东南大学学报（英文版）2016，Vol.32Issue(1)：6-10,5.DOI:10.3969/j.issn.1003-7985.2016.01.002
基于 CNN 解调器的超奈奎斯特速率通信
Faster-than-Nyquist rate communication via convolutional neural networks-based demodulators
摘要
Abstract
A demodulator based on convolutional neural networks CNNs is proposed to demodulate bipolar extended binary phase shifting keying EBPSK signals transmitted at a faster-than-Nyquist FTN rate solving the problem of severe inter symbol interference ISI caused by FTN rate signals. With the characteristics of local connectivity pooling and weight sharing a six-layer CNNs structure is used to demodulate and eliminate ISI.The results show that with the symbol rate of 1.07 kBd the bandwidth of the band-pass filter BPF in a transmitter of 1 kHz and the changing number of carrier cycles in a symbol K =5 10 15 28 the overall bit error ratio BER performance of CNNs with single-symbol decision is superior to that with a double-symbol united-decision.In addition the BER performance of single-symbol decision is approximately 0.5 dB better than that of the coherent demodulator while K equals the total number of carrier circles in a symbol i.e. K=N=28.With the symbol rate of 1.07 kBd the bandwidth of BPF in a transmitter of 500 Hz and K=5 10 15 28 the overall BER performance of CNNs with double-symbol united-decision is superior to those with single-symbol decision. Moreover the double-symbol united-decision method is approximately 0.5 to 1.5 dB better than that of the coherent demodulator while K =N=28.The demodulators based on CNNs successfully solve the serious ISI problems generated during the transmission of FTN rate bipolar EBPSK signals which is beneficial for the improvement of spectrum efficiency.关键词
双极性EBPSK/卷积神经网络/超奈奎斯特速率/双码元联合判决Key words
bipolar extended binary phase shifting keying EBPSK/convolutional neural networks CNNs/faster-than-Nyquist/FTN rate double-symbol united-decision分类
信息技术与安全科学引用本文复制引用
欧阳星辰,吴乐南..基于 CNN 解调器的超奈奎斯特速率通信[J].东南大学学报（英文版）,2016,32(1):6-10,5.基金项目
The National Natural Science Foundation of China No．6504000089． （）
