Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.

Bibliografske podrobnosti
Main Authors:	Ahasan, Md. Mubtasim, Fahim, Mohammad, Mazumder, Himadri, Fatema, Nur E, Rahman, Sheikh Mustafizur
Drugi avtorji:	Noor, Jannatun
Format:	Thesis
Jezik:	English
Izdano:	Brac University 2022
Teme:	Deep learning Respiratory diseases Cough sound Covid-19 Mel-Spectrogram MFCC CNN Machine learning Neural networks (Computer science) Cognitive learning theory (Deep learning)
Online dostop:	http://hdl.handle.net/10361/16780

id	10361-16780
record_format	dspace
spelling	10361-167802022-06-01T21:03:10Z Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques Ahasan, Md. Mubtasim Fahim, Mohammad Mazumder, Himadri Fatema, Nur E Rahman, Sheikh Mustafizur Noor, Jannatun Department of Computer Science and Engineering, Brac University Deep learning Respiratory diseases Cough sound Covid-19 Mel-Spectrogram MFCC CNN Machine learning Neural networks (Computer science) Cognitive learning theory (Deep learning) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 56-61). Infectious and non-infectious respiratory diseases are among the major reasons for deaths, financial and social crises around the world. However, medical personnel still find it very difficult to detect the diseases using conventional methods to combat this global crisis. We propose a respiratory disease identification method from respiratory auscultation sounds and COVID-19 infected and healthy patients from cough sound recordings. Our experiments demonstrate that artificial intelligence can be utilized as an alternative method to detect respiratory illnesses. We extract image representations of audio features such as Mel-frequency Cepstral Coefficients (MFCCs) and Mel-Spectrogram from each audio recording and use convolutional neural network models for our experiments. Also, we compare the two audio features and ten different convolutional neural network architecture’s performance on disease classification. We conduct experiments with various model training procedures’ such as transfer learning and 1cycle policy, and balanced mini-batch training. In our experiment, we classified respiratory diseases with 94.57 percent accuracy and 0.93 ROC-AUC scores and COVID-19 affected and healthy patients’ cough recordings with 85.96 percent accuracy and 0.84 ROC-AUC scores. Md. Mubtasim Ahasan Mohammad Fahim Himadri Mazumder Nur E Fatema Sheikh Mustafizur Rahman B. Computer Science 2022-06-01T05:02:39Z 2022-06-01T05:02:39Z 2022 2022-01 Thesis ID 18101195 ID 18101487 ID 18101041 ID 18101340 ID 18101610 http://hdl.handle.net/10361/16780 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 61 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Deep learning Respiratory diseases Cough sound Covid-19 Mel-Spectrogram MFCC CNN Machine learning Neural networks (Computer science) Cognitive learning theory (Deep learning)
spellingShingle	Deep learning Respiratory diseases Cough sound Covid-19 Mel-Spectrogram MFCC CNN Machine learning Neural networks (Computer science) Cognitive learning theory (Deep learning) Ahasan, Md. Mubtasim Fahim, Mohammad Mazumder, Himadri Fatema, Nur E Rahman, Sheikh Mustafizur Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.
author2	Noor, Jannatun
author_facet	Noor, Jannatun Ahasan, Md. Mubtasim Fahim, Mohammad Mazumder, Himadri Fatema, Nur E Rahman, Sheikh Mustafizur
format	Thesis
author	Ahasan, Md. Mubtasim Fahim, Mohammad Mazumder, Himadri Fatema, Nur E Rahman, Sheikh Mustafizur
author_sort	Ahasan, Md. Mubtasim
title	Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques
title_short	Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques
title_full	Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques
title_fullStr	Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques
title_full_unstemmed	Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques
title_sort	classification of respiratory diseases and covid-19 from respiratory and cough sound using deep learning techniques
publisher	Brac University
publishDate	2022
url	http://hdl.handle.net/10361/16780
work_keys_str_mv	AT ahasanmdmubtasim classificationofrespiratorydiseasesandcovid19fromrespiratoryandcoughsoundusingdeeplearningtechniques AT fahimmohammad classificationofrespiratorydiseasesandcovid19fromrespiratoryandcoughsoundusingdeeplearningtechniques AT mazumderhimadri classificationofrespiratorydiseasesandcovid19fromrespiratoryandcoughsoundusingdeeplearningtechniques AT fatemanure classificationofrespiratorydiseasesandcovid19fromrespiratoryandcoughsoundusingdeeplearningtechniques AT rahmansheikhmustafizur classificationofrespiratorydiseasesandcovid19fromrespiratoryandcoughsoundusingdeeplearningtechniques
_version_	1814307135464407040

Classification of respiratory diseases and COVID-19 from respiratory and cough sound using deep learning techniques

Podobne knjige/članki