Underwater Acoustic Target Recognition Based on Deep Residual Attention Convolutional Neural Network

Abstract

Underwater acoustic target recognition methods based on time-frequency analysis have shortcomings, such as missing information on target characteristics and having a large computation volume, which leads to difficulties in improving the accuracy and immediacy of the target recognition system. In this paper, an underwater acoustic target recognition model based on a deep residual attention convolutional neural network called DRACNN is proposed, whose input is the time-domain signal of the underwater acoustic targets radiated noise. In this model, convolutional blocks with attention to the mechanisms are used to focus on and extract deep features of the target, and residual networks are used to improve the stability of the network training. On the full ShipsEar dataset, the recognition accuracy of the DRACNN model is 97.1%, which is 2.2% higher than the resnet-18 model with an approximately equal number of parameters as this model. With similar recognition accuracies, the DRACNN model parameters are 1/36th and 1/10th of the AResNet model and UTAR-Transformer model, respectively, and the floating-point operations are 1/292nd and 1/46th of the two models, respectively. Finally, the DRACNN model pre-trained on the ShipsEar dataset was migrated to the DeepShip dataset and achieved recognition accuracy of 89.2%. The experimental results illustrate that the DRACNN model has excellent generalization ability and is suitable for a micro-UATR system.