|本期目录/Table of Contents|

[1]朱兆彤,邹哲光,许肖梅*,等.基于BP神经网络的海洋声学仪器信号识别方法[J].厦门大学学报(自然科学版),2012,51(4):709.
 ZHU Zhao tong,ZOU Zhe guang,XU Xiao mei*,et al.A Marine Acoustic Instruments Signal Recognition Method Based on BP Neural Network[J].Journal of Xiamen University(Natural Science),2012,51(4):709.
点击复制

基于BP神经网络的海洋声学仪器信号识别方法(PDF)
分享到:

《厦门大学学报(自然科学版)》[ISSN:0438-0479/CN:35-1070/N]

卷:
51卷
期数:
2012年第4期
页码:
709
栏目:
研究论文
出版日期:
2012-07-15

文章信息/Info

Title:
A Marine Acoustic Instruments Signal Recognition Method Based on BP Neural Network
作者:
朱兆彤1邹哲光1许肖梅1*陶毅1吕连港2
1.厦门大学 海洋与地球学院,水声通信与海洋信息技术教育部重点实验室,福建 厦门 361005; 2.国家海洋局第一海洋研究所,山东 青岛 266061
Author(s):
ZHU Zhaotong1ZOU Zheguang1XU Xiaomei1*TAO Yi1L Liangang2
1.Key Laboratory of Underwater Acoustic Communication and Marine Information Technology, Ministry of Education,College of Ocean & Earth Sciences,Xiamen University,Xiamen 361005,China; 2.The First Institute of Oceanography,State Oceanic Administration,Qing
关键词:
海洋声学仪器BP神经网络仪器识别LevenbergMarquardt
Keywords:
marine acoustic instrumentsBP neural networkinstrument recognitionLevenbergMarquardt
分类号:
P 715.7
文献标志码:
-
摘要:
分析了几种常用海洋声学仪器信号的基本特征,提出一种基于误差反向传播(back propagation,BP)神经网络,以实现对信号特征参数进行分类、识别的方法.该方法采用短时傅里叶变换提取信号特征参数,运用LevenbergMarquardt算法训练BP神经网络.以实测海洋声学仪器信号的特征参数进行训练后,采用实测和仿真样本对BP神经网络的识别能力进行测试.实验结果表明,BP神经网络能够有效地区分不同海洋声学仪器的信号,识别准确率达到95%以上,且虚警率低于5%.该研究成果可用于识别海域中不同海洋声学仪
Abstract:
This paper analyzes the basic characteristics of several familiar marine acoustic instruments' signals,and presents a BP neural network (BPNN) based method for signal recognition and classification,which uses short time fourier transform(STFT) for characteristics extraction,and LevenbergMarquardt algorithm for BPNN training.After training with real acoustic signals,we evaluate the classification ability of BPNN with real and simulated samples.Experimental results show that BPNN is able to categorize different marine acoustic instruments efficiently,and the recognition accuracy is more than 95% while the false alarm probability is less than 5%.In general,this method can be used to identify a variety of marine acoustics instruments and detect their working status.Also,it may provide references for recognizing other marine acoustic signals.

参考文献/References:

[1]Urick R J.Principles of underwater sound[M].3rd ed.New York:McGrawHill,1983:12. [2]Chen C H,Lee J D,Lin M C.Classification of underwater signals using wavelet transforms and neural networks [J].Mathl Comput Modelling,1998,27(2):4760. [3]Boashash B,O′Shea P.A methodology for detection and classification of some underwater acoustic signals using timefrequency analysis techniques[J].IEEE Transactions on Acoustics Speech and Signal Processing,1990,38(11):18291841. [4]吴国清,李靖,李训诰,等.舰船噪声识别(IV)——模糊神经网络识别[J].声学学报,1999,24(3):275280. [5]周建平,陶春辉,吕文正,等.基于BP网络对模拟声呐信号分类[J].海洋学研究,2007,25(2):8390. [6]秦富童,岳丽华,万寿红.应用BP 神经网络的目标识别效果评估[J].计算机工程与应用,2010,46(5):148150. [7]Hagan M T,Menhaj M.Training feedforward network with the marquardt algorithm[J].IEEE Transactions on Neural Networks,1994,5(6):989993. [8]朱兆彤,邹哲光,许肖梅,等.基于LabVIEW的海洋声学仪器信号识别方法[J].声学与电子工程,2011(2):1821.

备注/Memo

备注/Memo:
收稿日期:20120110基金项目:国家自然科学基金项目(41176032);国家科技支撑计划项目(2008BAC50B02)*通信作者:xmxu@xmu.edu.cn
更新日期/Last Update: 2012-07-15