![Sample our Physical Sciences journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/110819/TOC-Subject-Sample-2021-Physical-Sciences.jpg"})
ABSTRACT
Herbal products produced from multiple plants have special characteristics in the clinical practice of traditional Chinese medicine. These traits provide the opportunity for fraudulent merchants to mix other herbal products similar in appearance into authentic herbal medicine. Shihu is a tonic herbal medicine from the Dendrobium plants with complex botanical origins. In this context, 11 Dendrobium plants including 109 individuals from China were collected for authentication work. Nine species have been described as herbal medicines in the literature while D. hookerianum and D. xichouense are not reported to have medicinal benefits. A key feature of this study was that multiple recognition approaches, based on near-infrared and ultraviolet–visible spectra as well as their combination, were compared to investigate their classification performance. Intuitively, score plots using principal component analysis and hierarchical cluster diagrams were used to evaluate the genetic relationships among these species. Compared with support vector machine discrimination analysis and k-nearest neighbor models, the partial least square discrimination analysis model combined with low-level data fusion provided excellent performance for authentication and was the most robust model with 100% accuracy rates for the training and prediction sets. The results indicated that near-infrared and ultraviolet–visible spectra and their fusion dataset combined with supervised recognition analysis are effective and therefore recommended for the authentication of genuine and sham of herbal Shihu species.