Statistical classification of soft solder alloys by laser-induced breakdown spectroscopy: review of methods

Abstract

This paper reviews machine-learning methods that are nowadays the most frequently used for the supervised classification of spectral signals in laser-induced breakdown spectroscopy (LIBS). We analyze and compare various statistical classification methods, such as linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), partial least-squares discriminant analysis (PLS-DA), soft independent modeling of class analogy (SIMCA), support vector machine (SVM), naive Bayes method, probabilistic neural networks (PNN), and K-nearest neighbor (KNN) method. The theoretical considerations are supported with experiments conducted for real soft-solder-alloy spectra obtained using LIBS. We consider two decision problems: binary and multiclass classification. The former is used to distinguish overheated soft solders from their normal versions. The latter aims to assign a testing sample to a given group of materials. The measurements are obtained for several laser-energy values, projection masks, and numbers of laser shots. Using cross-validation, we evaluate the above classification methods in terms of their usefulness in solving both classification problems.

Recognition of Pharmacological Bi-Heterocyclic Compounds by Using Terahertz Time Domain Spectroscopy and Chemometrics

“…Hence, we must use a higher number of PCs than comes from the variance analysis, which will be confirmed by the experiments. A similar conclusion was given in the paper [61] for classification of spectra in laser-induced breakdown spectroscopy (LIBS), and this behavior was also experimentally justified in the work [62].…”

Feasibility study on exhaled-breath analysis by untargeted Selected-Ion Flow-Tube Mass Spectrometry in children with cystic fibrosis, asthma, and healthy controls: Comparison of data pretreatment and classification techniques

“…In the presence of outliers some nearest neighbours have to be taken into account. The appropriate number of neighbours K is usually less than 10 [36]. The number of neighbours included will influence the method performance [37,38].…”

A method derived from genetic algorithm, principal component analysis and artificial neural networks to enhance classification capability of laser-Induced breakdown spectroscopy

“…In the last two decades, various methods are applied to solve these problems 20 , such as selecting characteristic peaks or intensive spectral segments 2,21 , using Principal Component Analysis (PCA) [12][13][14][22][23][24][25][26][27] , Partial Least Squares (PLS) [3][4][5]8,21 and other chemometrics techniques 28 . Owing to the ability of extracting effective information, producing stable models and insensitive to noise, chemometrics methods are widely used in LIBS data modeling.…”