数字农科院2.0

Fluorescence spectroscopy combined with a multi-task deep learning model for rapeseed oil quality analysis

文献类型: 外文期刊

作者: Xinna Jiang;Quancheng Liu;Xingda Cao;Fan Wang;Long Li;Lei Yan;Shuxiang Fan

作者机构:

关键词: CNN;Multi-task deep learning;Quantitative analysis;Rapeseed oil;SHAP values

期刊名称: Journal of Food Composition and Analysis

ISSN: 0889-1575

年卷期: 2025 年 146 卷

页码:

收录情况: SCIE(2025版)

摘要: This study aims to develop a non-destructive, multi-task deep learning model for the simultaneous prediction of multiple rapeseed oil quality indicators based on ultraviolet fluorescence spectroscopy. A novel multi-task convolutional neural network (MT-CNN) architecture was constructed, integrating multi-head attention and residual connections to enhance feature extraction and gradient propagation. Five common spectral preprocessing techniques were evaluated, with the combination of standard normal variate (SNV) and Savitzky–Golay (SG) filtering yielding optimal results. The proposed model was further interpreted using Shapley Additive Explanations (SHAP) to identify key wavelengths contributing to the prediction of acid value, peroxide value, α-tocopherol, and polyphenols. To comprehensively evaluate modeling performance, this study compared partial least squares regression (PLSR), K-nearest neighbors (KNN), support vector regression (SVR), long short-term memory (LSTM), and convolutional neural networks (CNN) under both single-task and multi-task learning frameworks. The results demonstrated that the MTDL model consistently outperformed all other models across all indicators, achieving an average correlation coefficient (R) of 0.9639. This study represents the first successful application of fluorescence spectroscopy with a multi-task deep learning model for rapeseed oil quality detection. This approach offers a rapid, accurate approach for simultaneous multi-parameter analysis of rapeseed oil constituents.

分类号:

  • 相关文献

[1]深度学习方法在作物遥感分类中的应用和挑战. 赵红伟,陈仲新,刘佳. 2020

[2]Unraveling almonds deterioration using whole-cell biosensor coupled with machine learning approaches and SHAP interpretation. Qianqian Li,Shengfan Chen,Jinhua Han,Bei Li,Lijun Wu,Jianxun Li. 2025

[3]Multi-Indicator Prediction of Kiwifruit Quality integrating Hyperspectral Analysis and WGAN-GP-MMoE Framework. 刘子涵,陈谦,李佳利,刘浩松,帅博宇,欧阳凌欢,卞子晗,王君怡,于家斌,钱建平. 2025

[4]Evaluation of five deep learning models for crop type mapping using sentinel-2 time series images with missing information. Hongwei Zhao,Sibo Duan,Jia Liu,Liang Sun,Louis Reymondin. 2021

[5]Image Classification of Wheat Rust Based on Ensemble Learning. Qian Pan,Maofang Gao,Pingbo Wu,Jingwen Yan,Mohamed A.E. AbdelRahman. 2022

[6]URSE-Net: a method of extraction winter wheat planting information based on multispectral remote sensing images. Zhou, Yuguang,Ma, Mingxu,Yang, Guang,Wang, Zeyu,Lai, Youchun,Liu, Haifan,Chen, Li,Wang, Mo. 2025

[7]Minor components and oxidative stability of cold-pressed oil from rapeseed cultivars in China. Yang, Mei,Zheng, Chang,Zhou, Qi,Huang, Fenghong,Liu, Changsheng,Wang, Hui. 2013

[8]Micronutrients-fortified rapeseed oil improves hepatic lipid accumulation and oxidative stress in rats fed a high-fat diet. Xu, Jiqu,Deng, Qianchun,Huang, Qingde,Yang, Jin'e,Huang, Fenghong,Xu, Jiqu,Deng, Qianchun,Huang, Qingde,Yang, Jin'e,Huang, Fenghong,Zhou, Xiaoqi,Gao, Hui,Chen, Chang,Ma, Jing,Wan, Zhengyang. 2013

