Spectral Features-Based Machine Learning Approach to Detect SARS-COV-2 Infection Using Cough Sound

Azam Siddique S, Kumar S, Kumar Upadhyay P, Vakilipoor Takaloo F, Scazzoli D (2024)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2024

Journal

Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering Springer Verlag

Publisher: Springer Science and Business Media Deutschland GmbH

Book Volume: 524 LNICST

Pages Range: 88-101

Conference Proceedings Title: Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

Event location: Milan IT

ISBN: 9783031725234

DOI: 10.1007/978-3-031-72524-1_8

Abstract

In this paper, a spectral features based automated techniques for the classification of Severe Acute Respiratory Syndrome coronavirus using cough audio sound is presented. The proposed technique has following major stages: pre-processing, feature extraction, feature representation, and classifications. COUGHVID dataset is used for this study which comprises cough audio data of both Corona Virus disease 19 (COVID-19) positive and healthy subjects. Different audio features such as Mel Frequency Cepstral Coefficients and Zero Crossing Rate were extracted and represented using different methods. We found that frame-level labeling and feature representation is providing the best accuracy. The feature vector was taken as input to the classifier with 5-fold cross-validation. Support Vector Machine, Random Forest, K Nearest Neighbor, and Light Gradient Boosting Method model are tested in this paper to classify the COVID-19 positive and healthy subjects achieving an accuracy of 88.52%, 88.91%, 98.34%, and 81.95%, respectively.

Authors with CRIS profile

Fardad Vakilipoor Takaloo Lehrstuhl für Digitale Übertragung (IDC)

Involved external institutions

Politecnico di Milano IT Italy (IT) Indian Institute of Technology Indore (IITI) / भारतीय प्रौद्योगिकी संस्थान इंदौर IN India (IN)

How to cite

APA:

Azam Siddique, S., Kumar, S., Kumar Upadhyay, P., Vakilipoor Takaloo, F., & Scazzoli, D. (2024). Spectral Features-Based Machine Learning Approach to Detect SARS-COV-2 Infection Using Cough Sound. In Marouan Mizmizi, Maurizio Magarini, Prabhat Kumar Upadhyay, Massimiliano Pierobon (Eds.), Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST (pp. 88-101). Milan, IT: Springer Science and Business Media Deutschland GmbH.

MLA:

Azam Siddique, Shadab, et al. "Spectral Features-Based Machine Learning Approach to Detect SARS-COV-2 Infection Using Cough Sound." Proceedings of the 18th EAI International Conference on Body Area Networks, BODYNETS 2024, Milan Ed. Marouan Mizmizi, Maurizio Magarini, Prabhat Kumar Upadhyay, Massimiliano Pierobon, Springer Science and Business Media Deutschland GmbH, 2024. 88-101.

BibTeX: Download