基于遗传小波神经网络的海底声学底质识别分类

熊明宽; 吴自银; 李守军; 尚继宏

doi:10.3969/j.issn.0253-4193.2014.05.010

基于遗传小波神经网络的海底声学底质识别分类

doi: 10.3969/j.issn.0253-4193.2014.05.010

国家海洋局第二海洋研究所, 浙江杭州 310012;国家海洋局海底科学重点实验室, 浙江杭州 310012

基金项目: 国家海洋公益专项（201105001）；科技基础性工作专项（2013FY112900）；国家自然科学基金（40506017）。

计量
- 文章访问数: 1498
- HTML全文浏览量: 12
- PDF下载量: 1106
- 被引次数: 0
出版历程
- 收稿日期: 2013-04-28
- 修回日期: 2013-10-16

Wavelet neural network identification and classification of sediment seabed sonar images based on genetic algorithms

Second Institute of Oceanography, State Oceanic Administration, Hangzhou 310012, China;Key Laboratory of Submarine Geosciences, State Oceanic Administration, Hangzhou 310012, China

摘要

摘要: 分割海底声纳探测图像，提取单元特征向量进行主成份分析，选取均值、标准差、对比度、相关系数、能量及同质性作为训练特征向量，构建小波神经网络。利用遗传算法优化小波神经网络的初始权值及小波参数，对砂、礁石、泥3种底质类型分别进行训练，并得到3种底质的测试精度都在90%以上，优于单独利用小波神经网络进行训练时的测试精度，克服了小波神经网络训练时易陷入局部极小的固有缺陷，表明基于遗传算法的小波神经网络可有效用于海底底质声纳图像的识别和分类。
- 遗传小波神经网络 /
- 底质分类 /
- 声纳图像 /
- 遗传算法 /
- 小波分析
Abstract: Segmenting the seafloor sonar gray image,and extracting characteristic vector unit with principal component analysis,the selection of the mean,standard deviation,contrast,correlation coefficient,energy and homogeneity is as training characteristic vector,to build wavelet neural network. Using genetic algorithm to optimize the wavelet neural network initial weights and wavelet parameters,the three of sediment types sand,rocks,mud were been training,and get three sediment test accuracy of 90% or more,far better than single wavelet neural network training test accuracy. Experiments show that wavelet neural network based on genetic algorithm can be effectively used for seabed sediment sonar image recognition and classification,and overcome that the wavelet neural network training shortcomings easy to fall into local minimum.
- genetic algorithm-wavelet neural network /
- sediment classification /
- sonar gray image /
- genetic algorithm /
- wavelet analysis

HTML全文

参考文献(24)

吴自银, 郑玉龙, 初凤友, 等.海底浅表层信息声探测技术研究现状及发展[J].地球科学进展, 2005, 20(11):1210—1217.

唐秋华, 周兴华, 丁继胜, 等.多波束反向散射强度数据处理研究[J].海洋学报, 2006, 28(2):51—55.

焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社, 1990.

韩立群.人工神经网络教程[M].北京:北京邮电大学出版社, 2006.

史峰, 王小川, 郁磊, 等.MATLAB神经网络30个案例分析[M].北京:北京航空航天大学出版社, 2010.

赵学智, 皱春华, 陈统坚, 等.小波神经网络的参数初始化研究[J].华南理工大学学报(自然科学版), 2003, 31(2):77—79.

Jiang Yougi, Li Xiao.A Method for Face Recognition Based on Wavelet Neural Network[C]//Proceedings of the Intelligent Systems(GCIS), 2010 Second WRI Global Congress on.IEEE, 2010, 3:133—136.

韩志艳, 王健, 伦淑娴.基于遗传小波神经网络的语音识别分类器设计[J].计算机科学, 2010, 37(11):243—246.

刘美容.基于遗传算法、小波与神经网络的模拟电路故障诊断方法[D].长沙:湖南大学, 2009.

Song G M, Wang H J, Jiang S Y, et al. Fault diagnosis approach of analog circuits based on genetic wavelet neural network[C]//Proceedings of the Electronic Measurement and Instruments, 2007. ICEMI'07. 8th International Conference on.IEEE, 2007:3-675—3-679.

Chen W G, Liang L M, Du L, et al. A fault diagnosis method for power transformers based on wavelet neural network and D S evidence theory[C]//International Conference on High Voltage Engineering and Application, 2008:666—671.

Bo H, Wen H T, Bo C, et al. Wavelet neural network based fault diagnosis of asynchronous motor[J]. Control and Decision Conference, 2009:3260—3263.

Hai Y Y, Guang J C, San B S, et al. Research on Fault Diagnosis in Analog Circuit Based on Wavelet-Neural Network[C]//The Sixth World Congress, 2006, 1:2659—2662.

林雪原.基于遗传小波神经网络的GPS/SINS组合导航系统算法[J].兵工自动化, 2011, 30(4):42—45.

高美静, 赵勇, 谈爱玲.基于遗传小波神经网络的多传感器信息融合技术的研究[J].仪器仪表学报, 2007, 28(11):2103—2107.

Mei J G, Jing W T, Kai L. Research on detecting method of submarine oil pipelines corrosion degree based on chaos genetic algorithm neural network[C]//Eighth ACIS International Conference, 2007, 2:464—469.

阳凡林, 刘经南, 赵建虎, 等.基于遗传算法的BP网络实现海底底质分类[J].测绘科学, 2006, 31(2):111—114.

唐秋华, 刘保华, 陈永奇, 等.结合遗传算法的LVQ神经网络在声学底质分类中的应用[J].地球物理学报, 2007, 50(1):313—319.

Holland J H.Adaptation in neural and artificial system[M].Michigan:The University of Michigan Press, 1975:12—27.

史峰, 王辉, 郁磊, 等.MATLAB智能算法30个案例分析[M].北京:北京航空航天大学出版社, 2011.

陈哲, 冯天谨.小波神经网络研究进展及展望[J].青岛海洋大学学报, 1999, 29(4):660—668.

Chen T P, Chen H. Approximation capability to functions of several variables, nonlinear functions, and operators by radial basis function neural network[J]. IEEE Trans on NN, 1995, 6(4):904—910.

Delyon B, Juditsky A, Benveniste A. Accuracy analysis for wavelet approximation[J]. IEEE Trans on NN, 1995, 6(2):332—348.

Szu H, Telfer B, Kadambe S.Neural network adaptive wavelets for signal representation and classification[J]. Opncel Engineering, 1992, 36(9):1907—1916

施引文献

资源附件(0)

访问统计