Milk adulteration detection method based on Raman spectroscopy and spatiotemporal attention networks
Abstract
［Objective］ To enhance the milk adulteration detection accuracy.［Methods］ This study proposes a milk adulteration detection method by integrating Raman spectroscopy with a spatiotemporal attention network (STAN ).In the method,Raman spectroscopy is employed to extract molecular features,while STAN is applied to capture both temporal and spatial features,with a self -attention mechanism for further emphasizing critical information.［Results］ Compared with existing methods,the experimental method increases milk adulteration detection accuracy by an average of 4.5%,precision by about 5.8%,recall by 4.9%,and F1 score by 5.4%.［Conclusion］ The experimental method achieves high accuracy and robustness in milk adulteration detection,with strong potential for real -time detection and broad applicability.It can be utilized for online quality monitoring in milk production and regulatory processes and extended to adulteration detection in other foods.
Publication Date
6-13-2025
First Page
71
Last Page
76
DOI
10.13652/j.spjx.1003.5788.2025.60006
Recommended Citation
Yanmei, LIU; Baofeng, ZHAO; and Huilian, MA
(2025)
"Milk adulteration detection method based on Raman spectroscopy and spatiotemporal attention networks,"
Food and Machinery: Vol. 41:
Iss.
5, Article 10.
DOI: 10.13652/j.spjx.1003.5788.2025.60006
Available at:
https://www.ifoodmm.cn/journal/vol41/iss5/10
References
[1] 蒋莉莉,王悦欣.乳制品质量管理体系的优化研究 [J].中国检验检测,2024,32(5):141-144.JIANG L L,WANG Y X.Research on optimization of quality management system for dairy products [J].China Inspection Body & Laboratory,2024,32(5):141-144.
[2] 张振宇,崔海燕,王勇.动物源性食品中酰胺醇类药物残留检测研究进展 [J].食品与机械,2024,40(2):233-239.ZHANG Z Y,CUI H Y,WANG Y.Research progress in the detection of amide alcohol drugs in animal-origin foods [J].Food & Machinery,2024,40(2):233-239.
[3] 关佳琪,张方,杜宇萱,等.基于模糊认知图的乳制品质量安全风险形成机理研究 [J].中国乳业,2024 (3):71-76,82.GUAN J Q,ZHANG F,DU Y X,et al.Research on the formation mechanism of dairy product quality and safety risks based on fuzzy cognitive map [J].China Dairy,2024 (3):71-76,82.
[4] 王留留,孙方涛.表面增强拉曼光谱技术在食品安全检测领域中的应用 [J].食品与机械,2024,40(1):212-218.WANG L L,SUN F T.Application of surface-enhanced Raman spectroscopy in food safety detection [J].Food & Machinery,2024,40(1):212-218.
[5] XIA K,WU T X,ZHANG S W,et al.A new method for high-precision estimation of soil organic matter using two-dimensional correlation spectroscopy:to support collaborative use of global open soil spectral libraries [J].Geoderma,2024,445:116877.
[6] 陈燕雨.高光谱成像技术在食品掺假检测中的应用研究综述[J].食品安全导刊,2025 (3):144-147.CHEN Y Y.Review of the application of hyperspectral imaging technology in food adulteration detection [J].China Food Safety Magazine,2025 (3):144-147.
[7] 张微微,璩怡,王强,等.同步荧光光谱技术结合支持向量机对 掺 杂 牛 奶 智 能 判 别 研 究 [J].光 谱 学 与 光 谱 分 析,2024,44(9):2 428-2 433.ZHANG W W,QU Y,WANG Q,et al.Research on the synchronous fluorescence spectroscopy combined with support vector machines for intelligent discrimination of milk adulteration [J].Spectroscopy and Spectral Analysis,2024,44(9):2 428-2 433.
[8] 詹沙磊,江向东,叶永.基于 AI-HI 融合的突发食品污染事件风 险 管 理 [J/OL ].系 统 工 程 理 论 与 实 践.(2024 -05-16) [2025 -05-05].http://kns.cnki.net/kcms/detail/ 11.2267.n.20240515.1621.033.html.ZHAN S L,JIANG X D,YE Y.Risk management of food contamination events based on AI-HI integration [J/OL ].Systems Engineering-Theory & Practice.(2024 -05-16) [2025 -05-05].http://kns.cnki.net/kcms/detail/ 11.2267.n.20240515.1621.033.html.
