Research on Feature Extraction and Recognition Method of Underwater Acoustic Target Based on Deep Convolutional Network
Peibing Wang, Yuan Peng
Abstract
Underwater acoustic target recognition technology is an important support technology for underwater acoustic information acquisition and underwater acoustic information confrontation. Its core includes target feature extraction and classification recognition. In this paper, deep convolution neural network is applied to feature extraction and classification of underwater acoustic target signal based on LOFAR spectrum. Firstly, the extraction method and preprocessing of LOFAR spectral features are introduced. Then, the applicability of deep convolution neural network in feature extraction and LOFAR spectrum of underwater acoustic target signal is briefly analyzed. Finally, the model construction and parameter optimization method of deep convolution neural network are explained in detail. Through analysis and research, this method has good applicability in the field of underwater acoustic target recognition.