Jump to main content
Jump to site search


Variable selection with support vector machine for discriminating Cryptococcus fungus species based on ATR-FTIR spectroscopy

Abstract

Variable selection with supervised classification is currently an important tool for discriminating biological samples. In this paper, fifteen supervised classification algorithms based on support vector machine (SVM) were applied to discriminate Cryptococcus neoformans and Cryptococcus gattii fungus species using ATR-FTIR spectroscopy. These two fungus species of the Cryptococcus genus are the etiological agents of Cryptococcosis, which is an opportunistic or primary fungal infection with global distribution. This disease is potentially fatal, especially for immunocompromised patients, like those suffering from AIDS. The multivariate classification algorithms tested were based on principal component analysis (PCA), successive projections algorithm (SPA) and genetic algorithm (GA) as data reduction and variable selection method, being coupled to SVM with different kernel functions (linear, quadratic, 3rd order polynomial, radial basis function, multilayer perceptron). Some of these algorithms achieved very successful classification rates for discriminating fungi species, with accuracy, sensitivity, and specificity equal to 100% using both SPA-SVM-polynomial and GA-SVM-polynomial algorithms. These results show the potential of such techniques coupled to ATR-FTIR spectroscopy as a rapid and non-destructive tool for classifying these fungi species.

Back to tab navigation
Please wait while Download options loads

Publication details

The article was received on 17 Feb 2017, accepted on 11 Apr 2017 and first published on 12 Apr 2017


Article type: Paper
DOI: 10.1039/C7AY00428A
Citation: Anal. Methods, 2017, Accepted Manuscript
  •   Request permissions

    Variable selection with support vector machine for discriminating Cryptococcus fungus species based on ATR-FTIR spectroscopy

    C. Lelis, F. S. Costa and K. M. G. de Lima, Anal. Methods, 2017, Accepted Manuscript , DOI: 10.1039/C7AY00428A

Search articles by author