Probabilistic Neural Network Based Equalizer for Indoor Visible Light Communications

摘要

In this paper, we present a new equalizer based on probabilistic neural networks (PNN) for visible light communication (VLC) systems. While traditional artificial neural networks (ANN) type equalizers have to identify the distribution of the received signal, in our method kernel density estimation (KDE) is exploited to obtain the probability density function (PDF) of the states of the received signal, which reduces the computational complexity, especially when severe inter symbol interference (ISI) exists and when the number of signal states in the observation space increases. Then the constructed PDF is used to find the optimal Bayes solution at the receiver. Moreover, the decision feedback (DF) mechanism is utilized for further performance enhancements. The simulated bit error rate (BER) performances of the presented PNN based equalizers are compared with linear equalizer (LE) and conventional decision feedback equalizer (DFE). Simulation results demonstrate that the PNN-based equalizer without and with DF outperform LE and conventional DFE, respectively, thanks to the employment of KDE.