Title: Ensemble deep learning approach with hybrid optimisation for enhanced underwater acoustic OFDM communication systems
Authors: S. Pradeep; Subba Reddy Borra; C.V.P.R. Prasad; N. Sreekanth; Sudhakar Kallur
Addresses: Department of CSE, Malla Reddy Engineering College for Women (UGC-Autonomous Institution), Secunderabad, Telangana, India ' Department Information Technology, Malla Reddy Engineering College for Women (UGC-Autonomous Institution), Secunderabad, Telangana, India ' Department of CSE, Malla Reddy Engineering College for Women (UGC-Autonomous Institution), Secunderabad, Telangana, India ' Department of ECE, Malla Reddy Engineering College for Women (UGC-Autonomous Institution), Secunderabad, Telangana, India ' Department of ECE, Malla Reddy Engineering College for Women (UGC-Autonomous Institution), Secunderabad, Telangana, India
Abstract: Underwater acoustic (UWA) communication involves transmitting information through sound waves in aquatic environments, which presents challenges due to signal attenuation, multi-path propagation, and background noise. This research presents a novel approach using ensemble deep learning (EDL) combined with hybrid optimisation for UWA-orthogonal-frequency-division-multiplexing (OFDM) systems. Contrary to the traditional receiver dependence on channel estimation and equalisation for symbol detection, the proposed EDL model directly retrieves transmitted symbols after sufficient training. It employs convolutional neural networks (CNNs), bi-directional long-short-term memory (bi-LSTM) networks, and recurrent neural networks (RNNs) to capture spatial, temporal, and sequence-based dependencies in the signal. To optimise the training process, a hybrid strategy, OppTalO, which integrates driving training-based optimisation (DTBO) and osprey optimisation algorithm (OOA), is utilised. The effectiveness of this EDL approach with hybrid optimisation is assessed across various system parameters: cyclic prefix length and pilot symbol count; and found to have less error rate than existing methods.
Keywords: underwater acoustic; UWA; ensemble deep learning; EDL; driving training-based optimisation; DTBO; osprey optimisation algorithm; OOA; recurrent neural network; RNN; convolutional neural network; CNN; bi-LSTM.
DOI: 10.1504/IJAHUC.2024.141963
International Journal of Ad Hoc and Ubiquitous Computing, 2024 Vol.47 No.2, pp.89 - 101
Received: 01 Aug 2023
Accepted: 19 Oct 2023
Published online: 03 Oct 2024 *