[9] 刘洋硕,燕芳,李文文,等.基于卷积神经网络的三聚氰胺太赫兹光谱定量分析 [J].食品与机械,2024,40(11):41-46.LIU Y S,YAN F,LI W W,et al.Quantitative analysis of melamine in terahertz spectra based on convolutional neural network [J].Food & Machinery,2024,40(11):41-46.
[10] MHAPSEKAR R U,O'SHEA N,DAVY S,et al.Hybrid blended deep learning approach for milk quality analysis [J].IEEE Transactions on Emerging Topics in Computational Intelligence,2024,8(3):2 253-2 268.
[11] ZHONG J,SUN L,ZUO E G,et al.An ensemble of AHP-EW and AE-RNN for food safety risk early warning [J].PLoS One,2023,18(4):e0284144.
[12] MANIBABU V,GOMATHY M.Data quality management and risk assessment of dairy farming with feed behaviour analysis using big data analytics with YOLOv 51 algorithm [J/OL ].Research Square.(2024 -06-18) [2025 -01-22].https://doi.org/10.21203 /rs.3.rs-4519712 /v1.
[13] 杨国亮,余华声,夏金龙,等.融合自注意力和时空卷积网络的 空 气 质 量 预 测 方 法 [J].安 全 与 环 境 学 报,2023,23(12):4 580-4 589.YANG G L,YU H S,XIA J L,et al.Air quality prediction methods based on self-attention and spatiotemporal convolutional network [J].Journal of Safety and Environment,2023,23(12):4 580-4 589.
[14] 张建伟,陈旭,王叔洋,等.时空图神经网络在物联网中的应用综述 [J].计算机工程与应用,2025,61(5):43-54.ZHANG J W,CHEN X,WANG S Y,et al.Review of application of spatiotemporal graph neural networks in internet of things [J].Computer Engineering and Applications,2025,61(5):43-54.
[15] 张焕俊,戴臻,费洪晓.基于一维卷积神经网络结合便携式拉 曼 光 谱 特 级 初 榨 橄 榄 油 掺 假 定 量 分 析 [J].光 散 射 学 报,2024,36(4):436-444.ZHANG H J,DAI Z,FEI H X.Quantitative analysis of adulteration in extra virgin olive oil based on one-dimensional convolutional neural network portable Raman spectroscopy [J].The Journal of Light Scattering,2024,36(4):436-444.[16] 张雅茹,程碧瑶,杨博,等.基于机器学习的硝酸拉曼光谱定量分析方法 [J].探测与控制学报,2024,46(4):63-68.ZHANG Y R,CHENG B Y,YANG B,et al.Quantitative analysis of nitric acid using Raman spectroscopy based on machine learning [J].Journal of Detection & Control,2024,46(4):63-68.
[17] 刘庆珍,张溢,鄢仁武.基于拉曼光谱数据处理和谱峰识别的 变 压 器 油 绝 缘 老 化 研 究 [J].电 力 系 统 保 护 与 控 制,2024,52(8):158-166.LIU Q Z,ZHANG Y,YAN R W.Transformer oil insulation aging based on Raman spectral data processing and peak identification [J].Power System Protection and Control,2024,52(8):158-166.
[18] 范航舟,梅红岩,赵勤,等.融合双注意力机制的 GNN 多维时间序列预测 [J].智能系统学报,2024,19(5):1 277-1 286.FAN H D,MEI H Y,ZHAO Q,et al.Multivariate time series forecasting with a graph neural network and dual attention mechanism [J].CAAI Transactions on Intelligent Systems,2024,19(5):1 277-1 286.
[19] 向晓倩,陈璟.基于双重注意力时空图卷积网络的行人轨迹预测 [J].浙江大学学报 (工学版 ),2024,58(12):2 586-2 595.XIANG X Q,CHEN J.Pedestrian trajectory prediction based on dual-attention spatial-temporal graph convolutional network[J].Journal of Zhejiang University (Engineering Science ),2024,58(12):2 586-2 595.
[20] 肖琳,陈洪超,邹复民.基于多头注意力时空图神经网络的交 通 流 预 测 [J].重 庆 交 通 大 学 学 报 (自 然 科 学 版 ),2024,43(9):78-85.XIAO L,CHEN H C,ZOU F M.Traffic flow prediction based on multi-head attention spatiotemporal graph neural network[J].Journal of Chongqing Jiaotong University (Natural Science ),2024,43(9):78-85.