您好，欢迎访问云南省农业科学院 机构知识库！

A fast and effective way for authentication of Dendrobium species: 2DCOS combined with ResNet based on feature bands extracted by spectrum standard deviation

文献类型： 外文期刊

作者： Ding, Yu-Gang 1 ; Zhang, Qing-Zhi 2 ; Wang, Yuan-Zhong 1 ;

作者机构： 1.Yunnan Acad Agr Sci, Med Plants Res Inst, 2238 Beijing Rd, Kunming 650200, Yunnan, Peoples R China

2.Yunnan Univ Chinese Med, Coll Chinese Med, Kunming 650500, Yunnan, Peoples R China

关键词： Dendrobium Sw; Deep learning; Spectrum standard deviation (SDD); Two-dimensional correlation spectroscopy (2DCOS); Residual convolutional neural network (ResNet)

期刊名称：SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY （ 影响因子：4.098； 五年影响因子：3.464 ）

ISSN： 1386-1425

年卷期： 2021 年 261 卷

页码：

收录情况： SCI

摘要： Dendrobium Sw., as a traditional herb and function food with over 1500 years of history, shows a signif-icant effect in improving immunity and fatigue resistance. However, due of course the large number of species and the quality fluctuating in different species, a fast and effective discrimination method is in need. Recently, spectroscopic techniques combined with chemometrics have become an effective method for low-cost and fast analysis in food and herb. Nevertheless, chemometrics method which based on one-dimensional spectral dataset still encounter the difficulty that can not effectively extract useful informa-tion from the spectra. Different from one-dimensional spectra, the two-dimensional correlation spec-troscopy (2DCOS) can reveal more detail information of the spectral dataset. Moreover, the appearance of convolutional neural network makes the application of deep learning in image recognition faster and more accurate. In this study, a novel method 2DCOS combined with residual convolutional neural network (ResNet) was used to discriminate the 20 species of Dendrobium. Five feature bands were selected based on spectrum standard deviation (SDD) method in NIR and MIR spectra. Moreover, the models based on full band, total five feature bands, and their fusion-bands had been compared. The results showed that two feature bands 1800-450 cm-1 and 2400-1900 cm-1 displayed 100% accuracy in both training set and test set. And also, the accurate discrimination of 10% external validation showed that these models have good generalization ability. In conclusion, 2DCOS combined with ResNet could be an effective and accurate method for classify different Dendrobium species. (c) 2021 Elsevier B.V. All rights reserved.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：云南省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台