STM: Spectrogram Transformer Model for Underwater Acoustic Target Recognition
With the evolution of machine learning and deep learning, more and more researchers have utilized these methods in the field of underwater acoustic target recognition. In these studies, convolutional neural networks (CNNs) are the main components of recognition models. In recent years, a neural netw...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/10/10/1428 |
| _version_ | 1797472358051610624 |
|---|---|
| author | Peng Li Ji Wu Yongxian Wang Qiang Lan Wenbin Xiao |
| author_facet | Peng Li Ji Wu Yongxian Wang Qiang Lan Wenbin Xiao |
| author_sort | Peng Li |
| collection | DOAJ |
| description | With the evolution of machine learning and deep learning, more and more researchers have utilized these methods in the field of underwater acoustic target recognition. In these studies, convolutional neural networks (CNNs) are the main components of recognition models. In recent years, a neural network model Transformer that uses a self-attention mechanism was proposed and achieved good performance in deep learning. In this paper, we propose a Transformer-based underwater acoustic target recognition model STM. To the best of our knowledge, this is the first work to introduce Transformer into the underwater acoustic field. We compared the performance of STM with CNN, ResNet18, and other multi-class algorithm models. Experimental results illustrate that under two commonly used dataset partitioning methods, STM achieves 97.7% and 89.9% recognition accuracy, respectively, which are 13.7% and 50% higher than the CNN Model. STM also outperforms the state-of-the-art model CRNN-9 by 3.1% and ResNet18 by 1.8%. |
| first_indexed | 2024-03-09T20:00:43Z |
| format | Article |
| id | doaj.art-2d56c77e559141d58904480dc6036407 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-09T20:00:43Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-2d56c77e559141d58904480dc60364072023-11-24T00:44:04ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-10-011010142810.3390/jmse10101428STM: Spectrogram Transformer Model for Underwater Acoustic Target RecognitionPeng Li0Ji Wu1Yongxian Wang2Qiang Lan3Wenbin Xiao4College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege 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, ChinaWith the evolution of machine learning and deep learning, more and more researchers have utilized these methods in the field of underwater acoustic target recognition. In these studies, convolutional neural networks (CNNs) are the main components of recognition models. In recent years, a neural network model Transformer that uses a self-attention mechanism was proposed and achieved good performance in deep learning. In this paper, we propose a Transformer-based underwater acoustic target recognition model STM. To the best of our knowledge, this is the first work to introduce Transformer into the underwater acoustic field. We compared the performance of STM with CNN, ResNet18, and other multi-class algorithm models. Experimental results illustrate that under two commonly used dataset partitioning methods, STM achieves 97.7% and 89.9% recognition accuracy, respectively, which are 13.7% and 50% higher than the CNN Model. STM also outperforms the state-of-the-art model CRNN-9 by 3.1% and ResNet18 by 1.8%.https://www.mdpi.com/2077-1312/10/10/1428underwater acoustic target recognitiondeep learningTransformer |
| spellingShingle | Peng Li Ji Wu Yongxian Wang Qiang Lan Wenbin Xiao STM: Spectrogram Transformer Model for Underwater Acoustic Target Recognition Journal of Marine Science and Engineering underwater acoustic target recognition deep learning Transformer |
| title | STM: Spectrogram Transformer Model for Underwater Acoustic Target Recognition |
| title_full | STM: Spectrogram Transformer Model for Underwater Acoustic Target Recognition |
| title_fullStr | STM: Spectrogram Transformer Model for Underwater Acoustic Target Recognition |
| title_full_unstemmed | STM: Spectrogram Transformer Model for Underwater Acoustic Target Recognition |
| title_short | STM: Spectrogram Transformer Model for Underwater Acoustic Target Recognition |
| title_sort | stm spectrogram transformer model for underwater acoustic target recognition |
| topic | underwater acoustic target recognition deep learning Transformer |
| url | https://www.mdpi.com/2077-1312/10/10/1428 |
| work_keys_str_mv | AT pengli stmspectrogramtransformermodelforunderwateracoustictargetrecognition AT jiwu stmspectrogramtransformermodelforunderwateracoustictargetrecognition AT yongxianwang stmspectrogramtransformermodelforunderwateracoustictargetrecognition AT qianglan stmspectrogramtransformermodelforunderwateracoustictargetrecognition AT wenbinxiao stmspectrogramtransformermodelforunderwateracoustictargetrecognition |