly, the Scattering Vision Transform Module(SVTM) based on Dual-Tree Complex Wavelet Transform(DTCWT) is introduced to decompose the image into low frequency and high frequency information, aiming to capture the target structure and fine-grained details in the image, thus improving the robustness and accuracy of the model in complex environments. The proposed framework achieves accuracies of 86.1%, 64.4%, and 63.2% on OTB99, LaSOT and TNL2K tracking datasets respectively. Moreover, it attains an accuracy of 70.21% on the RefCOCOg dataset, the performance in tracking and locating surpasses that of the baseline model.
2024, 46(11): 4247-4258.
doi: 10.11999/JEIT240295
Abstract:
Video compressed sensing reconstruction is a highly underdetermined problem, where the low-quality of initial reconstructed and the single-motion estimation approach limit the effective modeling of inter-frames correlations. To improve video reconstruction performance, the Static and Dynamic-domain Prior Enhancement Two-stage reconstruction Network (SDPETs-Net) is proposed. Firstly, a strategy of reconstructing second-order static-domain residuals using reference frame measurements is proposed, and a corresponding Static-domain Prior Enhancement Network (SPE-Net) is designed to provide a reliable basis for dynamic-domain prior modeling. Secondly, the Pyramid Deformable-convolution Combined with Attention-search Network (PDCA-Net) is designed, which combines the advantages of deformable-convolution and attention mechanisms, and a pyramid cascade structure is constructed to effectively model and utilize dynamic-domain prior knowledge. Lastly, the Multi-Feature Fusion Residual Reconstruction Network (MFRR-Net) extracts and fuses key information of each feature from multiple scales to reconstruct residues, alleviating the instability of model training caused by the coupling of the two stages and suppressing feature degradation. Simulation results show that the Peak Signal-to-Noise Ratio (PSNR) is improved by an average of 3.34 dB compared to the representative two-stage network JDR-TAFA-Net under the UCF101 test set, and by an average of 0.79 dB compared to the recent multi-stage network DMIGAN.
Video compressed sensing reconstruction is a highly underdetermined problem, where the low-quality of initial reconstructed and the single-motion estimation approach limit the effective modeling of inter-frames correlations. To improve video reconstruction performance, the Static and Dynamic-domain Prior Enhancement Two-stage reconstruction Network (SDPETs-Net) is proposed. Firstly, a strategy of reconstructing second-order static-domain residuals using reference frame measurements is proposed, and a corresponding Static-domain Prior Enhancement Network (SPE-Net) is designed to provide a reliable basis for dynamic-domain prior modeling. Secondly, the Pyramid Deformable-convolution Combined with Attention-search Network (PDCA-Net) is designed, which combines the advantages of deformable-convolution and attention mechanisms, and a pyramid cascade structure is constructed to effectively model and utilize dynamic-domain prior knowledge. Lastly, the Multi-Feature Fusion Residual Reconstruction Network (MFRR-Net) extracts and fuses key information of each feature from multiple scales to reconstruct residues, alleviating the instability of model training caused by the coupling of the two stages and suppressing feature degradation. Simulation results show that the Peak Signal-to-Noise Ratio (PSNR) is improved by an average of 3.34 dB compared to the representative two-stage network JDR-TAFA-Net under the UCF101 test set, and by an average of 0.79 dB compared to the recent multi-stage network DMIGAN.
2024, 46(11): 4259-4267.
