← 研踪 PaperTrailarXiv:2609.12244 · v2
CRFCAN: A Complex-Valued Cross-Domain Residual Network for Joint Channel and Phase Noise Estimation in Sub-THz OFDM Systems
首次提交 2026-09-11 06:02
版本更新 2026-11-15 16:01
雷达观测 2026-11-17 19:15
摘要
The coupling between multipath propagation and phase noise (PN) poses challenges for joint channel and PN estimation in sub-terahertz (sub-THz) cyclic-prefix OFDM systems. This paper proposes CRFCAN, a complex-valued residual FFT convolutional attention network for single-input single-output systems using comb-type pilots only. Its shared backbone alternately refines time- and frequency-domain features through complex-valued residual channel attention and PN-inspired multiplicative updates, producing channel and PN estimates in their respective domains. An unfolded PN refinement tail combines least-squares updates with feature-guided complex-valued CNN corrections. Simulation results show that CRFCAN achieves lower channel estimation error and bit error rate than the evaluated baselines in both training TDL-A/B/E + 3GPP RAN4 and TDL-C/D + 3GPP RAN1 generalization settings, together with lower PN estimation error at medium-to-high signal-to-noise ratios. Further tests without fine-tuning demonstrate its applicability across different data modulations, OFDM parameters, channel models, and PN spectra.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-15 16:01 · 最新观测版本
CRFCAN: A Complex-Valued Cross-Domain Residual Network for Joint Channel and Phase Noise Estimation in Sub-THz OFDM Systems
The coupling between multipath propagation and phase noise (PN) poses challenges for joint channel and PN estimation in sub-terahertz (sub-THz) cyclic-prefix OFDM systems. This paper proposes CRFCAN, a complex-valued residual FFT convolutional attention network for single-input single-output systems using comb-type pilots only. Its shared backbone alternately refines time- and frequency-domain features through complex-valued residual channel attention and PN-inspired multiplicative updates, producing channel and PN estimates in their respective domains. An unfolded PN refinement tail combines least-squares updates with feature-guided complex-valued CNN corrections. Simulation results show that CRFCAN achieves lower channel estimation error and bit error rate than the evaluated baselines in both training TDL-A/B/E + 3GPP RAN4 and TDL-C/D + 3GPP RAN1 generalization settings, together with lower PN estimation error at medium-to-high signal-to-noise ratios. Further tests without fine-tuning demonstrate its applicability across different data modulations, OFDM parameters, channel models, and PN spectra.
查看此版本解读 →查看此版本原文 ↗