Key result
Deep-learning transceivers improve convergence and BER under impulsive noise vs existing approaches.
A novel deep learning-based transceiver design improves bit-error rate performance in non-Gaussian impulsive noise channels compared to existing methods.
Answers are grounded in this paper and cite their sources.
May support DL transceiver use in impulsive noise; leaves open real-world validation and deployment.
This paper presents a deep-learning (DL)-based transceiver design on additive non-Gaussian impulsive noise (IN) channels. At first, an impulsive generative adversarial network (IGAN) with specific regularization terms is proposed to capture the IN behaviours and used as the channel noise simulator (CNS). Subsequently, the transmitter and receiver are jointly optimized to develop both optimal transmit signal and detection. Furthermore, to enhance the detection performance, the multi-level wavelet signal recovery network (MWSRN) is applied to construct a preprocessor to combat both IN and channel fading without pilots. Illustrative simulation results show that the proposed scheme can achieve better convergence and bit-error rate (BER) performance under different IN settings than various existing approaches.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2025) studied Additive non-Gaussian impulsive noise channels. Deep-learning-based transceiver design (IGAN and MWSRN) vs. Various existing approaches was evaluated on Convergence and bit-error rate (BER) performance. A deep-learning-based transceiver design using IGAN and MWSRN achieved better convergence and bit-error rate performance under different impulsive noise settings than existing approaches.
Synapse has enriched 10 related papers. Consider them for comparative context: