Hybrid Deep Learning-Based Adaptive Multiple Access Schemes Underwater Wireless Networks

Achieving sound communication systems in Under Water Acoustic (UWA) environment remains challenging for researchers. The scheme is complex since these acoustic channels exhibit uneven characteristics such as long propagation delay and irregular Doppler shifts. development of machine deep learning algorithms has reduced the burden achieving reliable good schemes underwater environment. This paper proposes a novel intelligent selection method between different modulation Code Division Multiple Access(CDMA), Time Access(TDMA), Orthogonal Frequency Multiplexing(OFDM) techniques using hybrid combination convolutional neural networks(CNN) ensemble single feedforward layers(SFL). networks are used channel feature extraction, boosted ensembled layers based on CNN outputs. extensive experimentation carried out compared with other models conventional methods. Simulation results demonstrate that performance proposed model achieved nearly 98% accuracy 30% increase BER which outperformed under dynamic environments.