COVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy

The present work relates to the implementation of core parallel architecture in a deep learning algorithm. At present, deep learning technology forms the main interdisciplinary basis of healthcare, hospital hygiene, biological and medicine. This work establishes a baseline range by training hyperpar...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Manickam Murugappan, John Victor Joshua Thomas, Ugo Fiore, Yesudas Bevish Jinila, Subhashini Radhakrishnan
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	embarrassingly parallel hyperparameters optimization convolutional networks Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/b6606dcd6fc7439da1e766ec723a2c12
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b6606dcd6fc7439da1e766ec723a2c12
record_format	dspace
spelling	oai:doaj.org-article:b6606dcd6fc7439da1e766ec723a2c122021-11-25T17:39:35ZCOVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy10.3390/fi131102691999-5903https://doaj.org/article/b6606dcd6fc7439da1e766ec723a2c122021-10-01T00:00:00Zhttps://www.mdpi.com/1999-5903/13/11/269https://doaj.org/toc/1999-5903The present work relates to the implementation of core parallel architecture in a deep learning algorithm. At present, deep learning technology forms the main interdisciplinary basis of healthcare, hospital hygiene, biological and medicine. This work establishes a baseline range by training hyperparameter space, which could be support images, and sound with further develop a parallel architectural model using multiple inputs with and without the patient’s involvement. The chest X-ray images input could form the model architecture include variables for the number of nodes in each layer and dropout rate. Fourier transformation Mel-spectrogram images with the correct pixel range use to covert sound acceptance at the convolutional neural network in embarrassingly parallel sequences. COVIDNet the end user tool has to input a chest X-ray image and a cough audio file which could be a natural cough or a forced cough. Three binary classification models (COVID-19 CXR, non-COVID-19 CXR, COVID-19 cough) were trained. The COVID-19 CXR model classifies between healthy lungs and the COVID-19 model meanwhile the non-COVID-19 CXR model classifies between non-COVID-19 pneumonia and healthy lungs. The COVID-19 CXR model has an accuracy of 95% which was trained using 1681 COVID-19 positive images and 10,895 healthy lungs images, meanwhile, the non-COVID-19 CXR model has an accuracy of 91% which was trained using 7478 non-COVID-19 pneumonia positive images and 10,895 healthy lungs. The reason why all the models are binary classification is due to the lack of available data since medical image datasets are usually highly imbalanced and the cost of obtaining them are very pricey and time-consuming. Therefore, data augmentation was performed on the medical images datasets that were used. Effects of parallel architecture and optimization to improve on design were investigated.Manickam MurugappanJohn Victor Joshua ThomasUgo FioreYesudas Bevish JinilaSubhashini RadhakrishnanMDPI AGarticleembarrassingly parallelhyperparametersoptimizationconvolutional networksInformation technologyT58.5-58.64ENFuture Internet, Vol 13, Iss 269, p 269 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	embarrassingly parallel hyperparameters optimization convolutional networks Information technology T58.5-58.64
spellingShingle	embarrassingly parallel hyperparameters optimization convolutional networks Information technology T58.5-58.64 Manickam Murugappan John Victor Joshua Thomas Ugo Fiore Yesudas Bevish Jinila Subhashini Radhakrishnan COVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy
description	The present work relates to the implementation of core parallel architecture in a deep learning algorithm. At present, deep learning technology forms the main interdisciplinary basis of healthcare, hospital hygiene, biological and medicine. This work establishes a baseline range by training hyperparameter space, which could be support images, and sound with further develop a parallel architectural model using multiple inputs with and without the patient’s involvement. The chest X-ray images input could form the model architecture include variables for the number of nodes in each layer and dropout rate. Fourier transformation Mel-spectrogram images with the correct pixel range use to covert sound acceptance at the convolutional neural network in embarrassingly parallel sequences. COVIDNet the end user tool has to input a chest X-ray image and a cough audio file which could be a natural cough or a forced cough. Three binary classification models (COVID-19 CXR, non-COVID-19 CXR, COVID-19 cough) were trained. The COVID-19 CXR model classifies between healthy lungs and the COVID-19 model meanwhile the non-COVID-19 CXR model classifies between non-COVID-19 pneumonia and healthy lungs. The COVID-19 CXR model has an accuracy of 95% which was trained using 1681 COVID-19 positive images and 10,895 healthy lungs images, meanwhile, the non-COVID-19 CXR model has an accuracy of 91% which was trained using 7478 non-COVID-19 pneumonia positive images and 10,895 healthy lungs. The reason why all the models are binary classification is due to the lack of available data since medical image datasets are usually highly imbalanced and the cost of obtaining them are very pricey and time-consuming. Therefore, data augmentation was performed on the medical images datasets that were used. Effects of parallel architecture and optimization to improve on design were investigated.
format	article
author	Manickam Murugappan John Victor Joshua Thomas Ugo Fiore Yesudas Bevish Jinila Subhashini Radhakrishnan
author_facet	Manickam Murugappan John Victor Joshua Thomas Ugo Fiore Yesudas Bevish Jinila Subhashini Radhakrishnan
author_sort	Manickam Murugappan
title	COVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy
title_short	COVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy
title_full	COVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy
title_fullStr	COVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy
title_full_unstemmed	COVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy
title_sort	covidnet: implementing parallel architecture on sound and image for high efficacy
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b6606dcd6fc7439da1e766ec723a2c12
work_keys_str_mv	AT manickammurugappan covidnetimplementingparallelarchitectureonsoundandimageforhighefficacy AT johnvictorjoshuathomas covidnetimplementingparallelarchitectureonsoundandimageforhighefficacy AT ugofiore covidnetimplementingparallelarchitectureonsoundandimageforhighefficacy AT yesudasbevishjinila covidnetimplementingparallelarchitectureonsoundandimageforhighefficacy AT subhashiniradhakrishnan covidnetimplementingparallelarchitectureonsoundandimageforhighefficacy
_version_	1718412127382798336

COVIDNet: Implementing Parallel Architecture on Sound and Image for High Efficacy

Ejemplares similares