基于神经网络的可见光通信接收系统的研究

发布时间：2018-11-27 14:51

【摘要】：由于码间干扰的影响,导致可见光通信系统的误码率提升。为此,提出了一种基于人工神经元网络(ANN)的接收系统,采用角度分集接收技术采集信号,并通过神经元网络对所获得的多组数据进行合并优化构成总的输出信号。该接收系统可以有效地降低码间干扰对系统的影响,提高接收信号的信噪比(SNR),降低系统的误码率(BER)。采用Matlab软件模拟仿真信号传输实验以验证该系统的性能及优越性。仿真结果表明,在信源与环境的信噪比相同情况下,基于神经元网络均衡处理的分集接收系统误码率比传统的使用单输入单输出(SISO)技术的系统误码率更低,并且可以减弱码间干扰所带来的影响。优化了可见光通信(VLC)系统的信道性能,具有广阔的应用前景。
[Abstract]:Due to the influence of inter-symbol interference (ISI), the BER of visible light communication system is improved. In this paper, a receiving system based on artificial neural network (ANN) is proposed, in which angle diversity is used to collect the signal, and the neural network is used to combine and optimize the multiple sets of data to form the total output signal. The receiver system can effectively reduce the influence of inter-symbol interference on the system, and improve the SNR of received signal (SNR), to reduce the bit error rate (BER).) of the system. The Matlab software is used to simulate the simulation signal transmission experiment to verify the performance and superiority of the system. The simulation results show that the bit error rate of the diversity receiving system based on neural network equalization is lower than that of the traditional single-input single-output (SISO) system under the same signal to noise ratio between the source and the environment. And can reduce the impact of inter-symbol interference. The channel performance of (VLC) system for visible light communication is optimized and has a broad application prospect.
【作者单位】：华南理工大学材料科学与工程学院;华南理工大学发光材料与器件国家重点实验室;
【基金】：广东省战略性新兴产业专项(2011A081301017,2012A080304012,2012A080304001) 广州市科技计划(2013J4300021) 国家级大学生创新创业训练计划项目(201510561003)
【分类号】：TN929.1

【参考文献】