Nonlinear geometric feature equalizers based on minimum bit error rate criterion for EBPSK communications
Renxiang Zhu, Lenan Wu · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2007
A novel nonlinear geometric feature equalizer based on minimum bit error rate is proposed in this paper for the filtering of noise and interference whose frequency band overlaps with the desired signal in extended binary phase shifting keying communications. Considering that the desired signal and the interference have different stochastic characters in feature space, the proposed equalization algorithm recovers the desired signal by neural network. Simulation results show that when extended binary phase shifting keying signals are contaminated by relatively strong interference, geometric feature equalizers can provide very low bit error rate. This will provide an alternate filter used for extended binary phase shifting keying communications and also for deep-space communications etc.