Determination of the Geographical Origin of Vinh Linh Black Pepper Using a Combination of FT‐NIR Spectroscopy, Machine Learning Algorithms, and Variable Selection Techniques.
Saved in:
| Title: | Determination of the Geographical Origin of Vinh Linh Black Pepper Using a Combination of FT‐NIR Spectroscopy, Machine Learning Algorithms, and Variable Selection Techniques. |
|---|---|
| Authors: | Le, Tuan Phuc1 (AUTHOR), Lai, Quoc Dat2 (AUTHOR), Nguyen, Hoang Dung2 (AUTHOR), Pham, Ngoc Hung1 (AUTHOR), Hoang, Quoc Tuan1 (AUTHOR), Cung, Thi To Quynh1 (AUTHOR) quynh.cungthito@hust.edu.vn, Jha, Poulami (AUTHOR) pojha@wiley.com |
| Source: | Journal of Food Processing & Preservation. 4/30/2026, Vol. 2026, p1-10. 10p. |
| Subjects: | Near infrared spectroscopy, Machine learning, Black pepper (Plant), Food traceability, Quality assurance, Feature selection |
| Abstract: | Determining the geographical origin of black pepper is crucial for combating fraud in the spice industry. This study employs near‐infrared (NIR) spectroscopy combined with machine learning to classify black pepper samples from three distinct Vietnamese regions. Using the novel preprocessing–variable selection–model tuning–evaluation (PVME) framework, a robust classification accuracy of 92% was achieved on the training set and 93% on the test set, with precision, recall, and specificity exceeding 92% and 98%, respectively. The framework systematically integrates advanced preprocessing techniques, variable selection algorithms, and optimized machine learning models (LDA, KNN, RF, XGB, and SVM). This nondestructive, rapid, and cost‐effective method offers a standardized protocol for origin verification, with potential applications to other agricultural products. Beyond black pepper, this approach can be extended to other agricultural commodities for tasks such as quality prediction, adulteration detection, and real‐time, noninvasive monitoring in food processing environments. The proposed framework supports scalable, technology‐driven quality assurance strategies in modern agri‐food supply chains. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Food Processing & Preservation is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Determining the geographical origin of black pepper is crucial for combating fraud in the spice industry. This study employs near‐infrared (NIR) spectroscopy combined with machine learning to classify black pepper samples from three distinct Vietnamese regions. Using the novel preprocessing–variable selection–model tuning–evaluation (PVME) framework, a robust classification accuracy of 92% was achieved on the training set and 93% on the test set, with precision, recall, and specificity exceeding 92% and 98%, respectively. The framework systematically integrates advanced preprocessing techniques, variable selection algorithms, and optimized machine learning models (LDA, KNN, RF, XGB, and SVM). This nondestructive, rapid, and cost‐effective method offers a standardized protocol for origin verification, with potential applications to other agricultural products. Beyond black pepper, this approach can be extended to other agricultural commodities for tasks such as quality prediction, adulteration detection, and real‐time, noninvasive monitoring in food processing environments. The proposed framework supports scalable, technology‐driven quality assurance strategies in modern agri‐food supply chains. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 01458892 |
| DOI: | 10.1155/jfpp/2750185 |
