Empirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification

Deep learning algorithms are employed in many applications, especially in medical fields such as gait analysis and human pose detection for rehabilitation. However, creating the desired model with deep learning algorithms requires high memory and computing costs, which is problematic because deep le...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jermphiphut Jaruenpunyasak, Rakkrit Duangsoithong
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Feature Reduction autoencoder LBP SVM foot classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/38942c5258614266a3e75b2fd9cfa712
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:38942c5258614266a3e75b2fd9cfa712
record_format	dspace
spelling	oai:doaj.org-article:38942c5258614266a3e75b2fd9cfa7122021-11-09T00:00:34ZEmpirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification2169-353610.1109/ACCESS.2021.3069625https://doaj.org/article/38942c5258614266a3e75b2fd9cfa7122021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9389726/https://doaj.org/toc/2169-3536Deep learning algorithms are employed in many applications, especially in medical fields such as gait analysis and human pose detection for rehabilitation. However, creating the desired model with deep learning algorithms requires high memory and computing costs, which is problematic because deep learning technologies must be run on low-power devices such as edge computing equipment. To deal with these problems, feature reduction methods reduce the memory and energy costs. This paper presents an empirical analysis of deep learning with feature reduction. The method classifies foot images for knee rehabilitation using convolutional and dense autoencoders. The obtained results are compared with those of conventional methods (histograms of oriented gradients and local binary pattern algorithms). The features were classified and compared using support vector machine, k-nearest neighbor, and multilayer perceptron methods. The experimental results demonstrate that the conventional method uses fewer features than the deep learning method with higher accuracy because its algorithm projects pixels onto the histogram. In addition, using fewer features in deep learning layers maintains high accuracy, which is beneficial for edge computing implementations.Jermphiphut JaruenpunyasakRakkrit DuangsoithongIEEEarticleFeature ReductionautoencoderLBPSVMfoot classificationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 53133-53145 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Feature Reduction autoencoder LBP SVM foot classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Feature Reduction autoencoder LBP SVM foot classification Electrical engineering. Electronics. Nuclear engineering TK1-9971 Jermphiphut Jaruenpunyasak Rakkrit Duangsoithong Empirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification
description	Deep learning algorithms are employed in many applications, especially in medical fields such as gait analysis and human pose detection for rehabilitation. However, creating the desired model with deep learning algorithms requires high memory and computing costs, which is problematic because deep learning technologies must be run on low-power devices such as edge computing equipment. To deal with these problems, feature reduction methods reduce the memory and energy costs. This paper presents an empirical analysis of deep learning with feature reduction. The method classifies foot images for knee rehabilitation using convolutional and dense autoencoders. The obtained results are compared with those of conventional methods (histograms of oriented gradients and local binary pattern algorithms). The features were classified and compared using support vector machine, k-nearest neighbor, and multilayer perceptron methods. The experimental results demonstrate that the conventional method uses fewer features than the deep learning method with higher accuracy because its algorithm projects pixels onto the histogram. In addition, using fewer features in deep learning layers maintains high accuracy, which is beneficial for edge computing implementations.
format	article
author	Jermphiphut Jaruenpunyasak Rakkrit Duangsoithong
author_facet	Jermphiphut Jaruenpunyasak Rakkrit Duangsoithong
author_sort	Jermphiphut Jaruenpunyasak
title	Empirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification
title_short	Empirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification
title_full	Empirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification
title_fullStr	Empirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification
title_full_unstemmed	Empirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification
title_sort	empirical analysis of feature reduction in deep learning and conventional methods for foot image classification
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/38942c5258614266a3e75b2fd9cfa712
work_keys_str_mv	AT jermphiphutjaruenpunyasak empiricalanalysisoffeaturereductionindeeplearningandconventionalmethodsforfootimageclassification AT rakkritduangsoithong empiricalanalysisoffeaturereductionindeeplearningandconventionalmethodsforfootimageclassification
_version_	1718441376249544704

Empirical Analysis of Feature Reduction in Deep Learning and Conventional Methods for Foot Image Classification

Ejemplares similares