Title: Coati optimisation algorithm based hyperparameter tuned attention B-BiLTF model for spectrum prediction

Authors: Avani Vithalani

Addresses: Department of Electronics and Communication Engineering, Government Engineering College, Sector-28, Gandhinagar, Gujarat, India

Abstract: The burgeoning demand for spectrum in the 5G era and internet of things underscores the critical need for accurate spectrum prediction models. Existing methods grapple with challenges, particularly the inability to capture frequency band features at specific times. This research introduces the coati optimisation algorithm-based attention B-BiLTF model, addressing the pervasive issue of gradient disappearance in spectrum prediction. Combining bidirectional long short-term memory (BiLSTM) and backpropagation (BP) neural networks, the B-BiLTF algorithm achieves enhanced convergence speed and overall prediction accuracy. The attention B-BiLTF mechanism mitigates the impact of sequence length changes on performance. Leveraging the coati optimisation algorithm ensures systematic hyperparameter optimisation, outperforming existing approaches across diverse signal-to-noise ratio conditions and sequence lengths. Experimental results on RML2016.10a dataset demonstrate superior accuracy, RMSE, MAE, and Haversine distance, affirming the model's reliability and robustness modulation modes and signal to noise ratio (SNR) levels. This research contributes an efficient approach to spectrum prediction, advancing cognitive radio systems, and optimising spectrum utilisation.

Keywords: spectrum prediction; coati optimisation algorithm; attention-B-BiLTF; deep learning.

DOI: 10.1504/IJIEI.2024.140165

International Journal of Intelligent Engineering Informatics, 2024 Vol.12 No.3, pp.302 - 327

Received: 22 Jan 2024
Accepted: 21 Mar 2024
Published online: 26 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article