ACB-Assisted Deep FIR Compensation with Beluga Whale Optimization for Adaptive Wireless Communication

This is the authors' abstract. We don't add key points for this paper.

Wireless communication is an essential aspect of modern connectivity because it enables the transfer of data under various conditions. However, signal distortion due to dynamic wireless channels, which include fading, interference, and noise, is a significant threat to reliable communication. To address these issues, this paper proposes a novel Convolutional neural network-based Bidirectional Long Short-Term Memory Attention using Beluga Whale optimisation (ACB BWO) Deep FIR framework, which integrates the Convolutional layer Bi LSTM attention mechanism and BWO to effectively optimize the coefficients of the Deep FIR (Finite Impulse Response) to mitigate the distortions in the wireless communication channels. This method allows time-frequency properties of the channel to be modelled, and FIR filter coefficients are optimized to thoroughly reconstruct a signal. The experimental results show that the proposed ACB-BWO Deep FIR method performs significantly better than the baseline communication system. In particular, the proposed method achieves up to 19% improvement in the performance of the PSA and PBA and also minimizes the Bit Error Rate (BER) at different SNR levels. The proposed method decreases the distortion of the waveform by 44%. Additionally, the compensated signal is reduced by 69%, indicating enhanced signal stability and robustness. These results indicate that the ACB-BWO Deep FIR framework has the potential to be an effective solution to adaptive and reliable wireless communication under adverse channel conditions.