[9]Influence of Microwave Treatment of Rapeseed on Minor Components Content and Oxidative Stability of Oil. Yang, Mei,Huang, Fenghong,Liu, Changsheng,Zheng, Chang,Zhou, Qi,Wang, Hui. 2013

[10]Changes in the content of canolol and total phenolics, oxidative stability of rapeseed oil during accelerated storage. Zheng, Chang,Yang, Mei,Zhou, Qi,Liu, Chang-Sheng,Huang, Feng-Hong,Zheng, Chang.

[11]Effects of endogenous and exogenous micronutrients in rapeseed oils on the antioxidant status and lipid profile in high-fat fed rats. Deng, Qianchun,Yu, Xiao,Xu, Jiqu,Huang, Fenghong,Huang, Qingde,Liu, Changsheng,Deng, Qianchun,Yu, Xiao,Xu, Jiqu,Huang, Fenghong,Huang, Qingde,Liu, Changsheng,Wang, Lan,Ma, Fangli. 2014

[12]Influence of Microwaves Treatment of Rapeseed on Phenolic Compounds and Canolol Content. Yang, Mei,Zheng, Chang,Zhou, Qi,Liu, Changsheng,Li, Wenlin,Huang, Fenghong,Yang, Mei,Zheng, Chang,Zhou, Qi,Liu, Changsheng,Li, Wenlin.

[13]Rapeseed oil fortified with micronutrients reduces atherosclerosis risk factors in rats fed a high-fat diet. Xu, Jiqu,Deng, Qianchun,Huang, Qingde,Yang, Jin'e,Huang, Fenghong,Zhou, Xiaoqi. 2011

[14]Effect of rapeseed oil and beta-cyclodextrin coatings on the quality of eggs in shell. Dai, Yan,Chen, De-hui,Lei, Qin,Ren, Xiao-li,Li, Chun-hong,Zhang, Jing,Chang, Hai-jun. 2023

[15]Inhibitory effects and mechanisms of phenolic compounds in rapeseed oil on advanced glycation end product formation in chemical and cellular models in vitro. Huihui Liu,Ruiying Zhang,Wen Wang,Xiaoyang Xia,Zhenxia Xu,Xia Xiang. 2024

[16]Enzymatic Deacidification and Aroma Characteristics Analysis of Rapeseed Oil Using Self-Made Immobilized Lipase CALB@MCM-41-C8. Zhonghui Liu,Tieliang Liu,Run Liu,Qi Zhou,Yandaizi Zhou,Yi Zhang,Mingming Zheng. 2024

[17]Flavor Profile of 4-Isothiocyanato-1-butene in Microwave Rapeseed Oil and Its Anti-Inflammatory Properties In Vitro. Xiang, Xia,Liu, Huihui,Zheng, Chang,Jiang, Nanjie,Huang, Fenghong,Zhou, Qi. 2025

[18]Comprehensive analysis of phenolic profile, their antioxidant activities, and physicochemical characteristics of rapeseed oil under various microwave and storage conditions. Yao Zhang,Zhixian Xiang,Rong Xia,Wenxi Chen,Xin Zhang,Hongting Lei,Fang Wei,Yongjun Yuan. 2025

[19]Relationship Between Rapeseed Oil Intake and Inflammatory Cytokines: Results from NHANES 2003-2006 and Mendelian Randomization. Duan, Xiaorui,Xu, Yaxi,Chen, Ze. 2025

[20]Simultaneous quantification of six major triterpenoid saponins in Schefflera kwangsiensis using high-performance liquid chromatography coupled to orbitrap mass spectrometry. Zhang, Leilei,Zhang, Leilei,Wang, Yan,Yu, De-Quan,Wang, Yan,Yu, De-Quan,Wang, Yan.

作者其他论文 更多>>