An effective hybrid deep neural network for underwater acoustic target recognition

Abstract

Underwater acoustic target recognition is an important support technology for underwater information detection and signal processing. Due to the high complexity of the marine environment, it is not easy to obtain clear and reliable features from ship-radiated noise, which makes underwater acoustic target recognition difficult. We propose a new hybrid network of transformer networks and convolutional neural networks to alleviate this problem. It consists of three convolution modules and a transformer module. The convolution modules are used to learn the local features of the time-frequency map, and the features are enhanced using the residual structure and channel attention. The transformer module is used to extract the global features of the time-frequency map. The proposed network can obtain global and local features of the ship-radiated noise from the time-frequency map of the raw data, which can improve the accuracy of recognition. Experiments were conducted on DeepShip, a public benchmark dataset of ship-radiated noise, and compared with the current state-of-the-art methods. The results show that the proposed hybrid network achieves the highest recognition accuracy on the DeepShip dataset.