数字农科院2.0

A new comprehensive index for the assessment of mutton quality deterioration during storage using hyperspectral imaging combined with autoencoder-assisted self-supervised learning and generative network

文献类型： 外文期刊

作者： Yi, Weiguo;Zhao, Xingyan;Yun, Xueyan;Wang, Bing;Li, Shaobo;Dong, Tungalag

作者机构：

关键词： Mutton;Hyperspectral images;Autoencoder;Self-supervised learning;Generative network

期刊名称： LWT-FOOD SCIENCE AND TECHNOLOGY

ISSN： 0023-6438

年卷期： 2025 年 239 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Mutton is tender and juicy but is prone to quality deterioration during storage. Hyperspectral images (HSI) combined with deep learning has significant advantages in predicting mutton quality deterioration during storage, however, the current models are generally faced with the problems of limited sample size and a individual indicator for evaluating mutton deterioration. In this research, physicochemical indicators of mutton at different storage times were determined, including inosine monophosphate, inosine, hypoxanthine, thiobarbituric acid reactive substances, total volatile basic nitrogen, pH, and color. A comprehensive quality degradation index (CQDI) was constructed using the entropy weight method to integrate these measures. Subsequently, a convolutional neural network (CNN) model was developed to predict the CQDI from HSI data. To optimize the CNN performance under data constraints, we employed autoencoder-assisted self-supervised learning (AE-assisted SSL) and autoencoder-assisted generative networks (AE-assisted GN). The results demonstrated that spectral data predicted the CQDI with higher accuracy compared to individual physicochemical indicators. While AE-assisted SSL degrades CNN model performance, AE-assisted GN notably enhances CNN model performance under small sample scenarios. AE-assisted GN enhances CNN model performance, yielding a 3.73 % increase in R2p and a 94.56 % reduction in RMSE. The research indicated that a comprehensive index approach represented a novel method for evaluating mutton quality degradation during storage, and AE-assisted GN could enhance the performance of prediction models in small sample datasets.

分类号：

  • 相关文献

[1]Early lameness detection in dairy cattle based on wearable gait analysis using semi-supervised LSTM-Autoencoder. Kai Zhang,Shuqing Han,Jianzhai Wu,Guodong Cheng,Yali Wang,Saisai Wu,Jifang Liu. 2023

[2]DeepAT: A Deep Learning Wheat Phenotype Prediction Model Based on Genotype Data. Jiale Li,Zikang He,Guomin Zhou,Shen Yan,Jianhua Zhang. 2024

[3]Cotton Yield Prediction with Gaussian Distribution Sampling and Variational AutoEncoder. Yaqi Lan,Xiudong Wang,Lei Gao,Xiaoliang Chen. 2025

[4]Monocular Depth Estimation with Self-Supervised Learning for Vineyard Unmanned Agricultural Vehicle. Xue Zhi Cui,Quan Feng,Shu Zhi Wang,Jian Hua Zhang. 2022

[5]Self-supervised heterogeneous graph neural network based on deep and broad neighborhood encoding. Qianyu Song,Chao Li,Jinhu Fu,Qingtian Zeng,Nengfu Xie. 2025

[6]A Self-Supervised Pre-Trained Transformer Model for Accurate Genomic Prediction of Swine Phenotypes. Weixi Xiang,Zhaoxin Li,Qixin Sun,Xiujuan Chai,Tan Sun. 2025

[7]Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method. Dong Chun-wang,Ye Yang,Zhang Jian-qiang,Zhu Hong-kai,Liu Fei,Dong Chun-wang. 2014

[8]Land Cover Classification from Hyperspectral Images via Weighted Spatial–Spectral Joint Kernel Collaborative Representation Classifier. Rongchao Yang,Qingbo Zhou,Beilei Fan,Yuting Wang,Zhemin Li. 2023

[9]Land Cover Classification from Hyperspectral Images via Weighted Spatial-Spectral Kernel Collaborative Representation with Tikhonov Regularization. Rongchao Yang,Beilei Fan,Ren Wei,Yuting Wang,Qingbo Zhou. 2022

[10]Robustness and accuracy evaluation of moisture prediction model for black tea withering process using hyperspectral imaging. Ting An,Siyao Yu,Wenqian Huang,Guanglin Li,Xi Tian,Shuxiang Fan,Chunwang Dong,Chunjiang Zhao. 2022

[11]Nondestructive detection of adulterated wolfberry (Lycium Chinense) fruits based on hyperspectral imaging technology. Nirere, Adria,Sun, Jun,Kama, Rakhwe,Atindana, Vincent Akolbire,Nikubwimana, Felix Didier,Dusabe, Keza Dominique,Zhong, Yuhao. 2023

[12]The Quantified Analysis of Fresh Mutton Tenderness Using PLS Methods and Fourier Transform Near-Infrared Spectroscopy. Zhang De-quan,Li Chun-hong,Li Yong,Li Shu-rong,Li Qing-peng,Zhou Hong-jie,Chen Xiao-na,Zhang Bo-lin,Sun Su-qin. 2008

[13]Multi-element analysis for determining the geographical origin of mutton from different regions of China. Sun, Shumin,Guo, Boli,Wei, Yimin,Sun, Shumin,Fan, Mingtao.

[14]Phosphorylation inhibits the activity of mu-calpain at different incubation temperatures and Ca2+ concentrations in vitro. Du, Manting,Li, Xin,Li, Zheng,Li, Meng,Gao, Lingling,Zhang, Dequan,Du, Manting.

[15]Phosphorylation Inhibits The Activity Of M.u-Calpain At Different Incubation T emperatures And Ca2+ Concentrations In Vitro. Du, MT, Li, X, Li, Z, Li, M, Gao, LL, Zhang, DQ. 2017

[16]The Effect Of Dehydrogenase Enzyme A.ctivity In Glycolysis On T he Colour Stability Of Mutton During Postmortem Storage. Xin, JZ, Li, Z, Li, X, Li, M, Wang, L, Yang, FM, Zhang, DQ. 2017

[17]Effects Of Phosphorylation On The Activity Of Glycogen Phosphorylase In Mutton During Incubation At 4 Degrees C In Vitro. Bai, YQ, Li, X, Zhang, DQ, Chen, L, Hou, CL, Zheng, XC, Ren, C. 2020

[18]Comparison Of Protein Differences Between H.igh- And Low-Quality Goat A nd Bovine Parts Based On Itraq Technology. Wei, YC, Li, X, Zhang, DQ, Liu, YF. 2019

[19]Effects of mutton with different cooking methods on intestinal flora and metabolites in the elderly based on in vitro fermentation. Jianing Fu,Meizhen Xu,Shaobo Li,Li Chen,Dequan Zhang. 2025

[20]Analysis of bioactive substances in mutton and their effects on the quality of minced mutton. Cheng, Chengpeng,Xie, Xinru,Li, Shaobo,Chen, Pengyu,Huang, Caiyan,Zheng, Xiaochun,Chen, Li,Zhang, Dequan. 2025

作者其他论文 更多>>