Non-destructive identification of commercial jerky types based on multi-band hyperspectral imaging with machine learning

Commercial jerky counterfeiting is widespread in the market. This study combined visible-near-infrared and short-wave-near-infrared hyperspectral imaging along with multiple machine learning algorithms for non-destructive identification of five types of commercial jerky products, and explored the im...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuanxi Han, Liang Li, Siyuan Jiang, Pengpeng Sun, Wenliang Wu, Zhendong Liu
Format: Article
Language:English
Published: Elsevier 2025-02-01
Series:Food Chemistry: X
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590157525001403
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850079751275806720
author Yuanxi Han
Liang Li
Siyuan Jiang
Pengpeng Sun
Wenliang Wu
Zhendong Liu
author_facet Yuanxi Han
Liang Li
Siyuan Jiang
Pengpeng Sun
Wenliang Wu
Zhendong Liu
author_sort Yuanxi Han
collection DOAJ
description Commercial jerky counterfeiting is widespread in the market. This study combined visible-near-infrared and short-wave-near-infrared hyperspectral imaging along with multiple machine learning algorithms for non-destructive identification of five types of commercial jerky products, and explored the impact of different spectral bands, algorithm selection, and optimization methods on identification performance. After data preprocessing, all models' accuracies and stability improved. Specifically, the logistic regression model was best for jerky identification, with 85.78 %–100.00 % accuracy. With hyperparameter optimization, Support Vector Machine with linear kernel had highest accuracy (89.29 % and 95.29 % in two bands). Additionally, the artificial neural network with the hyperbolic tangent activation function had optimal training performance, exceeding 90.00 % accuracy. The findings demonstrate short-wave-near-infrared hyperspectral imaging combined with linear models (logistic regression and Support Vector Machine with linear kernel parameter settings) is better for identifying the types of jerky. This study provides reference for the band, model selection, and optimization of jerky type identification.
format Article
id doaj-art-b2964538b3a744efae216d6c4e77c3a0
institution DOAJ
issn 2590-1575
language English
publishDate 2025-02-01
publisher Elsevier
record_format Article
series Food Chemistry: X
spelling doaj-art-b2964538b3a744efae216d6c4e77c3a02025-08-20T02:45:07ZengElsevierFood Chemistry: X2590-15752025-02-012610229310.1016/j.fochx.2025.102293Non-destructive identification of commercial jerky types based on multi-band hyperspectral imaging with machine learningYuanxi Han0Liang Li1Siyuan Jiang2Pengpeng Sun3Wenliang Wu4Zhendong Liu5Food Science College, Xizang Agriculture & Animal Husbandry University, R&D Center of Agricultural Products with Xizang Plateau Characteristics, The Provincial and Ministerial Co-founded Collaborative Innovation Center for R&D in Xizang Characteristic Agricultural and Animal Husbandry Resources, Nyingchi 860000, ChinaFood Science College, Xizang Agriculture & Animal Husbandry University, R&D Center of Agricultural Products with Xizang Plateau Characteristics, The Provincial and Ministerial Co-founded Collaborative Innovation Center for R&D in Xizang Characteristic Agricultural and Animal Husbandry Resources, Nyingchi 860000, ChinaFood Science College, Xizang Agriculture & Animal Husbandry University, R&D Center of Agricultural Products with Xizang Plateau Characteristics, The Provincial and Ministerial Co-founded Collaborative Innovation Center for R&D in Xizang Characteristic Agricultural and Animal Husbandry Resources, Nyingchi 860000, ChinaCollege of Information Engineering, Northwest A&F University, Shaanxi, Xianyang, 712100, ChinaCollege of Information Engineering, Northwest A&F University, Shaanxi, Xianyang, 712100, China; Corresponding authors.Food Science College, Xizang Agriculture & Animal Husbandry University, R&D Center of Agricultural Products with Xizang Plateau Characteristics, The Provincial and Ministerial Co-founded Collaborative Innovation Center for R&D in Xizang Characteristic Agricultural and Animal Husbandry Resources, Nyingchi 860000, China; Corresponding authors.Commercial jerky counterfeiting is widespread in the market. This study combined visible-near-infrared and short-wave-near-infrared hyperspectral imaging along with multiple machine learning algorithms for non-destructive identification of five types of commercial jerky products, and explored the impact of different spectral bands, algorithm selection, and optimization methods on identification performance. After data preprocessing, all models' accuracies and stability improved. Specifically, the logistic regression model was best for jerky identification, with 85.78 %–100.00 % accuracy. With hyperparameter optimization, Support Vector Machine with linear kernel had highest accuracy (89.29 % and 95.29 % in two bands). Additionally, the artificial neural network with the hyperbolic tangent activation function had optimal training performance, exceeding 90.00 % accuracy. The findings demonstrate short-wave-near-infrared hyperspectral imaging combined with linear models (logistic regression and Support Vector Machine with linear kernel parameter settings) is better for identifying the types of jerky. This study provides reference for the band, model selection, and optimization of jerky type identification.http://www.sciencedirect.com/science/article/pii/S2590157525001403Commodity jerkyHyperspectral imagingMachine learningSpectral band optimizationType identification
spellingShingle Yuanxi Han
Liang Li
Siyuan Jiang
Pengpeng Sun
Wenliang Wu
Zhendong Liu
Non-destructive identification of commercial jerky types based on multi-band hyperspectral imaging with machine learning
Food Chemistry: X
Commodity jerky
Hyperspectral imaging
Machine learning
Spectral band optimization
Type identification
title Non-destructive identification of commercial jerky types based on multi-band hyperspectral imaging with machine learning
title_full Non-destructive identification of commercial jerky types based on multi-band hyperspectral imaging with machine learning
title_fullStr Non-destructive identification of commercial jerky types based on multi-band hyperspectral imaging with machine learning
title_full_unstemmed Non-destructive identification of commercial jerky types based on multi-band hyperspectral imaging with machine learning
title_short Non-destructive identification of commercial jerky types based on multi-band hyperspectral imaging with machine learning
title_sort non destructive identification of commercial jerky types based on multi band hyperspectral imaging with machine learning
topic Commodity jerky
Hyperspectral imaging
Machine learning
Spectral band optimization
Type identification
url http://www.sciencedirect.com/science/article/pii/S2590157525001403
work_keys_str_mv AT yuanxihan nondestructiveidentificationofcommercialjerkytypesbasedonmultibandhyperspectralimagingwithmachinelearning
AT liangli nondestructiveidentificationofcommercialjerkytypesbasedonmultibandhyperspectralimagingwithmachinelearning
AT siyuanjiang nondestructiveidentificationofcommercialjerkytypesbasedonmultibandhyperspectralimagingwithmachinelearning
AT pengpengsun nondestructiveidentificationofcommercialjerkytypesbasedonmultibandhyperspectralimagingwithmachinelearning
AT wenliangwu nondestructiveidentificationofcommercialjerkytypesbasedonmultibandhyperspectralimagingwithmachinelearning
AT zhendongliu nondestructiveidentificationofcommercialjerkytypesbasedonmultibandhyperspectralimagingwithmachinelearning