Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning
Underwater acoustic homing weapons (UAHWs) are formidable underwater weapons with the capability to detect, identify, and rapidly engage targets. Swift and precise target identification is crucial for the successful engagement of targets via UAHWs. This study presents a real-time target recognition...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/12/2305 |
| _version_ | 1827574493816553472 |
|---|---|
| author | Jianjing Deng Xiangfeng Yang Liwen Liu Lei Shi Yongsheng Li Yunchuan Yang |
| author_facet | Jianjing Deng Xiangfeng Yang Liwen Liu Lei Shi Yongsheng Li Yunchuan Yang |
| author_sort | Jianjing Deng |
| collection | DOAJ |
| description | Underwater acoustic homing weapons (UAHWs) are formidable underwater weapons with the capability to detect, identify, and rapidly engage targets. Swift and precise target identification is crucial for the successful engagement of targets via UAHWs. This study presents a real-time target recognition method for UAHWs based on stacking ensemble technology. UAHWs emit active broadband detection signals that manifest distinct reflection characteristics on the target. Consequently, we have extracted energy and spatial distribution features from the target’s broadband correlation detection output. To address the problem of imbalanced original sea trial data, we employed the SMOTE algorithm to generate a relatively balanced dataset. Then, we established a stacking ensemble model and performed training and testing on both the original dataset and relatively balanced dataset separately. In conclusion, we deployed the stacking ensemble model on an embedded system. The proposed method was validated using real underwater acoustic homing weapon sea trial data. The experiment utilized 5-fold cross-validation. The results indicate that the method presented in this study achieved an average accuracy of 93.3%, surpassing that of individual classifiers. The model’s single-cycle inference time was 15 ms, meeting real-time requirements. |
| first_indexed | 2024-03-08T20:38:00Z |
| format | Article |
| id | doaj.art-7f8246c8267d4d2fa5905b3b3b3f20b9 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-08T20:38:00Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-7f8246c8267d4d2fa5905b3b3b3f20b92023-12-22T14:18:52ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-12-011112230510.3390/jmse11122305Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble LearningJianjing Deng0Xiangfeng Yang1Liwen Liu2Lei Shi3Yongsheng Li4Yunchuan Yang5Xi’an Institute of Precision Mechanics, Xi’an 710076, ChinaXi’an Institute of Precision Mechanics, Xi’an 710076, ChinaXi’an Institute of Precision Mechanics, Xi’an 710076, ChinaXi’an Institute of Precision Mechanics, Xi’an 710076, ChinaXi’an Institute of Precision Mechanics, Xi’an 710076, ChinaXi’an Institute of Precision Mechanics, Xi’an 710076, ChinaUnderwater acoustic homing weapons (UAHWs) are formidable underwater weapons with the capability to detect, identify, and rapidly engage targets. Swift and precise target identification is crucial for the successful engagement of targets via UAHWs. This study presents a real-time target recognition method for UAHWs based on stacking ensemble technology. UAHWs emit active broadband detection signals that manifest distinct reflection characteristics on the target. Consequently, we have extracted energy and spatial distribution features from the target’s broadband correlation detection output. To address the problem of imbalanced original sea trial data, we employed the SMOTE algorithm to generate a relatively balanced dataset. Then, we established a stacking ensemble model and performed training and testing on both the original dataset and relatively balanced dataset separately. In conclusion, we deployed the stacking ensemble model on an embedded system. The proposed method was validated using real underwater acoustic homing weapon sea trial data. The experiment utilized 5-fold cross-validation. The results indicate that the method presented in this study achieved an average accuracy of 93.3%, surpassing that of individual classifiers. The model’s single-cycle inference time was 15 ms, meeting real-time requirements.https://www.mdpi.com/2077-1312/11/12/2305SMOTEstacking ensemble learningimbalanced datasetunderwater acoustic homing weapontarget recognition |
| spellingShingle | Jianjing Deng Xiangfeng Yang Liwen Liu Lei Shi Yongsheng Li Yunchuan Yang Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning Journal of Marine Science and Engineering SMOTE stacking ensemble learning imbalanced dataset underwater acoustic homing weapon target recognition |
| title | Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning |
| title_full | Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning |
| title_fullStr | Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning |
| title_full_unstemmed | Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning |
| title_short | Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning |
| title_sort | real time underwater acoustic homing weapon target recognition based on a stacking technique of ensemble learning |
| topic | SMOTE stacking ensemble learning imbalanced dataset underwater acoustic homing weapon target recognition |
| url | https://www.mdpi.com/2077-1312/11/12/2305 |
| work_keys_str_mv | AT jianjingdeng realtimeunderwateracoustichomingweapontargetrecognitionbasedonastackingtechniqueofensemblelearning AT xiangfengyang realtimeunderwateracoustichomingweapontargetrecognitionbasedonastackingtechniqueofensemblelearning AT liwenliu realtimeunderwateracoustichomingweapontargetrecognitionbasedonastackingtechniqueofensemblelearning AT leishi realtimeunderwateracoustichomingweapontargetrecognitionbasedonastackingtechniqueofensemblelearning AT yongshengli realtimeunderwateracoustichomingweapontargetrecognitionbasedonastackingtechniqueofensemblelearning AT yunchuanyang realtimeunderwateracoustichomingweapontargetrecognitionbasedonastackingtechniqueofensemblelearning |