An efficient variable selection method based on random frog for the multivariate calibration of NIR spectra.

Autor:	Sun J; College of Agriculture, Shanxi Agricultural University South Min-Xian Road, Taigu Shanxi China sxauywd@126.com fmc101@163.com.; College of Arts and Science, Shanxi Agricultural University South Min-Xian Road, Taigu Shanxi China., Yang W; College of Agriculture, Shanxi Agricultural University South Min-Xian Road, Taigu Shanxi China sxauywd@126.com fmc101@163.com., Feng M; College of Agriculture, Shanxi Agricultural University South Min-Xian Road, Taigu Shanxi China sxauywd@126.com fmc101@163.com., Liu Q; College of Information Science and Engineering, Shanxi Agricultural University South Min-Xian Road, Taigu Shanxi China., Kubar MS; College of Agriculture, Shanxi Agricultural University South Min-Xian Road, Taigu Shanxi China sxauywd@126.com fmc101@163.com.
Jazyk:	angličtina
Zdroj:	RSC advances [RSC Adv] 2020 Apr 23; Vol. 10 (28), pp. 16245-16253. Date of Electronic Publication: 2020 Apr 23 (Print Publication: 2020).
DOI:	10.1039/d0ra00922a
Abstrakt:	Variable selection is a critical step for spectrum modeling. In this study, a new method of variable interval selection based on random frog (RF), known as Interval Selection based on Random Frog (ISRF), is developed. In the ISRF algorithm, RF is used to search the most likely informative variables and then, a local search is applied to expand the interval width of the informative variables. Through multiple runs and visualization of the results, the best informative interval variables are obtained. This method was tested on three near infrared (NIR) datasets. Four variable selection methods, namely, genetic algorithm PLS (GA-PLS), random frog, interval random frog (iRF) and interval variable iterative space shrinkage approach (iVISSA) were used for comparison. The results show that the proposed method is very efficient to find the best interval variables and improve the model's prediction performance and interpretation. Competing Interests: There are no conflicts to declare. (This journal is © The Royal Society of Chemistry.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu