论文:2022,Vol:40,Issue(1):40-46
引用本文:
吴晏辰, 王英民. 面向小样本数据的水下目标识别神经网络深层化研究[J]. 西北工业大学学报
WU Yanchen, WANG Yingmin. A research on underwater target recognition neural network for small samples[J]. Northwestern polytechnical university

面向小样本数据的水下目标识别神经网络深层化研究
吴晏辰, 王英民
西北工业大学 航海学院, 陕西 西安 710072
摘要:
在面对新时期海洋工程应用领域的挑战时,可以通过利用基于深度学习的神经网络在水声工程中的实现,来达成自动化、高效性、准确性的目标。然而在面对水下目标样本匮乏、水下声环境复杂、样本信噪比差等客观问题时,深度学习也会因其自身的局限性而变得不那么灵敏。针对小样本问题,通过构建多种目标特征提取法和深层深度神经网络模型,得到了不同目标特征提取与网络模型匹配后的目标识别率与网络预测值,并通过比对实验结果,提出了通过深层神经网络深层化设计解决小样本目标识别的新思路。
关键词:    水下目标识别    深度学习    深层神经网络设计   
A research on underwater target recognition neural network for small samples
WU Yanchen, WANG Yingmin
School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
In the face of the challenges in the field of marine engineering applications in the new era, the goal of automation, high efficiency and accuracy can be achieved by using deep learning-based neural networks in hydroacoustic engineering. However, in the face of objective problems such as the lack of underwater target samples, the complex underwater sound environment, and the poor sample signal-to-noise ratio, the deep learning also becomes less sensitive due to its own limitations. In this paper, by constructing a variety of target feature extraction methods and a deep neural network model, we obtain the target recognition rate network prediction value after matched different target feature extraction with neural network model. Through comparing experimental results, a new idea of solving small sample target identification through deep neural network deep design is proposed.
Key words:    underwater target identification    deep learning    deep neural network design   
收稿日期: 2021-05-20     修回日期:
DOI: 10.1051/jnwpu/20224010040
通讯作者: 王英民(1963—),西北工业大学教授,主要从事水声工程领域研究。e-mail:ywang@nwpu.edu.cn     Email:ywang@nwpu.edu.cn
作者简介: 吴晏辰(1989—),西北工业大学博士研究生,主要从事神经网络和水下声信号研究。
相关功能
PDF(1852KB) Free
打印本文
把本文推荐给朋友
作者相关文章
吴晏辰  在本刊中的所有文章
王英民  在本刊中的所有文章

参考文献:
[1] 方尔正, 黄志浩, 桂晨阳, 等. 水面水下目标识别技术的现状与挑战[J]. 国防科技工业, 2020(7):66-68 FANG Erzheng, HUANG Zhihao, GUI Chenyang, et al. Current situation and challenges of surface and underwater target recognition technology[J]. National Defense Technology Industry, 2020(7):66-68(in Chinese)
[2] 李兰瑞, 李鹏, 刘天宇, 等. 水声信号检测与识别技术研究现状[J]. 通信技术, 2020, 53(12):2904-2907 LI Lanrui, LI Peng, LIU Tianyu, et al. Research status of underwater acoustic signal detection and recognition technology[J]. Communications Technology, 2020, 53(12):2904-2907(in Chinese)
[3] 陈阳. 水声阵列信号处理理论及实验研究[D]. 哈尔滨:哈尔滨工程大学, 2010:10-18 CHEN Yang. Theoretical and experimental study on underwater acoustic array processing[D]. Harbin:Harbin Engineering University, 2010:10-18(in Chinese)
[4] 吴姚振. 水下目标辐射噪声生理感知特征的提取方法研究[D]. 西安:西北工业大学,2014 WU Yaozhen. Studies on physiological perception feature extraction methods in underwater target-radiated noise[D]. Xi'an:Northwestern Polytechnical University, 2014(in Chinese)
[5] 吴晏辰, 王英民. 基于Gammatone频率倒谱系数的舰船辐射噪声分析[J]. 水下无人系统学报, 2021, 29(1):60-64 WU Yanchen, WANG Yingmin. Ship-radiated noise analysis based on the Gammatone frequency cepstrum coefficient[J]. Journal of Unmanned Undersea Systems, 2021, 29(1):60-64(in Chinese)
[6] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507
[7] 王强, 曾向阳. 深度学习方法及其在水下目标识别中的应用[C]//中国声学学会水声学分会2015年学术会议, 2015 WANG Qiang, ZENG Xiangyang. Deep learning methods and their applications in underwater targets recognition[C]//Proceedings of the 2015 Academic Conference of the Hydroacoustics Branch of the Acoustical Society of China, 2015(in Chinese)
[8] 程锦盛, 杜选民, 周胜增, 等. 基于目标MFCC特征的监督学习方法在被动声纳目标识别中的应用研究[J]. 舰船科学技术, 2018, 40(17):116-121 CHENG Jinsheng, DU Xuanmin, ZHOU Shengzeng, et al. Application of the MFCC feature based supervised learning method in passive sonar target recognition[J]. Ship Science and Technology, 2018, 40(17):116-121(in Chinese)
[9] 王继霞. 基于卷积神经网络的瓶状垃圾检测研究[D]. 哈尔滨:哈尔滨理工大学, 2020 WANG Jixia. Rearch on bottle waste detection based on convolution neural network[D]. Harbin:Harbin University of Science and Technology, 2020(in Chinese)
[10] 徐及, 黄兆琼, 李琛, 等. 深度学习在水下目标被动识别中的应用进展[J]. 信号处理, 2019, 35(9):1460-1475 XU Ji, HUANG Zhaoqiong, LI Chen, et al. Advances in underwater target passive recognition using deep learning[J]. Journal of Signal Processing, 2019, 35(9):1460-1475(in Chinese)
[11] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
[12] 周卓, 梁红, 杨长生, 等. 基于海豚听觉系统模型的水下目标识别[J]. 水下无人系统学报,2021, 29(2):147-152 ZHOU Zhuo, LIANG Hong, YANG Changsheng, et al. Underwater target identification based on dolphin auditory system model[J]. Journal of Unmanned Undersea Systems, 2021, 29(2):147-152(in Chinese)