基于卷积神经网络的水声目标分类技术
|
摘要
论文介绍了卷积神经网络方法以及其计算过程,然后根据卷积神经网络的特性,提出了应用于水声目标分类的深度学习算法,仿真实验了卷积神经网络方法对水声目标的识别效果,并对舰艇、海洋环境噪声以及商船渔船等目标进行识别。通过与传统水声目标分类方法做比较,验证基于卷积神经网络的深度学习方法对水声目标分类的辨识性能。
This paper introduces the convolutional neural networks method and it's computing process,with the characteristics of convolutional neural networks,the deep learning algorithm applied in underwater acoustic targets classification is raised.With the simulation experiment of convolutional neural networks method,the ships,the ambient sea noise,the merchant ships and the fishing-boat are classified. With the comparison of classic underwater acoustic targets classification methods,the identification performance of convolutional neural networks method turns out to be better.
This paper introduces the convolutional neural networks method and it's computing process,with the characteristics of convolutional neural networks,the deep learning algorithm applied in underwater acoustic targets classification is raised.With the simulation experiment of convolutional neural networks method,the ships,the ambient sea noise,the merchant ships and the fishing-boat are classified. With the comparison of classic underwater acoustic targets classification methods,the identification performance of convolutional neural networks method turns out to be better.
引文
[1]W S McCulloch,W Pitts. A logical calculus of the ideasimmanent in nervous activity[J]. The bulle. of Math.Bio.,1943,5(4):115-133.
[2]D Hebb. The Organization of Behavior:A Neuropsycholog-ical Theroy[M]. London:Psychology Press,1949,47(54):134-142.
[3]F Rosenblatt. The Peceptron:A probabilistic model for in-formation storage and organization in the Brain[J]. Psyc.Rev.,1958,65(6):386-408.
[4]M Minsky,S Papert. Perceptrons:An introduction to com-putational geometry[M]. Massachusetts:The MITPress.1969,54(43):78-83.
[5]S Grossberg. Some networks that can learn,remember,and reproduce any number of complicated space-time pat-terns[J]. Jour.of Math.and Mech.,1969,19(1):53-91.
[6]T Kohonen. Correlation matrix memories[J]. IEEE Trans.on Comp.,1972,100(4):353-359.
[7]K S Narendra,M A L Thathatchar. Learning automata-asurvey[J]. IEEE Trans. Syste.,Man,and Cybernetics,1974,(4):323-334.
[8]C von der Malsburg. Self-organization of orientation sensi-tive cells in the striate cortex[J]. Kybernetik,1973,14(1):85-100.
[9]B Widrow,M Hoff. Associative storage and retrieval ofdigital information in networks of adaptive neurons[M].Berlin:Springer,1992,56(34):57-63.
[10] G Palm. On associative memory[J]. Biol. Cybm.,1980,36(1):19-31.
[11]D J Willshaw,C von der Malsburg. How patterned neu-ral connections can be set up by self-organization[J].Proc.R.Soc.London B,1976,199(1117):431-445.
[12]J J Hopfield. Neural networks and physical systems withemergent collective computational abilities[C]//Proc.NASUSA,1982,76(24):2554-2558.
[2]D Hebb. The Organization of Behavior:A Neuropsycholog-ical Theroy[M]. London:Psychology Press,1949,47(54):134-142.
[3]F Rosenblatt. The Peceptron:A probabilistic model for in-formation storage and organization in the Brain[J]. Psyc.Rev.,1958,65(6):386-408.
[4]M Minsky,S Papert. Perceptrons:An introduction to com-putational geometry[M]. Massachusetts:The MITPress.1969,54(43):78-83.
[5]S Grossberg. Some networks that can learn,remember,and reproduce any number of complicated space-time pat-terns[J]. Jour.of Math.and Mech.,1969,19(1):53-91.
[6]T Kohonen. Correlation matrix memories[J]. IEEE Trans.on Comp.,1972,100(4):353-359.
[7]K S Narendra,M A L Thathatchar. Learning automata-asurvey[J]. IEEE Trans. Syste.,Man,and Cybernetics,1974,(4):323-334.
[8]C von der Malsburg. Self-organization of orientation sensi-tive cells in the striate cortex[J]. Kybernetik,1973,14(1):85-100.
[9]B Widrow,M Hoff. Associative storage and retrieval ofdigital information in networks of adaptive neurons[M].Berlin:Springer,1992,56(34):57-63.
[10] G Palm. On associative memory[J]. Biol. Cybm.,1980,36(1):19-31.
[11]D J Willshaw,C von der Malsburg. How patterned neu-ral connections can be set up by self-organization[J].Proc.R.Soc.London B,1976,199(1117):431-445.
[12]J J Hopfield. Neural networks and physical systems withemergent collective computational abilities[C]//Proc.NASUSA,1982,76(24):2554-2558.