SVM Aided Signal Detection in Generalized Spatial Modulation VLC System

Abstract

Efficient signal detection technique is developed for generalized spatial modulation (GSM) modulated indoor visible light communication (VLC) system, which is aided by a popular machine learning approach termed as support vector machine (SVM). For general VLC system, maximum likelihood (ML) detector has a high computational complexity, although it is the optimal detection algorithm. In order to alleviate this high computational complexity problem, we take the signal detection task in GSM-VLC system as a multiple classification problem, and propose an efficient signal detection scheme for the considered GSM-VLC system aided by SVM, which has lower computational complexity and nearly optimal detection accuracy. Simulation results demonstrate the efficiency of the proposed SVM aided signal detection technique in the considered indoor GSM-VLC system.