Underwater Target Recognition Based on Dynamic Ensemble of Random Forest

CAO Tao; DENG Jianjing; YUE Ling; LI Yongsheng

doi:10.11993/j.issn.2096-3920.2024-0054

Volume 32 Issue 3

Jun 2024

Turn off MathJax

Article Contents

Article Navigation > Journal of Unmanned Undersea Systems > 2024 > 32(3): 552-557

CAO Tao, DENG Jianjing, YUE Ling, LI Yongsheng. Underwater Target Recognition Based on Dynamic Ensemble of Random Forest[J]. Journal of Unmanned Undersea Systems, 2024, 32(3): 552-557. doi: 10.11993/j.issn.2096-3920.2024-0054

Citation:

CAO Tao, DENG Jianjing, YUE Ling, LI Yongsheng. Underwater Target Recognition Based on Dynamic Ensemble of Random Forest[J]. Journal of Unmanned Undersea Systems, 2024, 32(3): 552-557. doi: 10.11993/j.issn.2096-3920.2024-0054

Citation:

PDF( 1180 KB)

Underwater Target Recognition Based on Dynamic Ensemble of Random Forest

doi: 10.11993/j.issn.2096-3920.2024-0054

CAO Tao^1
,,
DENG Jianjing^{2, 3
,},
YUE Ling^{2, 3
,},
LI Yongsheng^{2, 3}

1.
Program Management Centre of Naval Armament Department, Beijing 100036, China
2.
The 705 Research Institute, China State Shipbuilding Corporation Limited, Xi’an 710077, China
3.
Science and Technology on Underwater Information and Control Laboratory, Xi’an 710077, China

Received Date: 2024-03-19
Accepted Date: 2024-05-07
Rev Recd Date: 2024-04-16

Available Online: 2024-05-23

Abstract

Abstract

Accurate recognition of the target is the key to attacking enemy for underwater acoustic homing weapon. A real-time target recognition method for underwater acoustic homing weapon was proposed based on dynamic ensemble selection technology. The statistical features of energy distribution and spatial distribution were extracted from the output of target wideband correlation detection by using the different reflection characteristics of the target irradiated by the active wideband detection waveform of the underwater acoustic homing weapon. In addition, a dynamic ensemble model based on a random forest was constructed, and it was trained and tested on the marine dataset. The simulation analysis shows that the dynamic ensemble model proposed in this paper has better recognition effects than other classification models and can be applied to target recognition by underwater acoustic homing weapon.
- underwater acoustic homing weapon,
- target recognition,
- dynamic ensemble selection,
- random forest

FullText(HTML)

References(19)

References

[1]	周德善, 李志舜, 朱邦元. 鱼雷自导技术[M]. 北京: 国防工业出版社, 2009.
[2]	蒋兴舟. 鱼雷制导设计原理[M]. 武汉: 海军工程大学, 2001.
[3]	何心怡, 高贺, 陈菁, 等. 鱼雷真假目标识别技术现状与展望[J]. 鱼雷技术, 2016, 24(1): 23-27. He Xinyi, Gao He, Chen Jing, et al. Current situation and prospect on torpedo's true/false target identification technologies[J]. Torpedo Technology, 2016, 24(1): 23-27.
[4]	王明洲, 郝重阳, 黄晓文. 基于相关法方位分析的水下主动目标尺度识别研究[J]. 西北工业大学学报, 2003, 21(3): 317-320. Wang Mingzhou, Hao Chongyang, Huang Xiaowen. On underwater target dimension recognition based on bearings analysis of signal correlation feature[J]. Journal of Northwestern Polytechnical University, 2003, 21(3): 317-320.
[5]	刘朝晖, 付战平, 王明洲. 基于方位走向法和互谱法的水中目标识别[J]. 兵工学报, 2006, 27(5): 932-935. Liu Zhaohui, Fu Zhanping, Wang Mingzhou. Underwater target identification based on the methods of bearing and cross-spectrum[J]. Acta Armamentarii, 2006, 27(5): 932-935.
[6]	石敏, 陈立纲, 蒋兴舟, 等. 具有亮点和方位延展特征的线列阵声诱饵研究[J]. 海军工程大学学报, 2005, 17(1): 58-62. Shi Min, Chen Ligang, Jiang Xingzhou, et al. On linear array acoustic bait with light spot and azimuth-range extensi on feature[J]. Journal of Naval University of Engineering, 2005, 17(1): 58-62.
[7]	樊书宏, 王英民, 岳玲, 等. 基于拖曳长线阵的水下目标模拟系统[J]. 系统仿真学报, 2012, 24(5): 1083-1087. Fan Shuhong, Wang Yingmin, Yue Ling, et al. Underwater target simulation system based on towed long line array[J]. Journal of System Simulation, 2012, 24(5): 1083-1087.
[8]	徐枫, 严冰, 王海陆, 等. 水下声自导武器垂直目标亮点高分辨算法仿真与实验研究[J]. 鱼雷技术, 2009, 17(6): 35-40. Xu Feng, Yan Bing, Wang Hailu, et al. Simulation and experimental study high-resolution method for torpedo vertical highlights[J]. Torpedo Technology, 2009, 17(6): 35-40.
[9]	Meng Q, Yang S, Piao S. The classification of underwater acoustic target signals based on wave structure and support vector machine[J]. J. Acoust. Soc. Am, 2014, 136: 2265.
[10]	Chen C, Fu J. Recognition method of underwater target radiated noise based on convolutional neural network[J]. Acoust. Technol, 2019, 38: 424.
[11]	Li C, Huang Z Q, Xu J, et al. Underwater target classification using deep learning[C]//Oceans 2018. Charleston, US: IEEE, 2018.
[12]	Lee S, Seo I, Seok J, et al. Active sonar target classification with power-normalized cepstral coefficients and convolutional neural network[J]. Appl. Sci, 2020, 10: 8450.
[13]	Kamal S, Chandran C S, Supriya M H. Passive sonar automated target classifier for shallow waters using end-to-end learnable deep convolutional LSTMs[J]. Eng. Sci. Technol. Int. J. 2021, 24: 860-871.
[14]	Feng S, Zhu X. A transformer-based deep learning network for underwater acoustic target recognition[J]. IEEE Geosci. Remote. Sens. Lett, 2022, 19: 1-5.
[15]	Deng J, Yang X, Liu L, et al. Real-time underwater acoustic homing weapon target recognition based on stacking technique of ensemble learning[J]. J. Mar. Sci. Eng, 2023, 11: 2305. doi: 10.3390/jmse11122305
[16]	King I, Yang H Q. Ensemble learning for imbalanced-commerce transaction anomaly classification[J]. Neural Information Processing, 2009, 58(63): 866-874.
[17]	Baumgartner D, Serpen G. Performance of global-local hybrid ensemble versus boosting bagging ensembles[J]. International Journal of Hybrid Intelligent Systems, 2012, 10(32): 25-37.
[18]	Azizi N, Farahn N, Ennajia A. New dynamic classifiers selection approach for handwritten recognition[C]//Proc of the 22nd International Conference on Artificial Neural Networks and Machine Learning. Berlin, Germany: Springer, 2012: 189-196.
[19]	Gao Y, Ji G, Yang Z, et al. A dynamic adaboost algorithm with adaptive changes of loss function[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2012, 42(6): 1828-1839.