NN-based IDF demodulator in band-limited communication system
To meet the spectrum requirement in the future wireless communication system, the m-ary phase position shift keying as a type of the spectrally efficient modulation has been considered in this study. However, the inter-symbol interference (ISI), the waveform distortion and the non-white noise are introduced by the band-pass infinite impulse response filters, which is adopted to limit the signal bandwidth and eliminate the out-band interference. The traditional demodulation methods based on impacting filter or matched filter cannot work well in these scenarios. Therefore, a neural network (NN)-based demodulator is proposed to solve the problem of waveform distortion. Additionally, a novel NN-based iterative decision feedback (IDF) demodulator is also proposed to further reduce the ISI iteratively by using the previous estimated symbol information. Simulation results show that both the NN-based demodulator and the NN-based IDF demodulator can greatly outperform the traditional demodulation methods in the band-limited communication system, and the NN-based IDF demodulator achieves better performance than the normal NN-based demodulator.