Abstract
In order to improve the classification accuracy of Chinese Salvia miltiorrhiza using near-infrared spectroscopy, a novel local variable selection strategy is thus proposed. Combining the strengths of the local algorithm and interval partial least squares, the spectra data have firstly been divided into several pairs of classes in sample direction and equidistant subintervals in variable direction. Then, a local classification model has been built, and the most proper spectral region has been selected based on the new evaluation criterion considering both classification error rate and best predictive ability under the leave-one-out cross validation scheme for each pair of classes. Finally, each observation can be assigned to belong to the class according to the statistical analysis of classification results of the local classification model built on selected variables. The performance of the proposed method was demonstrated through near-infrared spectra of cultivated or wild Salvia miltiorrhiza, which are collected from 8 geographical origins in 5 provinces of China. For comparison, soft independent modelling of class analogy and partial least squares discriminant analysis methods are, respectively, employed as the classification model. Experimental results showed that classification performance of the classification model with local variable selection was obvious better than that without variable selection.
Highlights
Salvia miltiorrhiza (S. miltiorrhiza), named “Danshen” in China, has been considered as an important component of traditional Chinese medicines (TCMs) [1]. e most important and frequent clinical application of S. miltiorrhiza is mainly employed for treatment of various cardiovascular diseases, including coronary artery disease, hyperlipidemia, hypertension, arrhythmias, and stroke by either alone or in combination with other herbal ingredients [2]
A novel local variable selection (L-VS) strategy was proposed for discrimination of Chinese S. miltiorrhiza according to its geographical origins and planting conditions
principal component analysis (PCA) was utilized initially to examine the qualitative difference of all the S. miltiorrhiza samples in the principal component (PC) space
Summary
Received 2 July 2017; Revised 5 November 2017; Accepted 14 November 2017; Published 29 January 2018. In order to improve the classification accuracy of Chinese Salvia miltiorrhiza using near-infrared spectroscopy, a novel local variable selection strategy is proposed. Combining the strengths of the local algorithm and interval partial least squares, the spectra data have firstly been divided into several pairs of classes in sample direction and equidistant subintervals in variable direction. Each observation can be assigned to belong to the class according to the statistical analysis of classification results of the local classification model built on selected variables. E performance of the proposed method was demonstrated through near-infrared spectra of cultivated or wild Salvia miltiorrhiza, which are collected from 8 geographical origins in 5 provinces of China. Experimental results showed that classification performance of the classification model with local variable selection was obvious better than that without variable selection
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