doi: 10.11999/JEIT240253
Abstract:
Sea surface temperature is one of the key elements of the marine environment, which is of great significance to the marine dynamic process and air-sea interaction. Buoy is a commonly used method of sea surface temperature observation. However, due to the irregular distribution of buoys in space, the sea surface temperature data collected by buoys also show irregularity. In addition, it is inevitable that sometimes the buoy is out of order, so that the sea surface temperature data collected is incomplete. Therefore, it is of great significance to reconstruct the incomplete irregular sea surface temperature data. In this paper, the sea surface temperature data is established as a time-varying graph signal, and the graph signal processing method is used to solve the problem of missing data reconstruction of sea surface temperature. Firstly, the sea surface temperature reconstruction model is constructed by using the low rank data and the joint variation characteristics of time-domain and graph-domain. Secondly, a time-varying graph signal reconstruction method based on Low Rank and Joint Smoothness (LRJS) constraints is proposed to solve the optimization problem by using the framework of alternating direction multiplier method, and the computational complexity and the theoretical limit of the estimation error of the method are analyzed. Finally, the sea surface temperature data of the South China Sea and the Pacific Ocean are used to evaluate the effectiveness of the method. The results show that the LRJS method proposed in this paper can improve the reconstruction accuracy compared with the existing missing data reconstruction methods.
Sea surface temperature is one of the key elements of the marine environment, which is of great significance to the marine dynamic process and air-sea interaction. Buoy is a commonly used method of sea surface temperature observation. However, due to the irregular distribution of buoys in space, the sea surface temperature data collected by buoys also show irregularity. In addition, it is inevitable that sometimes the buoy is out of order, so that the sea surface temperature data collected is incomplete. Therefore, it is of great significance to reconstruct the incomplete irregular sea surface temperature data. In this paper, the sea surface temperature data is established as a time-varying graph signal, and the graph signal processing method is used to solve the problem of missing data reconstruction of sea surface temperature. Firstly, the sea surface temperature reconstruction model is constructed by using the low rank data and the joint variation characteristics of time-domain and graph-domain. Secondly, a time-varying graph signal reconstruction method based on Low Rank and Joint Smoothness (LRJS) constraints is proposed to solve the optimization problem by using the framework of alternating direction multiplier method, and the computational complexity and the theoretical limit of the estimation error of the method are analyzed. Finally, the sea surface temperature data of the South China Sea and the Pacific Ocean are used to evaluate the effectiveness of the method. The results show that the LRJS method proposed in this paper can improve the reconstruction accuracy compared with the existing missing data reconstruction methods.
2024, 46(11): 4268-4277.
doi: 10.11999/JEIT240342
Abstract:
In modern electronic countermeasures, grouping of multiple joint radar and communication systems can improve the detection efficiency and collaborative detection capability of the single joint radar and communication system. Due to the high peak to average power ratio of the joint radar and communication signal itself, the signal is easy to be intercepted, and the system’s survivability is seriously threatened. In order to improve the Low Probability of Intercept (LPI) performance of the joint radar and communication signal, a time-frequency structure of grouping LPI joint radar and communication signal with communication subcarrier grouping power optimization and radar subcarrier interleaving equal power optimization under the framework of filter bank multicarrier is proposed in this paper. Then, from the perspective of the information theory, the paper unifies the performance assessment metrics of the system; On this basis, minimizing the intercepted information divergence of the interceptor is taken as the optimization objective, and an LPI optimization model of the group network joint radar and communication signal is established. The paper converts this optimization model into a convex optimization problem and solves it using the Karush-Kuhn-Tucker condition. The simulation results show that the radar interference of the network LPI joint radar and communication signal designed in this paper has inter-node radar interference as low as nearly –60 dB when detecting moving targets, and the communication bit error rate satisfies 10–6 order of magnitude, while the signal-to-noise ratio of the intercepted signal is effectively reduced.
In modern electronic countermeasures, grouping of multiple joint radar and communication systems can improve the detection efficiency and collaborative detection capability of the single joint radar and communication system. Due to the high peak to average power ratio of the joint radar and communication signal itself, the signal is easy to be intercepted, and the system’s survivability is seriously threatened. In order to improve the Low Probability of Intercept (LPI) performance of the joint radar and communication signal, a time-frequency structure of grouping LPI joint radar and communication signal with communication subcarrier grouping power optimization and radar subcarrier interleaving equal power optimization under the framework of filter bank multicarrier is proposed in this paper. Then, from the perspective of the information theory, the paper unifies the performance assessment metrics of the system; On this basis, minimizing the intercepted information divergence of the interceptor is taken as the optimization objective, and an LPI optimization model of the group network joint radar and communication signal is established. The paper converts this optimization model into a convex optimization problem and solves it using the Karush-Kuhn-Tucker condition. The simulation results show that the radar interference of the network LPI joint radar and communication signal designed in this paper has inter-node radar interference as low as nearly –60 dB when detecting moving targets, and the communication bit error rate satisfies 10–6 order of magnitude, while the signal-to-noise ratio of the intercepted signal is effectively reduced.
