Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases

Abstract Background Heart sound measurement is crucial for analyzing and diagnosing patients with heart diseases. This study employed phonocardiogram signals as the input signal for heart disease analysis due to the accessibility of the respective method. This study referenced preprocessing techniqu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wen-Hsien Ho, Tian-Hsiang Huang, Po-Yuan Yang, Jyh-Horng Chou, Jin-Yi Qu, Po-Chih Chang, Fu-I. Chou, Jinn-Tsong Tsai
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Phonocardiogram Heart disease Robust optimization Convolutional neural network Uniform design Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/c619fe36f26449518864407d71102bcc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c619fe36f26449518864407d71102bcc
record_format	dspace
spelling	oai:doaj.org-article:c619fe36f26449518864407d71102bcc2021-11-14T12:12:58ZRobust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases10.1186/s12859-021-04032-81471-2105https://doaj.org/article/c619fe36f26449518864407d71102bcc2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12859-021-04032-8https://doaj.org/toc/1471-2105Abstract Background Heart sound measurement is crucial for analyzing and diagnosing patients with heart diseases. This study employed phonocardiogram signals as the input signal for heart disease analysis due to the accessibility of the respective method. This study referenced preprocessing techniques proposed by other researchers for the conversion of phonocardiogram signals into characteristic images composed using frequency subband. Image recognition was then conducted through the use of convolutional neural networks (CNNs), in order to classify the predicted of phonocardiogram signals as normal or abnormal. However, CNN requires the tuning of multiple hyperparameters, which entails an optimization problem for the hyperparameters in the model. To maximize CNN robustness, the uniform experiment design method and a science-based methodical experiment design were used to optimize CNN hyperparameters in this study. Results An artificial intelligence prediction model was constructed using CNN, and the uniform experiment design method was proposed to acquire hyperparameters for optimal CNN robustness. The results indicate Filters ( $${X}_{1}$$ X 1 ), Stride ( $${X}_{3}$$ X 3 ), Activation functions ( $${X}_{6}$$ X 6 ), and Dropout ( $${X}_{7}$$ X 7 ) to be significant factors considerably influencing the ability of CNN to distinguish among heart sound states. Finally, the confirmation experiment was conducted, and the hyperparameter combination for optimal model robustness was Filters ( $${X}_{1}$$ X 1 ) = 32, Kernel Size ( $${X}_{2})$$ X 2 ) = 3 × 3, Stride ( $${X}_{3}$$ X 3 ) = (1,1), Padding ( $${X}_{4})$$ X 4 ) as same, Optimizer ( $${X}_{5})$$ X 5 ) as the stochastic gradient descent, Activation functions ( $${X}_{6}$$ X 6 ) as relu, and Dropout ( $${X}_{7}$$ X 7 ) = 0.544. With this combination of parameters, the model had an average prediction accuracy rate of 0.787 and standard deviation of 0. Conclusion In this study, phonocardiogram signals were used for the early prediction of heart diseases. The science-based and methodical uniform experiment design was used for the optimization of CNN hyperparameters to construct a CNN with optimal robustness. The results revealed that the constructed model exhibited robustness and an acceptable accuracy rate. Other literature has failed to address hyperparameter optimization problems in CNN; a method is subsequently proposed for robust CNN optimization, thereby solving this problem.Wen-Hsien HoTian-Hsiang HuangPo-Yuan YangJyh-Horng ChouJin-Yi QuPo-Chih ChangFu-I. ChouJinn-Tsong TsaiBMCarticlePhonocardiogramHeart diseaseRobust optimizationConvolutional neural networkUniform designComputer applications to medicine. Medical informaticsR858-859.7Biology (General)QH301-705.5ENBMC Bioinformatics, Vol 22, Iss S5, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Phonocardiogram Heart disease Robust optimization Convolutional neural network Uniform design Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
spellingShingle	Phonocardiogram Heart disease Robust optimization Convolutional neural network Uniform design Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5 Wen-Hsien Ho Tian-Hsiang Huang Po-Yuan Yang Jyh-Horng Chou Jin-Yi Qu Po-Chih Chang Fu-I. Chou Jinn-Tsong Tsai Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases
