Energy-Efficient Design of Seabed Substrate Detection Model Leveraging CNN-SVM Architecture and Sonar Data

Abstract

This study introduces an innovative seabed substrate detection model that harnesses the complementary strengths of Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs) to analyze sonar data with a focus on energy efficiency. The model addresses the challenges of underwater sensing and imaging, including variable lighting conditions, backscattering effects, and acoustic sensor limitations, while minimizing energy consumption. By leveraging advanced machine learning techniques, the proposed model aims to enhance seabed classification accuracy, a crucial aspect for marine operations, ecological studies, and energy-intensive underwater applications.The introduced ShuffleNet-DSE architecture demonstrates significant improvements in both accuracy and stability for seabed sediment image classification, while maintaining energy-efficient performance. This robust tool offers a valuable asset for underwater exploration, research, and monitoring efforts, especially in environments where energy resources are limited.