2024, 46(11): 4278-4286.
doi: 10.11999/JEIT240389
Abstract:
The design and optimization issues of secure downlink transmission scheme for two users based on rate-splitting multiple access are studied. Considering a scenario where partial messages sent to two users need to be kept confidential between users, the sum rate of non-confidential messages is maximized while ensuring the transmission rate of confidential messages. The common stream only carries the non-confidential messages, while the private streams carry both the non-confidential and confidential messages in a time-sharing manner. Transmit precoding vectors for each message flow, rate splitting, transmission time allocation for the private streams of non-confidential and confidential messages are jointly optimized. By decomposing the original problem into a two-level optimization problem and using methods such as binary search, relaxation variables, and successive convex approximation, the original problem is transformed and solved. The simulation results show that the proposed scheme can achieve higher non-confidential sum rate compared to the rate-splitting multiple access, where the private streams carry only the confidential messages, and space division multiple access with time-sharing between non-confidential messages and confidential messages.
The design and optimization issues of secure downlink transmission scheme for two users based on rate-splitting multiple access are studied. Considering a scenario where partial messages sent to two users need to be kept confidential between users, the sum rate of non-confidential messages is maximized while ensuring the transmission rate of confidential messages. The common stream only carries the non-confidential messages, while the private streams carry both the non-confidential and confidential messages in a time-sharing manner. Transmit precoding vectors for each message flow, rate splitting, transmission time allocation for the private streams of non-confidential and confidential messages are jointly optimized. By decomposing the original problem into a two-level optimization problem and using methods such as binary search, relaxation variables, and successive convex approximation, the original problem is transformed and solved. The simulation results show that the proposed scheme can achieve higher non-confidential sum rate compared to the rate-splitting multiple access, where the private streams carry only the confidential messages, and space division multiple access with time-sharing between non-confidential messages and confidential messages.
2024, 46(11): 4287-4294.
doi: 10.11999/JEIT240275
Abstract:
To solve the bottleneck problem of constrained spectrum resource for Unmanned Aerial Vehicles (UAVs) in unlicensed bands, a co-optimization scheme high spectral efficiency in underlay mechanism is proposed for UAV-assisted monitoring communication networks in urban environment. Considering the high maneuverability of UAVs, the air-to-ground channel is modeled as a probabilistic Line-of-Sight (LoS) channel, and the co-channel interference and maximum speed constraints are adopted to formulate a hybrid resource optimization model for power allocation and trajectory planning, enabling UAVs to construct the fast transmission scheme for monitoring data with occupied spectrum within the given time. The original problem is an NP-hard and non-convex integer problem, which is first decomposed into a two-layer programming problem, and then solved by applying the slack variable and Successive Convex Approximation (SCA) technologies to transform the trajectory design problem into a convex programming problem. Compared with the Particle Swarm Optimization (PSO) algorithm, the proposed joint optimization scheme is verified to improve the spectral efficiency by up to about 19% in simulations. For high-dimensional trajectory planning problems, the SCA-based algorithm is proved to have lower complexity and faster convergence.
