Differential Evolution Evolved RBFNN based automated recognition of Traffic Sign Images

The neural network performances depend entirely upon the quality of learning it has obtained in the past. The conventional gradient-based approach may trap in the local minima, and it may be the cause of premature convergence. To overcome this difficulty, in this paper, a differential evolution that...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Manasa R., K. Karibasappa, Manoj Kumar Singh
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://doaj.org/article/892005ba52114c6a8a2784b37c7c5998
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:892005ba52114c6a8a2784b37c7c5998
record_format dspace
spelling oai:doaj.org-article:892005ba52114c6a8a2784b37c7c59982021-12-04T04:36:22ZDifferential Evolution Evolved RBFNN based automated recognition of Traffic Sign Images2666-720710.1016/j.rico.2021.100056https://doaj.org/article/892005ba52114c6a8a2784b37c7c59982021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666720721000333https://doaj.org/toc/2666-7207The neural network performances depend entirely upon the quality of learning it has obtained in the past. The conventional gradient-based approach may trap in the local minima, and it may be the cause of premature convergence. To overcome this difficulty, in this paper, a differential evolution that establishes optimal learning of Radial basis function neural network (RBFNN) has been proposed where different parameters of kernel function and connection weights have been evolved simultaneously. The benefits of evolutionary learning of radial basis function have been evaluated extensively against the gradient-based learning in the classification of benchmark XOR problem. The model integrates principal component analysis (PCA); evolutionary self-adaptive Radial basis function neural network and correlation difference-based decision modules. The PCA has been applied in the pre-processing stage to retrieve the core details available at the input side of the image. A self-adaptive form of radial basis function neural network is used to develop a classifier. For making the learning process more precise and faster, the adjustment parameters considered. One-to-one mapping is used in the learning process to obtain the correlation between input and network parameters. The high recognition efficiency and a high level of decision confidence are the benefits of the proposed hybrid model. With an increase in iteration, the learning error approaches zero value for Differential evolution Adaptive radial basis function (DEARBF). Further, this method is computationally efficient and has shown robustness against visibility limitation because of weather and the aging effect of traffic signboards, proving its applicability in practical life.Manasa R.K. KaribasappaManoj Kumar SinghElsevierarticleRadial basis functionDifferential evolutionGradient descentTraffic sign recognitionPrincipal component analysisApplied mathematics. Quantitative methodsT57-57.97ENResults in Control and Optimization, Vol 5, Iss , Pp 100056- (2021)
institution DOAJ
collection DOAJ
language EN
topic Radial basis function
Differential evolution
Gradient descent
Traffic sign recognition
Principal component analysis
Applied mathematics. Quantitative methods
T57-57.97
spellingShingle Radial basis function
Differential evolution
Gradient descent
Traffic sign recognition
Principal component analysis
Applied mathematics. Quantitative methods
T57-57.97
Manasa R.
K. Karibasappa
Manoj Kumar Singh
Differential Evolution Evolved RBFNN based automated recognition of Traffic Sign Images
description The neural network performances depend entirely upon the quality of learning it has obtained in the past. The conventional gradient-based approach may trap in the local minima, and it may be the cause of premature convergence. To overcome this difficulty, in this paper, a differential evolution that establishes optimal learning of Radial basis function neural network (RBFNN) has been proposed where different parameters of kernel function and connection weights have been evolved simultaneously. The benefits of evolutionary learning of radial basis function have been evaluated extensively against the gradient-based learning in the classification of benchmark XOR problem. The model integrates principal component analysis (PCA); evolutionary self-adaptive Radial basis function neural network and correlation difference-based decision modules. The PCA has been applied in the pre-processing stage to retrieve the core details available at the input side of the image. A self-adaptive form of radial basis function neural network is used to develop a classifier. For making the learning process more precise and faster, the adjustment parameters considered. One-to-one mapping is used in the learning process to obtain the correlation between input and network parameters. The high recognition efficiency and a high level of decision confidence are the benefits of the proposed hybrid model. With an increase in iteration, the learning error approaches zero value for Differential evolution Adaptive radial basis function (DEARBF). Further, this method is computationally efficient and has shown robustness against visibility limitation because of weather and the aging effect of traffic signboards, proving its applicability in practical life.
format article
author Manasa R.
K. Karibasappa
Manoj Kumar Singh
author_facet Manasa R.
K. Karibasappa
Manoj Kumar Singh
author_sort Manasa R.
title Differential Evolution Evolved RBFNN based automated recognition of Traffic Sign Images
title_short Differential Evolution Evolved RBFNN based automated recognition of Traffic Sign Images
title_full Differential Evolution Evolved RBFNN based automated recognition of Traffic Sign Images
title_fullStr Differential Evolution Evolved RBFNN based automated recognition of Traffic Sign Images
title_full_unstemmed Differential Evolution Evolved RBFNN based automated recognition of Traffic Sign Images
title_sort differential evolution evolved rbfnn based automated recognition of traffic sign images
publisher Elsevier
publishDate 2021
url https://doaj.org/article/892005ba52114c6a8a2784b37c7c5998
work_keys_str_mv AT manasar differentialevolutionevolvedrbfnnbasedautomatedrecognitionoftrafficsignimages
AT kkaribasappa differentialevolutionevolvedrbfnnbasedautomatedrecognitionoftrafficsignimages
AT manojkumarsingh differentialevolutionevolvedrbfnnbasedautomatedrecognitionoftrafficsignimages
_version_ 1718372924991209472