Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test

The purpose of this study was to classify ULTT videos through transfer learning with pre-trained deep learning models and compare the performance of the models. We conducted transfer learning by combining a pre-trained convolution neural network (CNN) model into a Python-produced deep learning proce...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wansuk Choi, Seoyoon Heo
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep structured learning supervised machine learning automated feature extraction Brachial Plexus Tension Tests rehabilitation medicine human action recognition Medicine R
Acceso en línea:	https://doaj.org/article/57e00cfad483443f915587d71e3a9398
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:57e00cfad483443f915587d71e3a9398
record_format	dspace
spelling	oai:doaj.org-article:57e00cfad483443f915587d71e3a93982021-11-25T17:46:35ZDeep Learning Approaches to Automated Video Classification of Upper Limb Tension Test10.3390/healthcare91115792227-9032https://doaj.org/article/57e00cfad483443f915587d71e3a93982021-11-01T00:00:00Zhttps://www.mdpi.com/2227-9032/9/11/1579https://doaj.org/toc/2227-9032The purpose of this study was to classify ULTT videos through transfer learning with pre-trained deep learning models and compare the performance of the models. We conducted transfer learning by combining a pre-trained convolution neural network (CNN) model into a Python-produced deep learning process. Videos were processed on YouTube and 103,116 frames converted from video clips were analyzed. In the modeling implementation, the process of importing the required modules, performing the necessary data preprocessing for training, defining the model, compiling, model creation, and model fit were applied in sequence. Comparative models were Xception, InceptionV3, DenseNet201, NASNetMobile, DenseNet121, VGG16, VGG19, and ResNet101, and fine tuning was performed. They were trained in a high-performance computing environment, and validation and loss were measured as comparative indicators of performance. Relatively low validation loss and high validation accuracy were obtained from Xception, InceptionV3, and DenseNet201 models, which is evaluated as an excellent model compared with other models. On the other hand, from VGG16, VGG19, and ResNet101, relatively high validation loss and low validation accuracy were obtained compared with other models. There was a narrow range of difference between the validation accuracy and the validation loss of the Xception, InceptionV3, and DensNet201 models. This study suggests that training applied with transfer learning can classify ULTT videos, and that there is a difference in performance between models.Wansuk ChoiSeoyoon HeoMDPI AGarticledeep structured learningsupervised machine learningautomated feature extractionBrachial Plexus Tension Testsrehabilitation medicinehuman action recognitionMedicineRENHealthcare, Vol 9, Iss 1579, p 1579 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep structured learning supervised machine learning automated feature extraction Brachial Plexus Tension Tests rehabilitation medicine human action recognition Medicine R
spellingShingle	deep structured learning supervised machine learning automated feature extraction Brachial Plexus Tension Tests rehabilitation medicine human action recognition Medicine R Wansuk Choi Seoyoon Heo Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test
description	The purpose of this study was to classify ULTT videos through transfer learning with pre-trained deep learning models and compare the performance of the models. We conducted transfer learning by combining a pre-trained convolution neural network (CNN) model into a Python-produced deep learning process. Videos were processed on YouTube and 103,116 frames converted from video clips were analyzed. In the modeling implementation, the process of importing the required modules, performing the necessary data preprocessing for training, defining the model, compiling, model creation, and model fit were applied in sequence. Comparative models were Xception, InceptionV3, DenseNet201, NASNetMobile, DenseNet121, VGG16, VGG19, and ResNet101, and fine tuning was performed. They were trained in a high-performance computing environment, and validation and loss were measured as comparative indicators of performance. Relatively low validation loss and high validation accuracy were obtained from Xception, InceptionV3, and DenseNet201 models, which is evaluated as an excellent model compared with other models. On the other hand, from VGG16, VGG19, and ResNet101, relatively high validation loss and low validation accuracy were obtained compared with other models. There was a narrow range of difference between the validation accuracy and the validation loss of the Xception, InceptionV3, and DensNet201 models. This study suggests that training applied with transfer learning can classify ULTT videos, and that there is a difference in performance between models.
format	article
author	Wansuk Choi Seoyoon Heo
author_facet	Wansuk Choi Seoyoon Heo
author_sort	Wansuk Choi
title	Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test
title_short	Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test
title_full	Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test
title_fullStr	Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test
title_full_unstemmed	Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test
title_sort	deep learning approaches to automated video classification of upper limb tension test
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/57e00cfad483443f915587d71e3a9398
work_keys_str_mv	AT wansukchoi deeplearningapproachestoautomatedvideoclassificationofupperlimbtensiontest AT seoyoonheo deeplearningapproachestoautomatedvideoclassificationofupperlimbtensiontest
_version_	1718412043190534144

Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test

Ejemplares similares