To solve the bottleneck problem of constrained spectrum resource for Unmanned Aerial Vehicles (UAVs) in unlicensed bands, a co-optimization scheme high spectral efficiency in underlay mechanism is proposed for UAV-assisted monitoring communication networks in urban environment. Considering the high maneuverability of UAVs, the air-to-ground channel is modeled as a probabilistic Line-of-Sight (LoS) channel, and the co-channel interference and maximum speed constraints are adopted to formulate a hybrid resource optimization model for power allocation and trajectory planning, enabling UAVs to construct the fast transmission scheme for monitoring data with occupied spectrum within the given time. The original problem is an NP-hard and non-convex integer problem, which is first decomposed into a two-layer programming problem, and then solved by applying the slack variable and Successive Convex Approximation (SCA) technologies to transform the trajectory design problem into a convex programming problem. Compared with the Particle Swarm Optimization (PSO) algorithm, the proposed joint optimization scheme is verified to improve the spectral efficiency by up to about 19% in simulations. For high-dimensional trajectory planning problems, the SCA-based algorithm is proved to have lower complexity and faster convergence.
2024, 46(11): 4295-4304.
doi: 10.11999/JEIT240201
Abstract:
The Multi-Model Gaussian Mixture-Probability Hypothesis Density (MM-GM-PHD) filter is widely used in uncertain maneuvering target tracking, but it does not maintain parallel estimates under different models, leading to the model-related likelihood lagging behind unknown target maneuvers. To solve this issue, a Joint Multi-Gaussian Mixture PHD (JMGM-PHD) filter is proposed and applied to bearings-only multi-target tracking in this paper. Firstly, a JMGM model is derived, where each single-target state estimate is described by a set of parallel Gaussian functions with model probabilities, and the probability of this state estimate is characterized by a nonegative weight. The weights, model-related probabilities, means and covariances are collectively called JMGM components. According to the Bayesian rule, the updating method of the JMGM components is derived. Then, the multi-target PHD is approximated using the JMGM model. According to the Interactive Multi-Model (IMM) rule, the interacting, prediction and estimation methods of the JMGM components are derived. When addressing Bearings-Only Tracking (BOT), a method based on the derivative rule for composite functions is derived to compute the linearized observation matrix of observers that simultaneously performs translations and rotations. The proposed JMGM-PHD filter preserves the form of regular single-model PHD filter but can adaptively track uncertain maneuvering targets. Simulations show that our algorithm overcomes the likelihood lag issue and outperforms the MM-GM-PHD filter in terms of tracking accuracy and computation cost.
The Multi-Model Gaussian Mixture-Probability Hypothesis Density (MM-GM-PHD) filter is widely used in uncertain maneuvering target tracking, but it does not maintain parallel estimates under different models, leading to the model-related likelihood lagging behind unknown target maneuvers. To solve this issue, a Joint Multi-Gaussian Mixture PHD (JMGM-PHD) filter is proposed and applied to bearings-only multi-target tracking in this paper. Firstly, a JMGM model is derived, where each single-target state estimate is described by a set of parallel Gaussian functions with model probabilities, and the probability of this state estimate is characterized by a nonegative weight. The weights, model-related probabilities, means and covariances are collectively called JMGM components. According to the Bayesian rule, the updating method of the JMGM components is derived. Then, the multi-target PHD is approximated using the JMGM model. According to the Interactive Multi-Model (IMM) rule, the interacting, prediction and estimation methods of the JMGM components are derived. When addressing Bearings-Only Tracking (BOT), a method based on the derivative rule for composite functions is derived to compute the linearized observation matrix of observers that simultaneously performs translations and rotations. The proposed JMGM-PHD filter preserves the form of regular single-model PHD filter but can adaptively track uncertain maneuvering targets. Simulations show that our algorithm overcomes the likelihood lag issue and outperforms the MM-GM-PHD filter in terms of tracking accuracy and computation cost.
