Classification of gasoline brand and origin by Raman spectroscopy and a novel R-weighted LSSVM algorithm

Abstract

Raman spectroscopy, which is a kind of non-invasive measurement technique and the precise molecule fingerprint, has been widely applied to provide information on chemical structures and physical forms, making it possible to be used for substance classification in qualitative analysis. In this paper, we try to classify Raman spectra of 128 gasoline samples which are provided by three different refineries and belong to three different brands (90#, 93#, and 97#). Since samples are partly overlapped in the principal component space, traditional classification algorithms based on principal component analysis (PCA) cannot be effective. Least squares support vector machine (LSSVM) with the whole spectral range is introduced. Moreover, a novel local weighted LSSVM algorithm is proposed to improve the classification accuracy. The weight is constructed based on correlation coefficient R and this algorithm can be denoted as R-weighted LSSVM. In this algorithm, both of Euclidean distance and correlation coefficient are considered to select neighboring samples. LDA based on PCA, LSSVM, local LSSVM and R-weighted LSSVM are compared in the classification experiment. Experimental results show that Raman spectroscopy is an effective means to classify gasoline brand and origin, and the R-weighted LSSVM algorithm gives the best classification result.