Rapid Near-Infrared Detection of Base Baijiu Using Shapley Additive
Explanation Algorithm
ZHANG Gui-yu1, 2, 3, ZHANG Lei1, 2, 3*, TUO Xian-guo1, 3*, WANG Yi-bo1, 3, XIANG Xing-rui1, 3, YAN Jun1, 3
1. Artificial Intelligence Key Laboratory of Sichuan Province, Sichuan University of Science & Engineering, Yibin 644000, China
2. Liquor Making Biological Technology and Application of Key Laboratory of Sichuan Province, Yibin 644000, China
3. School of Automation & Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, China
Abstract：In current Baijiu extraction processes, the classification of base Baijiu grades is primarily performed using sensory evaluation, and the method is hampered by low detection efficiency and susceptibility to subjective influences. Therefore, near-infrared spectroscopy is applied to base Baijiu grade detection, and the feasibility of using the Shapley additive explanation (SHAP) algorithm from interpretable artificial intelligence for selecting characteristic spectral points is explored. It was found that when the number of features was 36, an accuracy of 97.08% was achieved by the LightGBM predictive model. To further improve model performance, a hybrid strategy combining interval partial least squares (iPLS) with SHAP was proposed, and an accuracy of 99.27% was achieved by the LightGBM model when the number of features was 9. Analysis of the spatial distribution of iPLS interval partitioning and SHAP contribution values indicated that the ranking of SHAP contributions does not strictly correspond to predictive performance. That model's performance can be improved by carefully designing feature selection strategies.
[1] Chen E, Yang F, Ma Z, et al. Journal of Food Composition and Analysis, 2024, 135: 106607.
[2] Wang Y, Xing L, He H J, et al. Food Chem X, 2024, 22: 101449.
[3] HUANG Qing-xia, FU Guo-yong, CHEN Li-ping(黄清霞，付国勇，陈黎萍). Science and Technology of Food Industry（食品工业科技）, 2022, 43(5): 310.
[4] LIU Jian-xue, YANG Guo-di, HAN Si-hai, et al（刘建学，杨国迪，韩四海，等）. Food Science（食品科学）, 2018, 39(2): 281.
[5] ZHANG Wei-wei, LIU Jian-xue, HAN Si-hai, et al（张卫卫，刘建学，韩四海，等）. Food Science（食品科学）, 2016, 37(6): 111.
[6] Zhang G Y, Tuo X G, Peng Y J, et al. Applied Sciences, 2024, 14(11): 4392.
[7] Li H B, Zhu L L, Li N, et al. Postharvest Biology and Technology, 2024, 218: 113201.
[8] Cruz-Tirado J P, Vieira M S S, Amigo J M, et al. Food Control, 2023, 153: 109969.
[9] Guo Z, Barimah A O, Shujat A, et al. LWT, 2020, 129: 109510.
[10] Xu Y H, Liu J M, Sun Y, et al. Science of The Total Environment, 2023, 857(Part 1): 159282.
[11] Liu Y C, Liu Z H, Luo X, et al. Biocybernetics and Biomedical Engineering, 2022, 42(3): 856.
[12] Effrosynidis D, Arampatzis A. Ecological Informatics, 2021, 61: 101224.
[13] Ahmed M T, Kamruzzaman M. Smart Agricultural Technology, 2024, 8: 100458.
[14] Huang J, Peng Y, Hu L. Expert Systems with Applications, 2024, 238(Part B): 121729.
[15] Wang J, Xu P C, Ji X, et al. Materials Today Communications, 2023, 37: 106910.
[16] Li Q X, Ji Y J, Zhu M R, et al. Applied Soft Computing, 2024, 155: 111426.
[17] Young H P. International Journal of Game Theory, 1985, 14(2): 65.
[18] Marcilio W E, Eler D M. From Explanations to Feature Selection: Assessing SHAP Values as Feature Selection Mechanism[C]. Proceedings of the 33rd SIBGRAPI Conference on Graphics, Patterns and Images, 2020：340.
[19] Lundberg S M, Lee S I. A Unified Approach to Interpreting Model Predictions[C]. Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS), 2017.
[20] Wang D, Thunéll S, Lindberg U, et al. Journal of Environmental Management, 2022, 301: 113941.
[21] Leardi R, Nørgaard L. Journal of Chemometrics, 2004, 18(11): 486.
[22] LIU Jian-xue, ZHANG Wei-wei, HAN Si-hai, et al（刘建学，张卫卫，韩四海，等）. Food Science（食品科学）, 2016, 37(4): 181.
[23] Fryer D, Strumke I, Nguyen H. IEEE Access, 2021, 9: 144352.
[24] Van Zyl C, Ye X M, Naidoo R. Applied Energy, 2024, 353(Part A): 122079.
[25] Workman J, Weyer L. Practical Guide to Interpretive Near-Infrared Spectroscopy. CRC Press, 2007.
[26] Harris N, Viejo C G, Barnes C, et al. Food Bioscience, 2023, 56: 103354.
