In this paper, we propose a novel integrated sensing and communication (ISAC) complex convolution neural network (CNN) CSI enhancer for 6G networks, which exploits the correlation between the sensing parameters, such as angle-of-arrival (AoA) and range, and the channel state information (CSI) to significantly improve the CSI estimation accuracy and further enhance the sensing accuracy. The ISAC complex CNN CSI enhancer uses the complex-value computation layers to form the CNN to better maintain the phase information of CSI. Furthermore, we incorporate the ISAC transform modules into the CNN enhancer to transform the CSI into the sparse angle-delay domain, which can be treated as images with prominent peaks and are suitable to be processed by CNN. Then, we further propose a novel biased FFT-based sensing scheme, where we actively add known phase bias terms to the original CSI to generate multiple estimation results using a simple FFT-based sensing method, and we finally calculate the average of all the debiased sensing results to obtain more accurate range estimates. The extensive simulation results show that the ISAC complex CNN CSI enhancer can converge within 30 training epochs. Its CSI estimation normalized mean square error (NMSE) is about 17 dB lower than the MMSE method, and the bit error rate (BER) of demodulation using the enhanced CSI approaches the perfect CSI. Finally, the range estimation MSE of the proposed biased FFT-based sensing method can approach the subspace-based method with much lower complexity.

翻译：本文针对6G网络提出一种新型集成感知与通信（ISAC）复值卷积神经网络（CNN）信道状态信息（CSI）增强器，该模型利用到达角（AoA）和距离等感知参数与CSI之间的相关性，显著提升CSI估计精度并进一步增强感知准确性。ISAC复值CNN CSI增强器采用复值计算层构建CNN，以更好地保持CSI的相位信息。此外，我们将ISAC变换模块集成至CNN增强器中，将CSI变换至稀疏角度-时延域，该域可视为具有显著峰值的图像，适合CNN处理。进一步地，我们提出一种新型基于有偏FFT的感知方案，通过主动向原始CSI添加已知相位偏置项，利用简单的FFT感知方法生成多个估计结果，最终计算所有去偏感知结果的均值以获得更精确的距离估计。大量仿真结果表明，ISAC复值CNN CSI增强器可在30个训练周期内收敛。其CSI估计归一化均方误差（NMSE）较MMSE方法降低约17 dB，且使用增强CSI解调得到的误码率（BER）接近完美CSI。最后，所提出的基于有偏FFT的感知方法在距离估计均方误差（MSE）上可接近子空间方法，同时具有更低的计算复杂度。