A Deep Convolutional Neural Network Inspired by Auditory Perception for Underwater Acoustic Target Recognition.

Honghui Yang,Junhao Li,Guanghui Xu,Sheng Shen

doi:10.3390/s19051104

Honghui Yang, Junhao Li + Show 2 more

Open Access

https://doi.org/10.3390/s19051104

Copy DOI

Abstract

Underwater acoustic target recognition (UATR) using ship-radiated noise faces big challenges due to the complex marine environment. In this paper, inspired by neural mechanisms of auditory perception, a new end-to-end deep neural network named auditory perception inspired Deep Convolutional Neural Network (ADCNN) is proposed for UATR. In the ADCNN model, inspired by the frequency component perception neural mechanism, a bank of multi-scale deep convolution filters are designed to decompose raw time domain signal into signals with different frequency components. Inspired by the plasticity neural mechanism, the parameters of the deep convolution filters are initialized randomly, and the is n learned and optimized for UATR. The n, max-pooling layers and fully connected layers extract features from each decomposed signal. Finally, in fusion layers, features from each decomposed signal are merged and deep feature representations are extracted to classify underwater acoustic targets. The ADCNN model simulates the deep acoustic information processing structure of the auditory system. Experimental results show that the proposed model can decompose, model and classify ship-radiated noise signals efficiently. It achieves a classification accuracy of 81.96%, which is the highest in the contrast experiments. The experimental results show that auditory perception inspired deep learning method has encouraging potential to improve the classification performance of UATR.

Highlights

Underwater acoustic target recognition using ship-radiated noise faces big challenge due to the complexity of the ocean environment and the application of acoustic stealth technology.Underwater acoustic target recognition based on machine learning methods is the research emphasis in the area of underwater acoustic signal processing
Inspired by the achievements of neuroscience mentioned above, in this paper, we present an end-to-end deep neural network, named auditory perception inspired Deep Convolutional Neural Network (ADCNN), for the underwater acoustic target recognition
The classification performance of the proposed model is evaluated by receivers operating characteristic (ROC) curve, area under ROC curves (AUC) value and classification accuracy, and is compared with several different methods

Summary

Introduction

Underwater acoustic target recognition using ship-radiated noise faces big challenge due to the complexity of the ocean environment and the application of acoustic stealth technology.Underwater acoustic target recognition based on machine learning methods is the research emphasis in the area of underwater acoustic signal processing. Traditional underwater acoustic target recognition methods via ship-radiated noise use hand designed features and shallow classifiers to classify ship types. The hand designed features of ship-radiated noise include waveform features [1], spectrum features [2], wavelet features [3] and so on. The noise features or redundant features can be removed by feature selection methods [4], the inherent generalization ability problem of these features still cannot be solved radically. The shallow classifiers, such as support vector machine (SVM) [5] and shallow neural classifier [6], have weak fitting capacity and weak generalization ability while processing

Methods

Findings

Discussion

Conclusion