Machine learning and deep learning based on the small FT-MIR dataset for fine-grained sampling site recognition of boletus tomentipes
文献类型： 外文期刊
作者： Dong, Jian-E 1 ; Li, Jieqing 2 ; Liu, Honggao 2 ; Wang, Yuan-Zhong 4 ;
作者机构： 1.Southwest Forestry Univ, Coll Big Data & Intelligence Engn, Kunming 650224, Peoples R China
2.Yunnan Agr Univ, Coll Agron & Biotechnol, Kunming 650201, Peoples R China
3.Zhaotong Univ, Zhaotong 657000, Peoples R China
4.Yunnan Acad Agr Sci, Med Plants Res Inst, Kunming 650200, Peoples R China
5.Yunnan Acad Agr Sci, Med Plants Res Inst, 2238 Beijing Rd, Kunming 650200, Peoples R China
关键词： Cadmium; Sampling site; Machine learning algorithm; Gradient Boosting Machine algorithm; Image processing; Deep learning
期刊名称：FOOD RESEARCH INTERNATIONAL （ 影响因子：8.1； 五年影响因子：7.7 ）
ISSN： 0963-9969
年卷期： 2023 年 167 卷
页码：
收录情况： SCI
摘要： This study proposed the necessity of identifying the sampling sites for Boletus tomentipes (B.tomentipes) in combination with cadmium content and environmental factors. Based on fourier transform mid-infrared spectroscopy (FT-MIR) preprocessing by 1st, 2nd, MSC, SNV and SG, five machine learning (ML) algorithms (NB, DT, KNN, RF, SVM) and three Gradient Boosting Machine (GBM) algorithms (XGBoost, LightGBM, CatBoost) were built. To avoid complex preprocessing, we construct BoletusResnet model, propose the concepts of 3DCOS, 3DCOS projected images, index images in addition to 2DCOS, and combine them with deep learning (DL) for classification for the first time. It shows that GBM has higher accuracy than ML and DL has better accuracy than GBM. The four DL models presented in this paper achieve fine-grained sampling sites recognition based on small samples with 100 % accuracy, and a computer application system was developed on them. Therefore, spectral image processing combined with DL is a rapid and efficient classification method which can be widely used in food identification.
- 相关文献
作者其他论文 更多>>
-
Rapid determination of geographical authenticity of Gastrodia elata f. glauca using Fourier transform infrared spectroscopy and deep learning
作者：Deng, Guangmei;Li, Jieqing;Deng, Guangmei;Wang, Yuanzhong;Liu, Honggao
关键词：Gastrodia elata f. glauca; Fourier transform infrared spectroscopy; Deep learning; Data driven version of soft independent; modeling of class analogy
-
Effect of drying temperature on composition of edible mushrooms: Characterization and assessment via HS-GC-MS and IR spectral based volatile profiling and chemometrics
作者：Zheng, Chuanmao;Li, Jieqing;Zheng, Chuanmao;Wang, Yuanzhong;Liu, Honggao
关键词：Boletus bainiugan; HS-SPME-GC-MS; VOCs; 2DCOS; Chemometrics; Quality estimation
-
The method based on ATR-FTIR spectroscopy combined with feature variable selection for the boletus species and origins identification
作者：Ji, Zhiyi;Li, Jieqing;Ji, Zhiyi;Wang, Yuanzhong;Liu, Honggao
关键词：feature variable selection; food safety; mid-infrared spectroscopy; species identification; traceability; wild boletus
-
Identification of geographical origins of Gastrodia elata Blume based on multisource data fusion
作者：Liu, Hong;Li, Jieqing;Liu, Hong;Wang, Yuanzhong;Liu, Honggao
关键词：2DCOS images; ATR-FTIR; data fusion; FT-NIR; Gastrodia elata Blume; geographical discrimination
-
A fast method for predicting adenosine content in porcini mushrooms using Fourier transform near-infrared spectroscopy combined with regression model
作者：Deng, Guangmei;Li, Jieqing;Deng, Guangmei;Wang, Yuanzhong;Liu, Honggao
关键词：Fourier transform near-infrared spectroscopy; Porcini mushrooms; Adenosine; Partial least squares regression
-
Applications of chemical fingerprints and machine learning in plant ecology: Recent progress and future perspectives
作者：Zhong, Chen;Wang, Yuan-Zhong;Zhong, Chen;Li, Li
关键词：Chemical fingerprints; Chemometrics; Plant ecology; Analytical techniques; Machine learning algorithms
-
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：
