Dimensional reduction is a technique used to increase the accuracy of the classification model. In this study, the effect of dimensional reduction by Principle Component Analysis(PCA) and Linear Discriminant Analysis(LDA) on the classification of laser-induced breakdown spectroscopy(LIBS) data of iron-chromiumnickel alloy samples was investigated using the Support Vector Machine(SVM) method with two linear and Radial Basis kernel(RBF) functions. For PCA method, classification results for SVM method with linear and radial kernels were %100 and %98, respectively, and for LDA method, these results were %100 and %68, respectively. The results showed that the PCA method was more effective than the LDA method in this field.

Keywords: Support Vector Machine(SVM), Laser Induced Breakdown Spectroscopy(LIBS), Principle Component Analysis(PCA), Linear Discriminant Analysis(LDA), Kernel Function

Full-Text [PDF 798 kb]   (834 Downloads)