Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data
Detecting and classifying ships based on radiated noise provide practical guidelines for the reduction of underwater noise footprint of shipping. In this paper, the detection and classification are implemented by auditory inspired convolutional neural networks trained from raw underwater acoustic si...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-12-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/20/12/990 |
id |
doaj-69ffda82e1e3489e852bd60180a1a921 |
---|---|
record_format |
Article |
spelling |
doaj-69ffda82e1e3489e852bd60180a1a9212020-11-25T02:46:37ZengMDPI AGEntropy1099-43002018-12-01201299010.3390/e20120990e20120990Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone DataSheng Shen0Honghui Yang1Junhao Li2Guanghui Xu3Meiping Sheng4School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, ChinaDetecting and classifying ships based on radiated noise provide practical guidelines for the reduction of underwater noise footprint of shipping. In this paper, the detection and classification are implemented by auditory inspired convolutional neural networks trained from raw underwater acoustic signal. The proposed model includes three parts. The first part is performed by a multi-scale 1D time convolutional layer initialized by auditory filter banks. Signals are decomposed into frequency components by convolution operation. In the second part, the decomposed signals are converted into frequency domain by permute layer and energy pooling layer to form frequency distribution in auditory cortex. Then, 2D frequency convolutional layers are applied to discover spectro-temporal patterns, as well as preserve locality and reduce spectral variations in ship noise. In the third part, the whole model is optimized with an objective function of classification to obtain appropriate auditory filters and feature representations that are correlative with ship categories. The optimization reflects the plasticity of auditory system. Experiments on five ship types and background noise show that the proposed approach achieved an overall classification accuracy of 79.2%, which improved by 6% compared to conventional approaches. Auditory filter banks were adaptive in shape to improve accuracy of classification.https://www.mdpi.com/1099-4300/20/12/990convolutional neural networkdeep learningauditoryship radiated noisehydrophone |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sheng Shen Honghui Yang Junhao Li Guanghui Xu Meiping Sheng |
spellingShingle |
Sheng Shen Honghui Yang Junhao Li Guanghui Xu Meiping Sheng Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data Entropy convolutional neural network deep learning auditory ship radiated noise hydrophone |
author_facet |
Sheng Shen Honghui Yang Junhao Li Guanghui Xu Meiping Sheng |
author_sort |
Sheng Shen |
title |
Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data |
title_short |
Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data |
title_full |
Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data |
title_fullStr |
Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data |
title_full_unstemmed |
Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data |
title_sort |
auditory inspired convolutional neural networks for ship type classification with raw hydrophone data |
publisher |
MDPI AG |
series |
Entropy |
issn |
1099-4300 |
publishDate |
2018-12-01 |
description |
Detecting and classifying ships based on radiated noise provide practical guidelines for the reduction of underwater noise footprint of shipping. In this paper, the detection and classification are implemented by auditory inspired convolutional neural networks trained from raw underwater acoustic signal. The proposed model includes three parts. The first part is performed by a multi-scale 1D time convolutional layer initialized by auditory filter banks. Signals are decomposed into frequency components by convolution operation. In the second part, the decomposed signals are converted into frequency domain by permute layer and energy pooling layer to form frequency distribution in auditory cortex. Then, 2D frequency convolutional layers are applied to discover spectro-temporal patterns, as well as preserve locality and reduce spectral variations in ship noise. In the third part, the whole model is optimized with an objective function of classification to obtain appropriate auditory filters and feature representations that are correlative with ship categories. The optimization reflects the plasticity of auditory system. Experiments on five ship types and background noise show that the proposed approach achieved an overall classification accuracy of 79.2%, which improved by 6% compared to conventional approaches. Auditory filter banks were adaptive in shape to improve accuracy of classification. |
topic |
convolutional neural network deep learning auditory ship radiated noise hydrophone |
url |
https://www.mdpi.com/1099-4300/20/12/990 |
work_keys_str_mv |
AT shengshen auditoryinspiredconvolutionalneuralnetworksforshiptypeclassificationwithrawhydrophonedata AT honghuiyang auditoryinspiredconvolutionalneuralnetworksforshiptypeclassificationwithrawhydrophonedata AT junhaoli auditoryinspiredconvolutionalneuralnetworksforshiptypeclassificationwithrawhydrophonedata AT guanghuixu auditoryinspiredconvolutionalneuralnetworksforshiptypeclassificationwithrawhydrophonedata AT meipingsheng auditoryinspiredconvolutionalneuralnetworksforshiptypeclassificationwithrawhydrophonedata |
_version_ |
1724757053690347520 |