Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional Network
A balanced dataset is generally beneficial to underwater acoustic target recognition. However, the imbalanced class distribution is always meted out in a real scene. To address this, a weighted cross entropy loss function based on trigonometric function is proposed. Then, the proposed loss function...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/16/4103 |
| _version_ | 1797431759892119552 |
|---|---|
| author | Yanxin Ma Mengqi Liu Yi Zhang Bingbing Zhang Ke Xu Bo Zou Zhijian Huang |
| author_facet | Yanxin Ma Mengqi Liu Yi Zhang Bingbing Zhang Ke Xu Bo Zou Zhijian Huang |
| author_sort | Yanxin Ma |
| collection | DOAJ |
| description | A balanced dataset is generally beneficial to underwater acoustic target recognition. However, the imbalanced class distribution is always meted out in a real scene. To address this, a weighted cross entropy loss function based on trigonometric function is proposed. Then, the proposed loss function is applied in a multi-scale residual convolutional neural network (named MR-CNN-A network) embedded with an attention mechanism for the recognition task. Firstly, a multi-scale convolution kernel is used to obtain multi-scale features. Then, an attention mechanism is used to fuse these multi-scale feature maps. Furthermore, a cos<i>x</i>-function-weighted cross-entropy loss function is used to deal with the class imbalance in underwater acoustic data. This function adjusts the loss ratio of each sample by adjusting the loss interval of every mini-batch based on cos<i>x</i> term to achieve a balanced total loss for each class. Two imbalanced underwater acoustic data sets, ShipsEar and autonomous underwater vehicle (self-collected data) are used to evaluate the proposed network. The experimental results show that the proposed network outperforms the support vector machine and a simple convolutional neural network. Compared with the other three loss functions, the proposed loss function achieves better stability and adaptability. The results strongly demonstrate the validity of the proposed loss function and the network. |
| first_indexed | 2024-03-09T09:49:58Z |
| format | Article |
| id | doaj.art-64c5eab6ef0d4190a9b7f6560eb06ab7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T09:49:58Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-64c5eab6ef0d4190a9b7f6560eb06ab72023-12-02T00:15:51ZengMDPI AGRemote Sensing2072-42922022-08-011416410310.3390/rs14164103Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional NetworkYanxin Ma0Mengqi Liu1Yi Zhang2Bingbing Zhang3Ke Xu4Bo Zou5Zhijian Huang6College of Meteorology and Oceanology, National University of Defense Technology, Changsha 410073, ChinaCollege of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, ChinaHunan Key Laboratory for Marine Detection Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaInstitute of Land Aviation, Beijing 101121, ChinaSchool of Computer Engineering and Applied Mathematics, Changsha University, Changsha 410073, ChinaA balanced dataset is generally beneficial to underwater acoustic target recognition. However, the imbalanced class distribution is always meted out in a real scene. To address this, a weighted cross entropy loss function based on trigonometric function is proposed. Then, the proposed loss function is applied in a multi-scale residual convolutional neural network (named MR-CNN-A network) embedded with an attention mechanism for the recognition task. Firstly, a multi-scale convolution kernel is used to obtain multi-scale features. Then, an attention mechanism is used to fuse these multi-scale feature maps. Furthermore, a cos<i>x</i>-function-weighted cross-entropy loss function is used to deal with the class imbalance in underwater acoustic data. This function adjusts the loss ratio of each sample by adjusting the loss interval of every mini-batch based on cos<i>x</i> term to achieve a balanced total loss for each class. Two imbalanced underwater acoustic data sets, ShipsEar and autonomous underwater vehicle (self-collected data) are used to evaluate the proposed network. The experimental results show that the proposed network outperforms the support vector machine and a simple convolutional neural network. Compared with the other three loss functions, the proposed loss function achieves better stability and adaptability. The results strongly demonstrate the validity of the proposed loss function and the network.https://www.mdpi.com/2072-4292/14/16/4103underwater acoustic target recognitionimbalanced datatrigonometric lossdeep learningattention mechanism |
| spellingShingle | Yanxin Ma Mengqi Liu Yi Zhang Bingbing Zhang Ke Xu Bo Zou Zhijian Huang Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional Network Remote Sensing underwater acoustic target recognition imbalanced data trigonometric loss deep learning attention mechanism |
| title | Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional Network |
| title_full | Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional Network |
| title_fullStr | Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional Network |
| title_full_unstemmed | Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional Network |
| title_short | Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional Network |
| title_sort | imbalanced underwater acoustic target recognition with trigonometric loss and attention mechanism convolutional network |
| topic | underwater acoustic target recognition imbalanced data trigonometric loss deep learning attention mechanism |
| url | https://www.mdpi.com/2072-4292/14/16/4103 |
| work_keys_str_mv | AT yanxinma imbalancedunderwateracoustictargetrecognitionwithtrigonometriclossandattentionmechanismconvolutionalnetwork AT mengqiliu imbalancedunderwateracoustictargetrecognitionwithtrigonometriclossandattentionmechanismconvolutionalnetwork AT yizhang imbalancedunderwateracoustictargetrecognitionwithtrigonometriclossandattentionmechanismconvolutionalnetwork AT bingbingzhang imbalancedunderwateracoustictargetrecognitionwithtrigonometriclossandattentionmechanismconvolutionalnetwork AT kexu imbalancedunderwateracoustictargetrecognitionwithtrigonometriclossandattentionmechanismconvolutionalnetwork AT bozou imbalancedunderwateracoustictargetrecognitionwithtrigonometriclossandattentionmechanismconvolutionalnetwork AT zhijianhuang imbalancedunderwateracoustictargetrecognitionwithtrigonometriclossandattentionmechanismconvolutionalnetwork |