Underwater Noise Modeling and Its Application in Noise Classification with Small-Sized Samples
Underwater noise classification is of great significance for identifying ships as well as other vehicles. Moreover, it is helpful in ensuring a marine habitat-friendly, noise-free ocean environment. But a challenge we are facing is the small-sized underwater noise samples. Because noise is influence...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/12/2669 |
| _version_ | 1797595101824811008 |
|---|---|
| author | Guoli Song Xinyi Guo Qianchu Zhang Jun Li Li Ma |
| author_facet | Guoli Song Xinyi Guo Qianchu Zhang Jun Li Li Ma |
| author_sort | Guoli Song |
| collection | DOAJ |
| description | Underwater noise classification is of great significance for identifying ships as well as other vehicles. Moreover, it is helpful in ensuring a marine habitat-friendly, noise-free ocean environment. But a challenge we are facing is the small-sized underwater noise samples. Because noise is influenced by multiple sources, it is often difficult to determine and label which source or which two sources are dominant. At present, research to solve the problem is focused on noise image processing or advanced computer technology without starting with the noise generation mechanism and modeling. Here, a typical underwater noise generation model (UNGM) is established to augment noise samples. It is established by generating noise with certain kurtosis according to the spectral and statistical characteristics of the actual noise and filter design. In addition, an underwater noise classification model is developed based on UNGM and convolutional neural networks (CNN). Then the UNGM-CNN-based model is used to classify nine types of typical underwater noise, with either the 1/3 octave noise spectrum level (NSL) or power spectral density (PSD) as the input features. The results show that it is effective in improving classification accuracy. Specifically, it increases the classification accuracy by 1.59%, from 98.27% to 99.86%, and by 2.44%, from 97.45% to 99.89%, when the NSL and PSD are used as the input features, respectively. Additionally, the UNGM-CNN-based method appreciably improves macro-precision and macro-recall by approximately 0.87% and 0.83%, respectively, compared to the CNN-based method. These results demonstrate the effectiveness of the UNGM established in noise classification with small-sized samples. |
| first_indexed | 2024-03-11T02:32:42Z |
| format | Article |
| id | doaj.art-6b6ef459ef8e4dbb84fdb0f9daa16b13 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T02:32:42Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-6b6ef459ef8e4dbb84fdb0f9daa16b132023-11-18T10:08:58ZengMDPI AGElectronics2079-92922023-06-011212266910.3390/electronics12122669Underwater Noise Modeling and Its Application in Noise Classification with Small-Sized SamplesGuoli Song0Xinyi Guo1Qianchu Zhang2Jun Li3Li Ma4Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaUnderwater noise classification is of great significance for identifying ships as well as other vehicles. Moreover, it is helpful in ensuring a marine habitat-friendly, noise-free ocean environment. But a challenge we are facing is the small-sized underwater noise samples. Because noise is influenced by multiple sources, it is often difficult to determine and label which source or which two sources are dominant. At present, research to solve the problem is focused on noise image processing or advanced computer technology without starting with the noise generation mechanism and modeling. Here, a typical underwater noise generation model (UNGM) is established to augment noise samples. It is established by generating noise with certain kurtosis according to the spectral and statistical characteristics of the actual noise and filter design. In addition, an underwater noise classification model is developed based on UNGM and convolutional neural networks (CNN). Then the UNGM-CNN-based model is used to classify nine types of typical underwater noise, with either the 1/3 octave noise spectrum level (NSL) or power spectral density (PSD) as the input features. The results show that it is effective in improving classification accuracy. Specifically, it increases the classification accuracy by 1.59%, from 98.27% to 99.86%, and by 2.44%, from 97.45% to 99.89%, when the NSL and PSD are used as the input features, respectively. Additionally, the UNGM-CNN-based method appreciably improves macro-precision and macro-recall by approximately 0.87% and 0.83%, respectively, compared to the CNN-based method. These results demonstrate the effectiveness of the UNGM established in noise classification with small-sized samples.https://www.mdpi.com/2079-9292/12/12/2669noise generation modelunderwater noise classificationsmall-sized samplesconvolutional neural networks |
| spellingShingle | Guoli Song Xinyi Guo Qianchu Zhang Jun Li Li Ma Underwater Noise Modeling and Its Application in Noise Classification with Small-Sized Samples Electronics noise generation model underwater noise classification small-sized samples convolutional neural networks |
| title | Underwater Noise Modeling and Its Application in Noise Classification with Small-Sized Samples |
| title_full | Underwater Noise Modeling and Its Application in Noise Classification with Small-Sized Samples |
| title_fullStr | Underwater Noise Modeling and Its Application in Noise Classification with Small-Sized Samples |
| title_full_unstemmed | Underwater Noise Modeling and Its Application in Noise Classification with Small-Sized Samples |
| title_short | Underwater Noise Modeling and Its Application in Noise Classification with Small-Sized Samples |
| title_sort | underwater noise modeling and its application in noise classification with small sized samples |
| topic | noise generation model underwater noise classification small-sized samples convolutional neural networks |
| url | https://www.mdpi.com/2079-9292/12/12/2669 |
| work_keys_str_mv | AT guolisong underwaternoisemodelinganditsapplicationinnoiseclassificationwithsmallsizedsamples AT xinyiguo underwaternoisemodelinganditsapplicationinnoiseclassificationwithsmallsizedsamples AT qianchuzhang underwaternoisemodelinganditsapplicationinnoiseclassificationwithsmallsizedsamples AT junli underwaternoisemodelinganditsapplicationinnoiseclassificationwithsmallsizedsamples AT lima underwaternoisemodelinganditsapplicationinnoiseclassificationwithsmallsizedsamples |