Combining UDT with XGBoost to identify the geographical origin of black beans by near-infrared spectroscopy

This study aims to rapidly and non-destructively identify the geographical origin of black beans (Phaseolus vulgaris) using a portable near-infrared (NIR) spectrometer, addressing the challenge of distinguishing black beans due to significant regional variations in quality. A total of 400 black bean...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhihang Cao, Xiaohong Wu, Bin Wu, Zexi Zhang, Jun Sun
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Current Research in Food Science
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2665927125001625
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710164685357056
author Zhihang Cao
Xiaohong Wu
Bin Wu
Zexi Zhang
Jun Sun
author_facet Zhihang Cao
Xiaohong Wu
Bin Wu
Zexi Zhang
Jun Sun
author_sort Zhihang Cao
collection DOAJ
description This study aims to rapidly and non-destructively identify the geographical origin of black beans (Phaseolus vulgaris) using a portable near-infrared (NIR) spectrometer, addressing the challenge of distinguishing black beans due to significant regional variations in quality. A total of 400 black bean samples were collected from five regions in China. To improve classification accuracy, a novel model combining uncorrelated discriminant transform (UDT) with extreme gradient boosting (XGBoost) was proposed for feature extraction and classification. When evaluated with k-nearest neighbor (KNN), naive Bayes (NB), and support vector machine (SVM) classifiers, UDT achieved accuracies of 96.25 %, 93.75 %, and 96.25 %, respectively, outperforming Foley-Sammon transform (FST) and discriminant principal component analysis (DPCA). The UDT + XGBoost combination achieved the highest classification accuracy of 100 %. For robust validation, a 5-fold cross-validation strategy was applied to the UDT + XGBoost model, achieving an average accuracy of 96.00 %. This study provides a reliable method for black bean origin traceability and authenticity.
format Article
id doaj-art-8a77314c0436402b8d00963b980a810f
institution DOAJ
issn 2665-9271
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Current Research in Food Science
spelling doaj-art-8a77314c0436402b8d00963b980a810f2025-08-20T03:15:02ZengElsevierCurrent Research in Food Science2665-92712025-01-011110113110.1016/j.crfs.2025.101131Combining UDT with XGBoost to identify the geographical origin of black beans by near-infrared spectroscopyZhihang Cao0Xiaohong Wu1Bin Wu2Zexi Zhang3Jun Sun4Mengxi Honors College, Jiangsu University, Zhenjiang, 212013, ChinaSchool of Electrical and Information Engineering, Jiangsu University, Zhenjiang, 212013, China; High-tech Key Laboratory of Agricultural Equipment and Intelligence of Jiangsu Province, Jiangsu University, Zhenjiang, 212013, China; Corresponding author. School of Electrical and Information Engineering, Jiangsu University, Xuefu Road No. 301, Zhenjiang, 212013, China.Department of Information Engineering, Chuzhou Polytechnic, Chuzhou, 239000, China; School of Computer Science and Engineering, Southeast University, Nanjing, 211189, China; Corresponding author. Department of Information Engineering, Chuzhou Polytechnic, Fengle Street No. 2188, Chuzhou, 239000, China.Mengxi Honors College, Jiangsu University, Zhenjiang, 212013, ChinaSchool of Electrical and Information Engineering, Jiangsu University, Zhenjiang, 212013, ChinaThis study aims to rapidly and non-destructively identify the geographical origin of black beans (Phaseolus vulgaris) using a portable near-infrared (NIR) spectrometer, addressing the challenge of distinguishing black beans due to significant regional variations in quality. A total of 400 black bean samples were collected from five regions in China. To improve classification accuracy, a novel model combining uncorrelated discriminant transform (UDT) with extreme gradient boosting (XGBoost) was proposed for feature extraction and classification. When evaluated with k-nearest neighbor (KNN), naive Bayes (NB), and support vector machine (SVM) classifiers, UDT achieved accuracies of 96.25 %, 93.75 %, and 96.25 %, respectively, outperforming Foley-Sammon transform (FST) and discriminant principal component analysis (DPCA). The UDT + XGBoost combination achieved the highest classification accuracy of 100 %. For robust validation, a 5-fold cross-validation strategy was applied to the UDT + XGBoost model, achieving an average accuracy of 96.00 %. This study provides a reliable method for black bean origin traceability and authenticity.http://www.sciencedirect.com/science/article/pii/S2665927125001625Black beanNear-infrared spectroscopyGeographical originExtreme gradient boostingUncorrelated discriminant transform
spellingShingle Zhihang Cao
Xiaohong Wu
Bin Wu
Zexi Zhang
Jun Sun
Combining UDT with XGBoost to identify the geographical origin of black beans by near-infrared spectroscopy
Current Research in Food Science
Black bean
Near-infrared spectroscopy
Geographical origin
Extreme gradient boosting
Uncorrelated discriminant transform
title Combining UDT with XGBoost to identify the geographical origin of black beans by near-infrared spectroscopy
title_full Combining UDT with XGBoost to identify the geographical origin of black beans by near-infrared spectroscopy
title_fullStr Combining UDT with XGBoost to identify the geographical origin of black beans by near-infrared spectroscopy
title_full_unstemmed Combining UDT with XGBoost to identify the geographical origin of black beans by near-infrared spectroscopy
title_short Combining UDT with XGBoost to identify the geographical origin of black beans by near-infrared spectroscopy
title_sort combining udt with xgboost to identify the geographical origin of black beans by near infrared spectroscopy
topic Black bean
Near-infrared spectroscopy
Geographical origin
Extreme gradient boosting
Uncorrelated discriminant transform
url http://www.sciencedirect.com/science/article/pii/S2665927125001625
work_keys_str_mv AT zhihangcao combiningudtwithxgboosttoidentifythegeographicaloriginofblackbeansbynearinfraredspectroscopy
AT xiaohongwu combiningudtwithxgboosttoidentifythegeographicaloriginofblackbeansbynearinfraredspectroscopy
AT binwu combiningudtwithxgboosttoidentifythegeographicaloriginofblackbeansbynearinfraredspectroscopy
AT zexizhang combiningudtwithxgboosttoidentifythegeographicaloriginofblackbeansbynearinfraredspectroscopy
AT junsun combiningudtwithxgboosttoidentifythegeographicaloriginofblackbeansbynearinfraredspectroscopy