Training RBF NN Using Sine-Cosine Algorithm for Sonar Target Classification

Radial basis function neural networks (RBF NNs) are one of the most useful tools in the classification of the sonar targets. Despite many abilities of RBF NNs, low accuracy in classification, entrapment in local minima, and slow convergence rate are disadvantages of these networks. In order to overc...

Full description

Saved in:
Bibliographic Details
Main Authors: Yixuan WANG, LiPing YUAN, Mohammad KHISHE, Alaveh MORIDI, Fallah MOHAMMADZADE
Format: Article
Language:English
Published: Institute of Fundamental Technological Research Polish Academy of Sciences 2020-11-01
Series:Archives of Acoustics
Subjects:
Online Access:https://acoustics.ippt.pan.pl/index.php/aa/article/view/2490
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850052614811549696
author Yixuan WANG
LiPing YUAN
Mohammad KHISHE
Alaveh MORIDI
Fallah MOHAMMADZADE
author_facet Yixuan WANG
LiPing YUAN
Mohammad KHISHE
Alaveh MORIDI
Fallah MOHAMMADZADE
author_sort Yixuan WANG
collection DOAJ
description Radial basis function neural networks (RBF NNs) are one of the most useful tools in the classification of the sonar targets. Despite many abilities of RBF NNs, low accuracy in classification, entrapment in local minima, and slow convergence rate are disadvantages of these networks. In order to overcome these issues, the sine-cosine algorithm (SCA) has been used to train RBF NNs in this work. To evaluate the designed classifier, two benchmark underwater sonar classification problems were used. Also, an experimental underwater target classification was developed to practically evaluate the merits of the RBFbased classifier in dealing with high-dimensional real world problems. In order to have a comprehensive evaluation, the classifier is compared with the gradient descent (GD), gravitational search algorithm (GSA), genetic algorithm (GA), and Kalman filter (KF) algorithms in terms of entrapment in local minima, the accuracy of the classification, and the convergence rate. The results show that the proposed classifier provides a better performance than other compared classifiers as it classifies the sonar datasets 2.72% better than the best benchmark classifier, on average.
format Article
id doaj-art-364fa040a3ad4ad0ba335ea65e2beec6
institution DOAJ
issn 0137-5075
2300-262X
language English
publishDate 2020-11-01
publisher Institute of Fundamental Technological Research Polish Academy of Sciences
record_format Article
series Archives of Acoustics
spelling doaj-art-364fa040a3ad4ad0ba335ea65e2beec62025-08-20T02:52:46ZengInstitute of Fundamental Technological Research Polish Academy of SciencesArchives of Acoustics0137-50752300-262X2020-11-0145410.24425/aoa.2020.135281Training RBF NN Using Sine-Cosine Algorithm for Sonar Target ClassificationYixuan WANG0LiPing YUAN1Mohammad KHISHE2Alaveh MORIDI3Fallah MOHAMMADZADE4Wuhan University of Technology1) Wuhan University of Technology 2) Wuhan Huaxia University of TechnologyIran University Of Science and TechnologyIran University of Science and TechnologyImam Khomeini Marine Science University of NowshahrRadial basis function neural networks (RBF NNs) are one of the most useful tools in the classification of the sonar targets. Despite many abilities of RBF NNs, low accuracy in classification, entrapment in local minima, and slow convergence rate are disadvantages of these networks. In order to overcome these issues, the sine-cosine algorithm (SCA) has been used to train RBF NNs in this work. To evaluate the designed classifier, two benchmark underwater sonar classification problems were used. Also, an experimental underwater target classification was developed to practically evaluate the merits of the RBFbased classifier in dealing with high-dimensional real world problems. In order to have a comprehensive evaluation, the classifier is compared with the gradient descent (GD), gravitational search algorithm (GSA), genetic algorithm (GA), and Kalman filter (KF) algorithms in terms of entrapment in local minima, the accuracy of the classification, and the convergence rate. The results show that the proposed classifier provides a better performance than other compared classifiers as it classifies the sonar datasets 2.72% better than the best benchmark classifier, on average.https://acoustics.ippt.pan.pl/index.php/aa/article/view/2490classifiersradial basis function neural networksine-cosine algorithmsonar
spellingShingle Yixuan WANG
LiPing YUAN
Mohammad KHISHE
Alaveh MORIDI
Fallah MOHAMMADZADE
Training RBF NN Using Sine-Cosine Algorithm for Sonar Target Classification
Archives of Acoustics
classifiers
radial basis function neural network
sine-cosine algorithm
sonar
title Training RBF NN Using Sine-Cosine Algorithm for Sonar Target Classification
title_full Training RBF NN Using Sine-Cosine Algorithm for Sonar Target Classification
title_fullStr Training RBF NN Using Sine-Cosine Algorithm for Sonar Target Classification
title_full_unstemmed Training RBF NN Using Sine-Cosine Algorithm for Sonar Target Classification
title_short Training RBF NN Using Sine-Cosine Algorithm for Sonar Target Classification
title_sort training rbf nn using sine cosine algorithm for sonar target classification
topic classifiers
radial basis function neural network
sine-cosine algorithm
sonar
url https://acoustics.ippt.pan.pl/index.php/aa/article/view/2490
work_keys_str_mv AT yixuanwang trainingrbfnnusingsinecosinealgorithmforsonartargetclassification
AT lipingyuan trainingrbfnnusingsinecosinealgorithmforsonartargetclassification
AT mohammadkhishe trainingrbfnnusingsinecosinealgorithmforsonartargetclassification
AT alavehmoridi trainingrbfnnusingsinecosinealgorithmforsonartargetclassification
AT fallahmohammadzade trainingrbfnnusingsinecosinealgorithmforsonartargetclassification