Two dimensional correlation spectroscopy combined with ResNet: Efficient method to identify bolete species compared to traditional machine learning
文献类型： 外文期刊
作者： Yan, Ziyun 1 ; Liu, Honggao 2 ; Li, Tao 4 ; Li, Jieqing 1 ; Wang, Yuanzhong 5 ;
作者机构： 1.Yunnan Agr Univ, Coll Resources & Environm, Kunming 650201, Yunnan, Peoples R China
2.Yunnan Agr Univ, Coll Agron & Biotechnol, Kunming 650201, Yunnan, Peoples R China
3.Zhaotong Univ, Zhaotong 657000, Peoples R China
4.Yuxi Normal Univ, Coll Resources & Environm, Yuxi 653199, Peoples R China
5.Yunnan Acad Agr Sci, Inst Med Plants, Kunming 650223, Yunnan, Peoples R China
关键词： Bolete; FT-NIR; Chemometrics; 2DCOS; ResNet
期刊名称：LWT-FOOD SCIENCE AND TECHNOLOGY （ 影响因子：6.056； 五年影响因子：6.295 ）
ISSN： 0023-6438
年卷期： 2022 年 162 卷
页码：
收录情况： SCI
摘要： Different species of bolete have different nutritional and medicinal value, which leads to the phenomenon of shoddy in the market from time to time. Therefore, consumers need a fast and effective detection method to identify their species. In this paper, different data pretreatment was carried out for the Fourier transform near infrared (FT-NIR) spectra, and the modeling results of partial least squares discrimination analysis (PLS-DA), support vector machines (SVM) and residual neural network (ResNet) were compared. The results show that PLS-DA and SVM models need a suitable combination of pretreatment for spectral data. The purpose is to improve the accuracy of the model and avoid over fitting. After spectral pretreatment, the accuracy of PLS-DA model were improved to 99.63% and 97.38% respectively. In order to ensure that the SVM model does not have the risk of over fitting, the accuracy of the SVM model after pretreatment were reduced to 98.5% and 93.63%. The ResNet model was established based on the original spectrum. The accuracy of the model was 100%, and there is no over fitting phenomenon, which is one of the advantages of the model. Comparing the above three models, ResNet is the best model for bolete species identification.
- 相关文献
作者其他论文 更多>>
-
Recent trends of multi-source and non-destructive information for quality authentication of herbs and spices
作者：Xu, Yulin;Zhang, Jinyu;Wang, Yuanzhong;Xu, Yulin
关键词：Herbs and spices; Non-destructive techniques; Multi -source information; Data processing; Data fusion; Quality authentication
-
Machine learning and deep learning based on the small FT-MIR dataset for fine-grained sampling site recognition of boletus tomentipes
作者：Dong, Jian-E;Dong, Jian-E;Li, Jieqing;Liu, Honggao;Liu, Honggao;Wang, Yuan-Zhong;Wang, Yuan-Zhong
关键词：Cadmium; Sampling site; Machine learning algorithm; Gradient Boosting Machine algorithm; Image processing; Deep learning
-
Contributions of ectomycorrhizal fungi in a reclaimed poplar forest (Populus yunnanensis) in an abandoned metal mine tailings pond, southwest China
作者：Xiao, Yinrun;Liu, Conglong;Hu, Na;Wang, Bowen;Zhao, Zhiwei;Li, Tao;Xiao, Yinrun;Liu, Conglong;Hu, Na;Wang, Bowen;Li, Tao;Zheng, Kuanyu
关键词：Bovista limosa; Physiological responses; Heavy metal tolerance; Phytoremediation; Compartmentalization
-
A new effective method for identifying boletes species based on FT-MIR and three dimensional correlation spectroscopy projected image processing
作者：Dong, Jian-E;Li, Jieqing;Liu, Honggao;Wang, Yuan Zhong;Dong, Jian-E;Wang, Yuan Zhong
关键词：Boletes; Species; Image processing; Deep learning; 3DCOS projection
-
Solving the identification problems of Bolete origins based on multiple data processing: Take Boletus bainiugan as an example
作者：Liu, Shuai;Li, Jieqing;Liu, Shuai;Wang, Yuanzhong;Liu, Honggao
关键词：Infrared spectroscopy; Boletus bainiugan; Data fusion; Chemometrics; Deep learning; Authentication
-
Building deep learning and traditional chemometric models based on Fourier transform mid- infrared spectroscopy: Identification of wild and cultivated Gastrodia elata
作者：Liu, Shuai;Li, Jieqing;Liu, Shuai;Wang, Yuanzhong;Liu, Honggao
关键词：authentication; chemometrics; deep learning; Fourier transform mid-infrared (FT-MIR) spectroscopy; Gastrodia elata; three-dimensional correlated spectral (3DCOS)
-
Qualitative and quantitative analysis of Lanmaoa asiatica in different storage years based on FT-NIR combined with chemometrics
作者：Yan, Ziyun;Li, Jieqing;Yan, Ziyun;Wang, Yuanzhong;Liu, Honggao
关键词：Lanmaoa asiatica; FT-NIR; HPLC; Chemometrics; Nucleoside; Content prediction