2024, 46(11): 4305-4316.
doi: 10.11999/JEIT240242
Abstract:
Ground Penetrating Radar (GPR) is identified as a non-destructive method usable for the identification of underground targets. Existing methods often struggle with variable target sizes, complex image recognition, and precise target localization. To address these challenges, an innovative method is introduced that leverages a dual YOLOv8-pose model for the detection and precise localization of hyperbolic keypoint. This method, termed Dual YOLOv8-pose Keypoint Localization (DYKL), offers a sophisticated solution to the challenges inherent in GPR-based target identification and positioning. The proposed model architecture includes two stages: firstly, the YOLOv8-pose model is employed for the preliminary detection of GPR targets, adeptly identifying regions that are likely to contain these targets. Secondly, building upon the training weights established in the first phase, the model further hones the YOLOv8-pose network. This refinement is geared towards the precise detection of keypoints within the candidate target features, thereby facilitating the automated identification and exact localization of underground targets with enhanced accuracy. Through comparison with four advanced deep-learning models— Cascade Region-based Convolutional Neural Networks (Cascade R-CNN), Faster Region-based Convolutional Neural Networks (Faster R-CNN), Real-Time Models for object Detection (RTMDet), and You Only Look Once v7(YOLOv7-face), the proposed DYKL model exhibits an average recognition accuracy of 98.8%, surpassing these models. The results demonstrate the DYKL model’s high recognition accuracy and robustness, serving as a benchmark for the precise localization of subterranean targets.
Ground Penetrating Radar (GPR) is identified as a non-destructive method usable for the identification of underground targets. Existing methods often struggle with variable target sizes, complex image recognition, and precise target localization. To address these challenges, an innovative method is introduced that leverages a dual YOLOv8-pose model for the detection and precise localization of hyperbolic keypoint. This method, termed Dual YOLOv8-pose Keypoint Localization (DYKL), offers a sophisticated solution to the challenges inherent in GPR-based target identification and positioning. The proposed model architecture includes two stages: firstly, the YOLOv8-pose model is employed for the preliminary detection of GPR targets, adeptly identifying regions that are likely to contain these targets. Secondly, building upon the training weights established in the first phase, the model further hones the YOLOv8-pose network. This refinement is geared towards the precise detection of keypoints within the candidate target features, thereby facilitating the automated identification and exact localization of underground targets with enhanced accuracy. Through comparison with four advanced deep-learning models— Cascade Region-based Convolutional Neural Networks (Cascade R-CNN), Faster Region-based Convolutional Neural Networks (Faster R-CNN), Real-Time Models for object Detection (RTMDet), and You Only Look Once v7(YOLOv7-face), the proposed DYKL model exhibits an average recognition accuracy of 98.8%, surpassing these models. The results demonstrate the DYKL model’s high recognition accuracy and robustness, serving as a benchmark for the precise localization of subterranean targets.
2024, 46(11): 4317-4327.
doi: 10.11999/JEIT240286
Abstract:
A novel and effective information geometry-based method for detecting radar targets is proposed based on the theory of matrix information geometry. Due to the poor discriminative power between the target and the clutter on matrix manifold under complex heterogeneous clutter background with low Signal-to-Clutter Ratio (SCR), in this study, the problem of unsatisfactory performance for the conventional information geometry detector is considered, therefore, to address this issue, a manifold transformation-based information geometry detector is proposed. Concretely, a manifold-to-manifold mapping scheme is designed, and a joint optimization method based on the geometric distance between the Cell Under Test (CUT) and the clutter centroid is presented to enhance the discriminative power between the target and the clutter on the mapped manifold. Finally, the superior performance of the proposed method is evaluated using simulated and real clutter data. The results of simulated data show that the detection probability of the proposed method is over 60% when the SCR exceeds 1 dB. Meanwhile, the real data results confirm that the proposed method can achieve SCR improvement about 3～6 dB compared with the conventional information geometry detector.
