VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion Features
Underwater acoustic target recognition is a hot research area in acoustic signal processing. With the development of deep learning, feature extraction and neural network computation have become two major steps of recognition. Due to the complexity of the marine environment, traditional feature extra...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/2/263 |
| _version_ | 1827757021050437632 |
|---|---|
| author | Ji Wu Peng Li Yongxian Wang Qiang Lan Wenbin Xiao Zhenghua Wang |
| author_facet | Ji Wu Peng Li Yongxian Wang Qiang Lan Wenbin Xiao Zhenghua Wang |
| author_sort | Ji Wu |
| collection | DOAJ |
| description | Underwater acoustic target recognition is a hot research area in acoustic signal processing. With the development of deep learning, feature extraction and neural network computation have become two major steps of recognition. Due to the complexity of the marine environment, traditional feature extraction cannot express the characteristics of the targets well. In this paper, we propose an underwater acoustic target recognition approach named VFR. VFR adopts a novel feature extraction method by fusing three-dimensional FBank features, and inputs the extracted features into a residual network, instead of the classical CNN network, plus cross-domain pre-training to perform target recognition. The experimental results show that VFR achieves 98.5% recognition accuracy on the randomly divided ShipsEar dataset and 93.8% on the time-divided dataset, respectively, which are better than state-of-the-art results. |
| first_indexed | 2024-03-11T08:36:38Z |
| format | Article |
| id | doaj.art-8bc7f137e65342ca84424ec8d21f0a49 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-11T08:36:38Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-8bc7f137e65342ca84424ec8d21f0a492023-11-16T21:26:45ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-01-0111226310.3390/jmse11020263VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion FeaturesJi Wu0Peng Li1Yongxian Wang2Qiang Lan3Wenbin Xiao4Zhenghua Wang5College of Computer, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Computer, National University of Defense Technology, Changsha 410073, ChinaUnderwater acoustic target recognition is a hot research area in acoustic signal processing. With the development of deep learning, feature extraction and neural network computation have become two major steps of recognition. Due to the complexity of the marine environment, traditional feature extraction cannot express the characteristics of the targets well. In this paper, we propose an underwater acoustic target recognition approach named VFR. VFR adopts a novel feature extraction method by fusing three-dimensional FBank features, and inputs the extracted features into a residual network, instead of the classical CNN network, plus cross-domain pre-training to perform target recognition. The experimental results show that VFR achieves 98.5% recognition accuracy on the randomly divided ShipsEar dataset and 93.8% on the time-divided dataset, respectively, which are better than state-of-the-art results.https://www.mdpi.com/2077-1312/11/2/263underwater acoustic target recognitionfeature extractionresidual networkcross-domin pre-training |
| spellingShingle | Ji Wu Peng Li Yongxian Wang Qiang Lan Wenbin Xiao Zhenghua Wang VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion Features Journal of Marine Science and Engineering underwater acoustic target recognition feature extraction residual network cross-domin pre-training |
| title | VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion Features |
| title_full | VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion Features |
| title_fullStr | VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion Features |
| title_full_unstemmed | VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion Features |
| title_short | VFR: The Underwater Acoustic Target Recognition Using Cross-Domain Pre-Training with FBank Fusion Features |
| title_sort | vfr the underwater acoustic target recognition using cross domain pre training with fbank fusion features |
| topic | underwater acoustic target recognition feature extraction residual network cross-domin pre-training |
| url | https://www.mdpi.com/2077-1312/11/2/263 |
| work_keys_str_mv | AT jiwu vfrtheunderwateracoustictargetrecognitionusingcrossdomainpretrainingwithfbankfusionfeatures AT pengli vfrtheunderwateracoustictargetrecognitionusingcrossdomainpretrainingwithfbankfusionfeatures AT yongxianwang vfrtheunderwateracoustictargetrecognitionusingcrossdomainpretrainingwithfbankfusionfeatures AT qianglan vfrtheunderwateracoustictargetrecognitionusingcrossdomainpretrainingwithfbankfusionfeatures AT wenbinxiao vfrtheunderwateracoustictargetrecognitionusingcrossdomainpretrainingwithfbankfusionfeatures AT zhenghuawang vfrtheunderwateracoustictargetrecognitionusingcrossdomainpretrainingwithfbankfusionfeatures |