Rapid Classification of Respiratory Syncytial Virus and Sendai Virus by a Low-cost and Portable Near-infrared Spectrometer

Weiran Song, Hui Wang, Enayetur Rahman, Judit Barabas, Jiandong Huang, Ultan F. Power, Hugh J. Byrne, James McLaughlin, Chris Nugent, Paul Maguire

Research output: Contribution to journalConference articlepeer-review

Abstract

In this work, we present the combination of near-infrared spectroscopy and chemometrics to distinguish respiratory syncytial virus (RSV) and Sendai virus (SeV), the first study of its kind. Using a low-cost and portable spectrometer, a total of 440 virus spectra were collected over four separate sessions. The spectra were pre-processed by normalisation and baseline removal, and variable elimination was conducted based on the standard deviation. Partial least squares discrimination analysis was used to model the relationship between the spectra and the virus categories, resulting in the accuracy of 0.825 and 0.855 for validation and prediction, respectively. Since the portable spectrometer has simple operation and can provide analytical results in real time, it can be used as a viable tool for rapid, on-site and low-cost virus screening for RSV, SeV and possibly other similar viruses such as SARS-CoV-2.
Original languageEnglish
Journal2021 IEEE SENSORS
DOIs
Publication statusPublished (in print/issue) - 17 Dec 2021

Keywords

  • near-infrared spectroscopy
  • respiratory syncytial virus
  • Sendai virus
  • partial least squares discriminant analysis
  • data pre-processing
  • classification

Fingerprint

Dive into the research topics of 'Rapid Classification of Respiratory Syncytial Virus and Sendai Virus by a Low-cost and Portable Near-infrared Spectrometer'. Together they form a unique fingerprint.

Cite this