Underwater Acoustic Target Recognition via Combining Adaptive Line Enhancement and Deep Neural Network

Intelligent recognition of underwater acoustic targets is a crucial component of the intelligentization of underwater acoustic devices [1]–[3]. In recent years, with the development of computing technology, deep learning has become increasingly attractive in the recognition of underwater acoustic targets. Compared to traditional machine learning techniques, deep learning utilizes the strong nonlinearmodeling capability of deep neural networks, which enables the discovery of complex patterns hidden in large datasets and produces high-quality predictions or classification results [4], [5]. However, the complex acoustic channels, interference, and noise in the ocean often lead to the degradation or masking of some features of underwater acoustic signals, reducing the differentiation of signal characteristics between different types of targets. This, in turn, affects the capability of employed neural networks to extract features and classify underwater acoustic signals. Currently, the existing deep learning-based recognition methods of underwater targets are heavily influenced by noise and interference.