Matches in SemOpenAlex for { <https://semopenalex.org/work/W3155403722> ?p ?o ?g. }
- W3155403722 endingPage "119850" @default.
- W3155403722 startingPage "119850" @default.
- W3155403722 abstract "• The highest interpretability of selected variables was achieved by the SELECT or SPA algorithms. • The number of selected variables had a great impact on interpretability and model performance. • SELECT, SPA, and PCA appear promising for determining chemically important wavelengths. • The best classification performance was attained using PCA for dimension reduction. Near infrared (NIR) spectra are collected as a high amount of absorption values which usually greatly exceeds the sample size. Variable selection methods are employed in NIR spectroscopy to avoid “curse of dimensionality” related issues. In this paper, we examined the interpretability of selected variables, that is, how much selected wavelengths are related to the chemical structure of the materials studied, and if the relation is important for classification performance. Additionally, we examined classification performance in dependence on the number of selected variables. For this purpose, relative standard deviation (RSD), successive projection algorithm (SPA), stepwise decorrelation of variables (SELECT), genetic algorithm (GA), principal component analysis (PCA), and random (RANDOM) variable selection were applied in two-class classification modelling using linear discriminant analysis (LDA) or a support vector machine (SVM). Different pre-treatments and sample sizes were considered. Variable selection improved classification performance and variables selected by a majority of the methods considered were conveniently related to chemical structure. Interpretability and performance increase/decrease depend greatly on the number of selected variables, however. Since selected variables reveal great chemical interpretability, some variable selection methods could be employed to determine material characteristic absorption bands. SELECT and SPA displayed the best properties among the methods considered. To avoid faulty results, optimization of the number of selected variables should become the crucial stage in the variable selection process." @default.
- W3155403722 created "2021-04-26" @default.
- W3155403722 creator A5007264873 @default.
- W3155403722 date "2021-09-01" @default.
- W3155403722 modified "2023-10-16" @default.
- W3155403722 title "Interpretability of selected variables and performance comparison of variable selection methods in a polyethylene and polypropylene NIR classification task" @default.
- W3155403722 cites W1892325955 @default.
- W3155403722 cites W1963738185 @default.
- W3155403722 cites W1970200460 @default.
- W3155403722 cites W1976996306 @default.
- W3155403722 cites W1978864727 @default.
- W3155403722 cites W1991072106 @default.
- W3155403722 cites W1996195892 @default.
- W3155403722 cites W1997270149 @default.
- W3155403722 cites W2002172066 @default.
- W3155403722 cites W2004197570 @default.
- W3155403722 cites W2012358846 @default.
- W3155403722 cites W2014696338 @default.
- W3155403722 cites W2021754455 @default.
- W3155403722 cites W2022492778 @default.
- W3155403722 cites W2029014344 @default.
- W3155403722 cites W2045786019 @default.
- W3155403722 cites W2054335324 @default.
- W3155403722 cites W2059672887 @default.
- W3155403722 cites W2062041991 @default.
- W3155403722 cites W2063524724 @default.
- W3155403722 cites W2065674521 @default.
- W3155403722 cites W2065746048 @default.
- W3155403722 cites W2072337151 @default.
- W3155403722 cites W2076902226 @default.
- W3155403722 cites W2080436886 @default.
- W3155403722 cites W2080832455 @default.
- W3155403722 cites W2085834676 @default.
- W3155403722 cites W2086190838 @default.
- W3155403722 cites W2094062524 @default.
- W3155403722 cites W2094294594 @default.
- W3155403722 cites W2119387367 @default.
- W3155403722 cites W2121821300 @default.
- W3155403722 cites W2139770740 @default.
- W3155403722 cites W2143684265 @default.
- W3155403722 cites W2149584226 @default.
- W3155403722 cites W2152159071 @default.
- W3155403722 cites W2153678774 @default.
- W3155403722 cites W2193967774 @default.
- W3155403722 cites W2328971175 @default.
- W3155403722 cites W2339661502 @default.
- W3155403722 cites W2479710617 @default.
- W3155403722 cites W2503702664 @default.
- W3155403722 cites W2606372955 @default.
- W3155403722 cites W2768728469 @default.
- W3155403722 cites W2790006631 @default.
- W3155403722 cites W2800379463 @default.
- W3155403722 cites W2911863681 @default.
- W3155403722 cites W3026350111 @default.
- W3155403722 cites W3096349094 @default.
- W3155403722 doi "https://doi.org/10.1016/j.saa.2021.119850" @default.
- W3155403722 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33957449" @default.
- W3155403722 hasPublicationYear "2021" @default.
- W3155403722 type Work @default.
- W3155403722 sameAs 3155403722 @default.
- W3155403722 citedByCount "3" @default.
- W3155403722 countsByYear W31554037222022 @default.
- W3155403722 countsByYear W31554037222023 @default.
- W3155403722 crossrefType "journal-article" @default.
- W3155403722 hasAuthorship W3155403722A5007264873 @default.
- W3155403722 hasConcept C105795698 @default.
- W3155403722 hasConcept C127413603 @default.
- W3155403722 hasConcept C134306372 @default.
- W3155403722 hasConcept C148483581 @default.
- W3155403722 hasConcept C153180895 @default.
- W3155403722 hasConcept C154945302 @default.
- W3155403722 hasConcept C159985019 @default.
- W3155403722 hasConcept C182365436 @default.
- W3155403722 hasConcept C192562407 @default.
- W3155403722 hasConcept C201995342 @default.
- W3155403722 hasConcept C2777973245 @default.
- W3155403722 hasConcept C2779751980 @default.
- W3155403722 hasConcept C2780451532 @default.
- W3155403722 hasConcept C2781067378 @default.
- W3155403722 hasConcept C33923547 @default.
- W3155403722 hasConcept C41008148 @default.
- W3155403722 hasConcept C81917197 @default.
- W3155403722 hasConceptScore W3155403722C105795698 @default.
- W3155403722 hasConceptScore W3155403722C127413603 @default.
- W3155403722 hasConceptScore W3155403722C134306372 @default.
- W3155403722 hasConceptScore W3155403722C148483581 @default.
- W3155403722 hasConceptScore W3155403722C153180895 @default.
- W3155403722 hasConceptScore W3155403722C154945302 @default.
- W3155403722 hasConceptScore W3155403722C159985019 @default.
- W3155403722 hasConceptScore W3155403722C182365436 @default.
- W3155403722 hasConceptScore W3155403722C192562407 @default.
- W3155403722 hasConceptScore W3155403722C201995342 @default.
- W3155403722 hasConceptScore W3155403722C2777973245 @default.
- W3155403722 hasConceptScore W3155403722C2779751980 @default.
- W3155403722 hasConceptScore W3155403722C2780451532 @default.
- W3155403722 hasConceptScore W3155403722C2781067378 @default.
- W3155403722 hasConceptScore W3155403722C33923547 @default.
- W3155403722 hasConceptScore W3155403722C41008148 @default.