基于SVM的水下LED可见光通信信号检测方法

SVM-based underwater LED visible light communication signal detection method

针对传统直流偏置正交频分复用(DCO-OFDM)水下发光二极管(LED)可见光通信系统的信号检测性能较差且通信距离较近的问题,采用了基于支持向量机(SVM)的水下LED可见光通信信号检测方法,即先对信号数据进行网格搜索和交叉验证,得到最优的SVM模型,再用所得模型对接收信号做出判决。仿真结果表明:在相同通信距离下且低信噪比(SNR)时,基于SVM检测的系统性能与基于直接判决最小均方(DD-LMS)检测的结果相当,高SNR时,前者优于后者;在相同误码率且通信距离小于3 m时,基于SVM检测的系统通信距离略远于DD-LMS检测。

Aiming at the problem of poor signal detection performance and short communication distance of traditional direct-currnt biased orthogonal frequency division multiplexing(DCO-OFDM)underwater light-emitting diode(LED)visible light communi-cation system,a signal detection method of underwater LED visible light communication based on support vector machine(SVM)is proposed.Firstly,grid search and cross validation are performed on the signal data to obtain the optimal SVM model,then the received signal is judged by the model.The simulation results show that the system performance based on SVM is equivalent to that based on direct decision least mean square(DD-LMS)at the same communication distance and low signal to noise ratio(SNR),when the SNR is high,the former is better than the latter.Under the same bit error rate,when the communication distance is less than 3 m,the communication distance of the system based on SVM detection is slightly longer than that of DD-LMS detection.