Assessing utility of handheld laser induced breakdown spectroscopy as a means of<i>Dalbergia</i>speciation

Celani, Caelin P.; Lancaster, Cady A.; Jordan, James A.; Espinoza, Edgard O.; Booksh, Karl S.

doi:10.1039/c9an00984a

Cited by 11 publications

(18 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supplied data come from the application of multiple classification methods for identification of Dalbergia subspecies via laser-induced breakdown spectroscopy (LIBS). 30 Dalbergia classes are based on the lot number analyzed by LIBS); each lot consisted of a single Dalbergia species (Table 1). Keep in mind that confusion matrix entries are based on number of samples in the given test (prediction) set and not the total number of samples present in any given class.…”

Section: Methodsmentioning

confidence: 99%

Visualization of confusion matrices with network graphs

Gilbraith

Celani

Booksh

2022

Journal of Chemometrics

View full text Add to dashboard Cite

The use of network analysis as a means of visualizing the off-diagonal (misclassified) elements of a confusion matrix is demonstrated, and the potential to use the network graphs as a guide for developing hierarchical classification models is presented. A very brief summary of graph theory is described. This is followed by an explanation and code with examples of how these networks can then be used for visualization of confusion matrices. The use of network graphs to provide insight into differing model performance is also addressed.

show abstract

Section: Methodsmentioning

confidence: 99%

Visualization of confusion matrices with network graphs

Gilbraith

Celani

Booksh

2022

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…The k -nearest neighbor (kNN) [ 21 , 22 , 23 , 24 , 25 ] is one of the most commonly used multi-classification algorithms. When it was applied to a supervised multi-category problem, the idea was as follows: based on the spectra of calibration samples containing multiple categories, the Euclidean (or Mahalanobis) distances between the unknown sample and all calibration samples were calculated; the k nearest calibration samples were determined; finally, the unknown sample was categorized as the category with the largest number among the k nearest samples.…”

Section: Introductionmentioning

confidence: 99%

“…It is not limited by the number of categories and is especially suitable for multi-category spectral discriminant analysis. The kNN has been applied to multi-category discriminant analysis based on various spectral techniques, such as, NIR [ 21 ], mid-infrared [ 22 ], Raman [ 23 , 24 ], and laser-induced breakdown spectroscopies [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Performance Improvement of NIR Spectral Pattern Recognition from Three Compensation Models’ Voting and Multi-Modal Fusion

Fang

et al. 2022

Molecules

View full text Add to dashboard Cite

Inspired by aquaphotomics, the optical path length of measurement was regarded as a perturbation factor. Near-infrared (NIR) spectroscopy with multi-measurement modals was applied to the discriminant analysis of three categories of drinking water. Moving window-k nearest neighbor (MW-kNN) and Norris derivative filter were used for modeling and optimization. Drawing on the idea of game theory, the strategy for two-category priority compensation and three-model voting with multi-modal fusion was proposed. Moving window correlation coefficient (MWCC), inter-category and intra-category MWCC spectra, and k-shortest distances plotting with MW-kNN were proposed to evaluate weak differences between two spectral populations. For three measurement modals (1 mm, 4 mm, and 10 mm), the optimal MW-kNN models, and two-category priority compensation models were determined. The joint models for three compensation models’ voting were established. Comprehensive discrimination effects of joint models were better than their sub-models; multi-modal fusion was better than single-modal fusion. The best joint model was the dual-modal fusion of compensation models of one- and two-category priority (1 mm), one- and three-category priority (10 mm), and two- and three-category priority (1 mm), validation’s total recognition accuracy rate reached 95.5%. It fused long-wave models (1 mm, containing 1450 nm) and short-wave models (10 mm, containing 974 nm). The results showed that compensation models’ voting and multi-modal fusion can effectively improve the performance of NIR spectral pattern recognition.

show abstract

“…Therefore, it is indispensable to develop a reliable method to identify different hongmu species and distinguish between rare hongmu and cheap fakes. Several methods such as nuclear magnetic resonance spectroscopy (NMR), 4,10 liquid chromatography-mass spectrometry (LC-MS), [11][12][13][14] gas chromatography-mass spectrometry (GC-MS), 2,15 direct analysis in real time-mass spectrometry (DART-MS), [16][17][18] laser induced breakdown spectroscopy (LIBS), 19 near-infrared spectroscopy (NIRS) 20 and Fourier transform infrared spectroscopy (FT-IR) 15,21 have been applied in the analysis of hongmu species.…”

Section: Introductionmentioning

confidence: 99%

Rapid detection and classification of hongmu by atmospheric pressure ionization mass spectrometry

Wang

et al. 2022

Analyst

View full text Add to dashboard Cite

show abstract

Assessing utility of handheld laser induced breakdown spectroscopy as a means ofDalbergiaspeciation

Abstract: Seven Dalbergia and two non-Dalbergia hardwood species were successfully differentiated with PLS-DA and KNN chemometric models of LIBS spectra.

Cited by 11 publications

References 34 publications

Visualization of confusion matrices with network graphs

Visualization of confusion matrices with network graphs

Performance Improvement of NIR Spectral Pattern Recognition from Three Compensation Models’ Voting and Multi-Modal Fusion

Rapid detection and classification of hongmu by atmospheric pressure ionization mass spectrometry

Contact Info

Product

Resources

About