Deep learning for geographical discrimination of Panax notoginseng with directly near-infrared spectra image
文献类型： 外文期刊
作者： Dong, Jian-E 1 ; Wang, Ye 2 ; Zuo, Zhi-Tian 2 ; Wang, Yuan-Zhong 2 ;
作者机构： 1.Southwest Forestry Univ, Coll Big Data & Intelligence Engn, Kunming 650224, Yunnan, Peoples R China
2.Yunnan Acad Agr Sci, Inst Med Plants, 2238 Beijing Rd, Kunming 650200, Yunnan, Peoples R China
3.Yunnan Univ Chinese Med, Coll Tradit Chinese Med, Kunming 650500, Yunnan, Peoples R China
关键词： Residual convolutional neural network; Deep teaming; Panax notoginseng; Geographical trace; Spectra discrimination
期刊名称：CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS （ 影响因子：3.491； 五年影响因子：3.839 ）
ISSN： 0169-7439
年卷期： 2020 年 197 卷
页码：
收录情况： SCI
摘要： Herbal materials have been widely used as functional food by a certain group of people for a potentially positive effect on body health regulation. Panax notoginseng as a crude material of functional food has long medical and cultivation history for more than 400 years in China and other countries. However, the quality was fluctuated with their geographical origins and Wenshan Autonomous Prefecture was regarded as the geo-authentic location with high properties. Therefore, rapid detection method is necessary for consumer to discriminate their authentic origins. In our study, 258 near infrared spectra of root powder of P. notoginseng from five main cultivation areas were used for discrimination analysis. A deep learning strategy (residual convolutional neural network) was established with 80% spectra images. Therein, the discrimination of geographical origins of the herb was first to be reported using directly spectra images instead of data matric from these spectra. The results indicated that these samples could be correctly classified as their respective categories with 100% accuracy in training set and 91% accuracy in test set. Finally, 22 samples were accurately discriminated in 25 samples of prediction set. In general, residual convolutional neural network using direct spectra image would be a feasible strategy for geographical traceability in further discrimination research.
- 相关文献
作者其他论文 更多>>
-
Based on metabolomics and fourier transforms near infrared spectroscopy characterization of Lanxangia tsaoko chemical profile differences among fruit types and development of rapid identification and nutrient prediction models
作者：Fu, Deng-Ke;Yang, Wei-Ze;Yang, Mei-Quan;Yang, Tian-Mei;Wang, Yuan-Zhong;Zhang, Jin-Yu;Fu, Deng-Ke
关键词：Lanxangia tsao-ko; Phenotype; Metabolic differences; 2DCOS; ResNet; PLSR
-
FT-NIR Spectra of Different Dimensions Combined with Machine Learning and Image Recognition for Origin Identification: An Example of Panax notoginseng
作者：Zuo, Zhi-Tian;Yao, Zeng-Yu;Zuo, Zhi-Tian;Wang, Yuan-Zhong
关键词：
-
Application of ATR-FTIR Spectrum Combined With Ensemble Learning and Deep Learning for Identification of Amomum tsao-ko at Different Drying Temperatures
作者：He, Gang;Yang, Shao-bing;Wang, Yuan-zhong;He, Gang
关键词：Amomum tsao-ko; deep learning; drying temperatures; ensemble learning; machine learning
-
Spatial and temporal distribution characteristics of Paris polyphylla var. yunnanensis and the prediction of steroidal saponins content
作者：Zhong, Chen;Li, Li;Zhong, Chen;Wang, Yuan-Zhong
关键词：Paris polyphylla var. yunnanensis; Habitat suitability; FT-IR spectroscopy; Chemometrics; Steroidal saponins
-
A rapid method for identification of Lanxangia tsaoko origin and fruit shape: FT-NIR combined with chemometrics and image recognition
作者：He, Gang;Yang, Shao-bing;Wang, Yuan-zhong;He, Gang;Yang, Shao-bing;Wang, Yuan-zhong
关键词：chemometrics; classification; Fourier transform-near infrared spectroscopy; image recognition; Lanxangia tsaoko
-
Analysis of Chemical Changes during Maturation of Amomum tsao-ko Based on GC-MS, FT-NIR, and FT-MIR
作者：He, Gang;Yang, Shao-bing;Wang, Yuan-zhong;He, Gang
关键词：
-
FT-IR spectroscopy coupled with HPLC for qualitative and quantitative analysis of different parts of Gentiana rigescens Franch
作者：He, Gang;Zhu, Xin-yan;Wang, Yuan-zhong;He, Gang;Shen, Tao
关键词：Gentiana rigescens; Total secoiridoids; FT-IR; HPLC; Content prediction
