A New Cooperative Deep Learning Method For Underwater Acoustic Target Recognition

Underwater acoustic target recognition is a difficult task due to the complicated and changeable environment. In this paper, a new cooperative deep learning method is proposed to get a better result. This new method combines deep long short-term memory network (DLSTM) and deep auto-encoder neural network (DAE) together. Firstly, we pre-train a DLSTM model in a LSTM based DAE network via unsupervised learning. Then, we utilize the pre -trained DLSTM model and softmax classifier to classify ship radiated noise. Experiments based on acquired data show that the proposed method can achieve a better classification performance compared with only using DAE network and DLSTM network.