A novel and effective information geometry-based method for detecting radar targets is proposed based on the theory of matrix information geometry. Due to the poor discriminative power between the target and the clutter on matrix manifold under complex heterogeneous clutter background with low Signal-to-Clutter Ratio (SCR), in this study, the problem of unsatisfactory performance for the conventional information geometry detector is considered, therefore, to address this issue, a manifold transformation-based information geometry detector is proposed. Concretely, a manifold-to-manifold mapping scheme is designed, and a joint optimization method based on the geometric distance between the Cell Under Test (CUT) and the clutter centroid is presented to enhance the discriminative power between the target and the clutter on the mapped manifold. Finally, the superior performance of the proposed method is evaluated using simulated and real clutter data. The results of simulated data show that the detection probability of the proposed method is over 60% when the SCR exceeds 1 dB. Meanwhile, the real data results confirm that the proposed method can achieve SCR improvement about 3～6 dB compared with the conventional information geometry detector.
2024, 46(11): 4328-4334.
doi: 10.11999/JEIT240188
Abstract:
The central symmetry based on the virtual array is a necessary fundamental assumption for the structure transformation of Uniform Circular Arrays (UCAs). In this paper, the virtual signal model for circular arrays is used to make an eigen analysis, and an efficient two-dimensional direction finding algorithm is proposed for arbitrary UCAs and Non Uniform Circular Arrays (NUCAs), where the structure transformation of linear arrays is avoided. As such, the Forward/Backward average of the Array Covariance Matrix (FBACM) and the sum-difference transformation method after separating the real and imaginary parts are both utilized to obtain the manifold and real-valued subspace with matching dimensions. Moreover, the linear relationship between the obtained real-valued subspace and the original complex-valued subspace is revealed, where the spatial spectrum is reconstructed without fake targets. The proposed method can be generalized to NUCAs, enhancing the adaptability of real-valued algorithms to circular array structures. Numerical simulations are applied to demonstrate that with significantly reduced complexity, the proposed method in this paper can provide similar performances and better angle resolution as compared to the traditional UCAs based on the mode-step. Meanwhile, the proposed method demonstrates high robustness with amplitude and phase errors in practical scenarios.
The central symmetry based on the virtual array is a necessary fundamental assumption for the structure transformation of Uniform Circular Arrays (UCAs). In this paper, the virtual signal model for circular arrays is used to make an eigen analysis, and an efficient two-dimensional direction finding algorithm is proposed for arbitrary UCAs and Non Uniform Circular Arrays (NUCAs), where the structure transformation of linear arrays is avoided. As such, the Forward/Backward average of the Array Covariance Matrix (FBACM) and the sum-difference transformation method after separating the real and imaginary parts are both utilized to obtain the manifold and real-valued subspace with matching dimensions. Moreover, the linear relationship between the obtained real-valued subspace and the original complex-valued subspace is revealed, where the spatial spectrum is reconstructed without fake targets. The proposed method can be generalized to NUCAs, enhancing the adaptability of real-valued algorithms to circular array structures. Numerical simulations are applied to demonstrate that with significantly reduced complexity, the proposed method in this paper can provide similar performances and better angle resolution as compared to the traditional UCAs based on the mode-step. Meanwhile, the proposed method demonstrates high robustness with amplitude and phase errors in practical scenarios.
News
more >
- JEIT has been included by DOAJ
- Call for papers of Radar Signal Processing Issue for JEIT
- WeChat public platform has been open for JEIT
- Call for papaers of Online Social Network for JEIT
- JEIT attended the 973 Project " social network "
- 2016 Annual NNFS Application Code and Research Direction
- JEIT Held the First Meeting of the Seventh Editorial Board
- JEIT won the title of "2014 Chinese TOP 100 Outstanding Academic Journals"
Conference
more >
- Call for papers of the 9th CWSN2015 Conference
- Notice to the 26th Annual Conference of Circle and System Branch, Chinese Institute of Electronics
- Notice of MAN2015 & ICMAN2015 Conference
- Call for papers 27th Annual Conference of Circle and System Branch, Chinese Institute of Electronics
- Notice on hosting the annual meeting of the 2016 Software Radar Technology Application Conference
- Notice on hosting the annual meeting of the 2016 Software Radar Technology Application Conference
- Call for paper of the 27th academic annual conference of circuits and systems branch
- Call for Papers of the Maritime Informantion Processing and Fusion
Author Center
Wechat Community