Performance of DWT-ANN based signal detector/equalizer for DPIM in practical indoor optical wireless links

Artificial neural network (ANN) finds its application in communication engineering in a diverse areas such as channel equalization, channel modelling, error control code because of its capability of nonlinear processing, adaptability, and parallel processing. On the other hand, the wavelet transform (WT) with both the time and the frequency resolution provides the exact representation of signal in both domains. Applying these modern tools to signal processing in channel equalization and digital signal detection provide an enhanced performance compared to the traditional tools. In this paper, the slot error rate (SER) performance of digital pulse interval modulation (DPIM) in diffuse indoor optical wireless links employing equalization using discrete WT (DWT) and ANN is reported. The simulation results show that a performance gain of ∼8 dB is achieved by utilizing the new approach compared to the traditional approach based on the finite impulse response (FIR) digital filters. © 2008 IEEE.