To Achieve Security and High Spectrum Efficiency: A New Transmission System Based on Faster-than-Nyquist and Deep Learning

Authors:
  • PSPeiyang Song
    Peiyang Song
  • NZNan Zhang
    Nan Zhang
  • FGFengkui Gong
    Fengkui Gong
  • QLQiang Li
    Qiang Li
  • HDHaiyang Ding
    Haiyang Ding

Abstract
With the rapid development of various services in wireless communications, spectrum resource has become increasingly valuable. Faster-than-Nyquist (FTN) signaling, which was proposed in the 1970s, has been a promising paradigm to improve the spectrum utilization. In this paper, we try to apply FTN into secure communications and propose a secure and high-spectrum-efficiency transmission system based on FTN and deep learning (DL). In the proposed system, the hopping symbol packing ratio with random values makes it difficult for the eavesdropper to obtain the accurate symbol rate and inter-symbol interference (ISI). While the receiver can use the blind estimation to choose the true parameters with the aid of DL. The results show that without the accurate symbol packing ratio, the eavesdropper will suffer from severe performance degradation. As a result, the system can achieve a secure transmission with a higher spectrum efficiency. Also, we propose a simplified symbol packing ratio estimation which has bee employed in our proposed system. Results show that the proposed simplified estimation achieves nearly the same performance as the original structure while its complexity has been greatly reduced.