复数离散Hopfield网络盲检测64QAM信号

张昀; 张志涌

doi:10.3724/SP.J.1146.2010.00921

复数离散Hopfield网络盲检测64QAM信号

doi: 10.3724/SP.J.1146.2010.00921

张昀^{*①② 张志涌,},
张志涌

基金项目:

国家自然科学基金(60772060)资助课题

计量
- 文章访问数: 3458
- HTML全文浏览量: 89
- PDF下载量: 631
- 被引次数: 0
出版历程
- 收稿日期: 2010-08-27
- 修回日期: 2010-11-14
- 刊出日期: 2011-02-19

Blind Detection of 64QAM Signals with a Complex Discrete Hopfield Network

Zhang Yun^{*①② 张志涌
,},
Zhang Zhi-Yong

摘要

摘要: 针对复数多电平QAM信号的盲检测问题，该文提出了一个新的复数离散多电平Hopfield神经网络。该网络的实部、虚部各含一个多电平离散激励实函数。该文分析了经典两电平离散Hopfield神经网络能量函数的局限性，构造了一个新的复数多电平神经网的能量函数，并用此能量函数讨论了神经网的稳定性。当该神经网的权矩阵借助接收数据补投影算子构成时，该复数离散多电平Hopfield网络可有效地求解带整数约束的二次规划问题，从而实现QAM信号盲检测。仿真试验表明：该算法所需接收数据较短，就可到达全局真平衡点，计算难度大大降低，具有良好的快速性。
- 信号处理 /
- 复数离散Hopfield神经网络 /
- 盲检测 /
- QAM信号
Abstract: A novel algorithm based on Complex Discrete Hopfield Neural Network (CDHNN) is proposed to detect blindly multi-valued QAM signals in this paper. A multi-valued discrete activation function is constructed in both of the real part and imaginary part of CDHNN. Limitation for the energy function of the classic binary-valued discrete Hopfield neural network is analyzed in this paper and a new energy function for CDHNN is also constructed. Further more the stability for multi-valued CDHNN is also proved in the paper. While the weighted matrix of CDHNN is constructed by the complementary projection operator of received signals, the problem of quadratic optimization with integer constraints can successfully solved with the CDHNN, and the QAM signals are blindly detected. Simulation results show that the algorithm reaches the real equilibrium points with shorter received signals and show high speed to detect blindly multi-valued signals.
- Signal processing /
- Complex Discrete Hopfield Neural Network (CDHNN) /
- Blind detection /
- QAM signal

HTML全文

参考文献(1)

[1] Wang H and Zhang L. Optimal Hopfield neural network and applicationg for multi-user detection[C]. 2009 International Conference on Communication Software and Networks, Chengdu, China, Feb. 2009: 567-570. [2] Ding Z and Li Y. Blind Equalization and Identification[M]. New York: Marcel Dekker 2002, Chapter 5. [3] Giannakis G B, Hua Y B, and Stoica P, et al.. Signal Processing Advances in Wireless and Mobile Communications, vol. 1: Trends in Channel Estimation and Equalization[M]. NJ, USA, Prentice Hall PTR Upper Saddle River, 2000, Chapter 6. [4] Achim E and Werner T G, et al.. A survey of multiuser / multisubchannel detection schemes based on recurrent neural networks[J].Wireless Communications and Mobile Computing.2002, 2(3):269-284 [5] Sheikh A T and Sheikh S A. Efficient Variants of Square Contour algorithm for blind equalization of QAM signals[C]. International Conference on Electrical, Computer Engineering, Hong Kong, China March 23-25, 2009: 200-208. [6] Quan Q and Kim J. Intercarrier interference suppression for OFDM systems using Hopfield neural network[J]. International Journal of Computer Science and Network Security, 2006, 6(6): 157-162. [7] Zurada J M. Neural networks: binary monotonic and multiple-valued[C]. Proc. of the 30th IEEE International Symposium on Multiple-Valued Logic, Portland, Oregon, May 23-25, 2000: 67-74. [8] 张志涌，张昀. 复数Hopfield盲恢复多用户QPSK信号[J]. 东南大学学报，2008, 38(12): 18-22. Zhang Z Y and Zhang Y. Blind recovery of multiuser QPSK with a complex Hopfield network[J]. Journal of Southeast University, 2008, 38(12): 18-22. [9] Liu Y and You Z. Stability analysis for the generalized Hopfield neural networks with multi-level activation functions[J].Neurocomputing.2008, 71(16/17/18):3595-3601 [10] Zhou W and Zurada J M. A class of discrete time recurrent neural networks with multivalued neurons[J].Neurocomputing.2009, 72(16/17/18):3782-3788 [11] NITTA T. Complex-Valued Neural Networks: Utilizing High-Dimensional Parameters[M]. Hershey PA USA: IGI Global, 2009: 361-365. [12] Gupta M M, Jin L, and Homma N. Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory[M]. New Jersey: IEEE Press, 2003: 469-577.

施引文献

资源附件(0)

访问统计