Weighted-averaging-based classification of laser-induced breakdown spectroscopy measurements using most informative spectral lines

Abstract

In this study, efficient spectral line selection and weighted-averaging-based processing schemes are proposed for the classification of laser-induced breakdown spectroscopy (LIBS) measurements. For fast on-line classification, a set of representative spectral lines are selected and processed relying on the information metric, instead of the time consuming full spectrum based analysis. The most informative spectral line sets are investigated by the joint mutual information estimation (MIE) evaluated with the Gaussian kernel density, where dominant intensity peaks associated with the concentrated components are not necessarily most valuable for classification. In order to further distinguish the characteristic patterns of the LIBS measured spectrum, two-dimensional spectral images are synthesized through column-wise concatenation of the peaks along with their neighbors. For fast classification while preserving the effect of distinctive peak patterns, column-wise Gaussian weighted averaging is applied to the synthesized images, yielding a favorable trade-off between classification performance and computational complexity. To explore the applicability of the proposed schemes, two applications of alloy classification and skin cancer detection are investigated with the multi-class and binary support vector machines classifiers, respectively. The MIE measures associated with selected spectral lines in both applications show a strong correlation to the actual classification or detection accuracy, which enables to find out meaningful combinations of spectral lines. In addition, the peak patterns of the selected lines and their Gaussian weighted averaging with neighbors of the selected peaks efficiently distinguish different classes of LIBS measured spectrum.

A Review on Laser-Induced Breakdown Spectroscopy in Different Cancers Diagnosis and Classification

“…They concluded that dermis and skin cancer fields are distinguished and compatible in the LIBS elemental mapping picture with the histologically calculated ones, showing the viability of LIBS as a beneficial tool for quicker decision Regions of Skin Cancer. To improve the classification accuracy of normal and melanoma samples, Ekta et al [52] used the Joint Mutual Information Estimation (MIE) and Weighted Average (WA) methods. To test and pick representative spectral lines, the MIE procedure was used, while column-wise Gaussian weighted lines based on the chosen feature lines and surrounding spectral lines, averaging was used to process two-dimensional spectral images.…”

Adversarial Data Augmentation and Transfer Net for Scrap Metal Identification Using Laser-Induced Breakdown Spectroscopy Measurement of Standard Reference Materials

“…S5 in the Supplementary Material also illustrates the spectral lines corresponding to each of the metal types as distinguishing features. Mutual information 8 was also estimated empirically to distinguish Al and Cu samples using the two dominant lines: Al I 324.73 nm and Cu I 396.22 nm. A score of 0.8538 was obtained for the original SRM dataset, which improved to 0.8556 with a preprocessing scheme (BR and RMS normalization).…”

“…Consequently, application of LIBS has been conducted in various other fields, such as food science, 4 biomedicine, 5 forensics, 6 and space exploration. 7 As one of the many LIBS applications, metal sorting 8 has recently attracted significant attention because of its commercial value. 9–11…”

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

“…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. 15 However, defocusing is caused because of the deviation between the laser region and surface when the sample is not at.…”