description	Abstract Background Heart sound measurement is crucial for analyzing and diagnosing patients with heart diseases. This study employed phonocardiogram signals as the input signal for heart disease analysis due to the accessibility of the respective method. This study referenced preprocessing techniques proposed by other researchers for the conversion of phonocardiogram signals into characteristic images composed using frequency subband. Image recognition was then conducted through the use of convolutional neural networks (CNNs), in order to classify the predicted of phonocardiogram signals as normal or abnormal. However, CNN requires the tuning of multiple hyperparameters, which entails an optimization problem for the hyperparameters in the model. To maximize CNN robustness, the uniform experiment design method and a science-based methodical experiment design were used to optimize CNN hyperparameters in this study. Results An artificial intelligence prediction model was constructed using CNN, and the uniform experiment design method was proposed to acquire hyperparameters for optimal CNN robustness. The results indicate Filters ( $${X}_{1}$$ X 1 ), Stride ( $${X}_{3}$$ X 3 ), Activation functions ( $${X}_{6}$$ X 6 ), and Dropout ( $${X}_{7}$$ X 7 ) to be significant factors considerably influencing the ability of CNN to distinguish among heart sound states. Finally, the confirmation experiment was conducted, and the hyperparameter combination for optimal model robustness was Filters ( $${X}_{1}$$ X 1 ) = 32, Kernel Size ( $${X}_{2})$$ X 2 ) = 3 × 3, Stride ( $${X}_{3}$$ X 3 ) = (1,1), Padding ( $${X}_{4})$$ X 4 ) as same, Optimizer ( $${X}_{5})$$ X 5 ) as the stochastic gradient descent, Activation functions ( $${X}_{6}$$ X 6 ) as relu, and Dropout ( $${X}_{7}$$ X 7 ) = 0.544. With this combination of parameters, the model had an average prediction accuracy rate of 0.787 and standard deviation of 0. Conclusion In this study, phonocardiogram signals were used for the early prediction of heart diseases. The science-based and methodical uniform experiment design was used for the optimization of CNN hyperparameters to construct a CNN with optimal robustness. The results revealed that the constructed model exhibited robustness and an acceptable accuracy rate. Other literature has failed to address hyperparameter optimization problems in CNN; a method is subsequently proposed for robust CNN optimization, thereby solving this problem.
format	article
author	Wen-Hsien Ho Tian-Hsiang Huang Po-Yuan Yang Jyh-Horng Chou Jin-Yi Qu Po-Chih Chang Fu-I. Chou Jinn-Tsong Tsai
author_facet	Wen-Hsien Ho Tian-Hsiang Huang Po-Yuan Yang Jyh-Horng Chou Jin-Yi Qu Po-Chih Chang Fu-I. Chou Jinn-Tsong Tsai
author_sort	Wen-Hsien Ho
title	Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases
title_short	Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases
title_full	Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases
title_fullStr	Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases
title_full_unstemmed	Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases
title_sort	robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases
publisher	BMC
publishDate	2021
url	https://doaj.org/article/c619fe36f26449518864407d71102bcc
work_keys_str_mv	AT wenhsienho robustoptimizationofconvolutionalneuralnetworkswithauniformexperimentdesignmethodacaseofphonocardiogramtestinginpatientswithheartdiseases AT tianhsianghuang robustoptimizationofconvolutionalneuralnetworkswithauniformexperimentdesignmethodacaseofphonocardiogramtestinginpatientswithheartdiseases AT poyuanyang robustoptimizationofconvolutionalneuralnetworkswithauniformexperimentdesignmethodacaseofphonocardiogramtestinginpatientswithheartdiseases AT jyhhorngchou robustoptimizationofconvolutionalneuralnetworkswithauniformexperimentdesignmethodacaseofphonocardiogramtestinginpatientswithheartdiseases AT jinyiqu robustoptimizationofconvolutionalneuralnetworkswithauniformexperimentdesignmethodacaseofphonocardiogramtestinginpatientswithheartdiseases AT pochihchang robustoptimizationofconvolutionalneuralnetworkswithauniformexperimentdesignmethodacaseofphonocardiogramtestinginpatientswithheartdiseases AT fuichou robustoptimizationofconvolutionalneuralnetworkswithauniformexperimentdesignmethodacaseofphonocardiogramtestinginpatientswithheartdiseases AT jinntsongtsai robustoptimizationofconvolutionalneuralnetworkswithauniformexperimentdesignmethodacaseofphonocardiogramtestinginpatientswithheartdiseases
_version_	1718429373005037568

Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases

Ejemplares similares