Development of a non-invasive Covid-19 detection framework using explainable AI and data augmentation1

Author:

Shamma Aashitha L.1,Vekkot Susmitha2,Gupta Deepa1,Zakariah Mohammed3,Alotaibi Yousef Ajami3

Affiliation:

1. Department of Computer Science & Engineering, Amrita School of Computing, Bengaluru, Amrita Vishwa Vidyapeetham,India

2. Department of Electronics & Communication Engineering, Amrita School of Engineering, Bengaluru, Amrita Vishwa Vidyapeetham, India

3. Department of Computer Engineering, College of Computer and Information Sciences,King Saud University, Riyadh, Saudi Arabia

Abstract

 This paper investigates the potential of COVID-19 detection using cough, breathing, and voice patterns. Speech-based features, such as MFCC, zero crossing rate, spectral centroid, spectral bandwidth, and chroma STFT are extracted from audio recordings and evaluated for their effectiveness in identifying COVID-19 cases from Coswara dataset. The explainable AI SHAP tool is employed which identified MFCC, zero crossing rate, and spectral bandwidth as the most influential features. Data augmentation techniques like random sampling, SMOTE, Tomek, and Edited Nearest Neighbours (ENN), are applied to improve the performance of various machine learning models used viz. Naive Bayes, K-nearest neighbours, support vector machines, XGBoost, and Random Forest. Selecting the top 20 features achieves an accuracy of 73%, a precision of 74%, a recall of 94%, and an F1-score of 83% using the Random Forest model with the Tomek sampling technique. These findings demonstrate that a carefully selected subset of features can achieve comparable performance to the entire feature set while maintaining a high recall rate. The success of the Tomek undersampling technique highlights the ability of model to handle sparse clinical data and predict COVID-19 and associated diseases using speech-based features.

Publisher

IOS Press

Reference32 articles.

1. Weekly epidemiological update on COVID-19, World Health Organisation (WHO)-Edition 139, ,Accessed on 20 April 2023.

2. Learning from imbalanced data: open challenges and future directions;Krawczyk;Progress in Artificial Intelligence,2016

3. SMOTE for high-dimensional class-imbalanced data;Blagus;BMC Bioinformatics,2013

4. Risk-sensitive loss functions for sparse multi-category classification problems;Suresh;Information Sciences,2008

5. Evaluation of neural networks and data mining methods on a credit assessment task for class imbalance problem;Huang;Nonlinear Analysis: Real World Applications,2006

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Development of a diacritic-aware large vocabulary automatic speech recognition for Hausa language;International Journal of Speech Technology;2024-07-20

2. Summarizing News: Unleashing the Power of BART, GPT-2, T5, and Pegasus Models in Text Summarization;2023 4th International Conference on Intelligent Technologies (CONIT);2024-06-21

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3