Classification accuracy improvement by data preprocessing in handheld laser-induced breakdown spectroscopy

Abstract

Qualitative analysis using handheld laser-induced breakdown spectroscopy (HH-LIBS) usually suffers from spectral fluctuation.

Review of In-Situ Online LIBS Detection in the Atmospheric Environment

“…Typically, the spectral data of characteristic lines are extracted from the spectra and used as a sample set to establish a suitable classification model. Currently, the most common algorithms used in LIBS analysis are principal component analysis (PCA), [82][83][84][85] linear discriminant analysis (LDA), [86][87][88] support vector machine (SVM), [89][90][91] random forest (RF), [92][93][94] and artificial neural networks (ANN). [95][96][97][98] For the classification of pollutants, these methods work equally well.…”

Classification of uneven steel samples by laser induced breakdown spectroscopy based on a Bessel beam

“…[4][5][6][7] Laser induced breakdown spectroscopy (LIBS) is a promising element analysis method. With the characteristics of rapidity, easy sample pretreatment, and in situ and real-time analysis, [8][9][10][11] LIBS has been widely used in the eld of qualitative and quantitative analysis of steel samples. [12][13][14] LIBS detects the spectra of plasmas generated by excitation of a pulsed laser focused on the surface of a sample.…”

Automatic rock classification of LIBS combined with 1DCNN based on an improved Bayesian optimization

“…This emits a spectrum during the process of plasma diffusion and cooling, allowing the collection of spectral data with a spectrometer, and then conducting a qualitative analysis of the material tested, based on the wavelength and intensity of the spectral peaks seen. [6][7][8] This approach has the advantage of multi-form analysis and is fast in operation. Further, the approach is non-destructive, shows a low detection limit, with there being no need to use vacuum environment.…”