Identification and classification of coronavirus genomic signals based on linear predictive coding and machine learning methods

Amin Khodaei; Parvaneh Shams; Hadi Sharifi; Behzad Mozaffari-Tazehkand

doi:10.1016/j.bspc.2022.104192

Identification and classification of coronavirus genomic signals based on linear predictive coding and machine learning methods

Biomed Signal Process Control. 2023 Feb:80:104192. doi: 10.1016/j.bspc.2022.104192. Epub 2022 Sep 23.

Authors

Amin Khodaei¹, Parvaneh Shams², Hadi Sharifi¹, Behzad Mozaffari-Tazehkand¹

Affiliations

¹ Faculty of Electrical & Computer Engineering of University of Tabriz, 29 Bahman Blvd, Tabriz, Iran.
² Computer Engineering Department, Istanbul Aydin University, Turkey.

Abstract

Corona disease has become one of the problems and challenges of humankind over the past two years. One of the problems that existed from the first days of this epidemic was clinical symptoms similar to other infectious viruses such as colds and influenza. Therefore, diagnosis of this disease and its coping and treatment approaches is also been difficult. In this study, Attempts has been made to investigate the origin of this disease and the genetic structure of the virus leading to it. For this purpose, signal processing and linear predictive coding approaches were used which are widely used in data compression. A pattern recognition model was presented for the detection and separation of covid samples from the influenza virus case studies. This model, which was based on support vector machine classifier, was tested successfully on several datasets collected from different countries. The obtained results performed on all datasets by more than 98% accuracy. The proposed model, in addition to its good performance accuracy, can be a step forward in quantifying and digitizing medical big data information.

Keywords: Corona; DNA Sequence; Linear predictive coding; Machine learning; Signal processing; Support vector machine.