基于遗传和引导聚集算法优化支持向量机的白酒基酒品质评估方法  

Quality Evaluation Method for Base Baijiu Based on Support Vector Machine Optimized by Genetic and Bootstrap Aggregating Algorithm

作　　者：庞婷婷 张贵宇 刘科材 李晓平 庹先国 彭英杰 曾祥林 PANG Tingting;ZHANG Guiyu;LIU Kecai;LI Xiaoping;TUO Xianguo;PENG Yingjie;ZENG Xianglin(Artificial Intelligence Key Laboratory of Sichuan Province,Sichuan University of Science&Engineering,Yibin 644000,China;School of Automation and Information Engineering,Sichuan University of Science&Engineering,Yibin 644000,China;Liquor Making Biological Technology and Application of Key Laboratory of Sichuan Province,Sichuan University of Science&Engineering,Yibin 644000,China;Liquor Making Biotechnology and Intelligent Manufacturing of Key Laboratory of China National Light Industry,Sichuan University of Science&Engineering,Yibin 644000,China;Engineering Practice Center,Sichuan University of Science&Engineering,Yibin 644000,China;School of Computer Science and Engineering,Sichuan University of Science&Engineering,Yibin 644000,China)

机构地区：[1]四川轻化工大学人工智能四川省重点实验室,四川宜宾644000 [2]四川轻化工大学自动化与信息工程学院,四川宜宾644000 [3]四川轻化工大学酿酒生物技术及应用四川省重点实验室,四川宜宾644000 [4]四川轻化工大学中国轻工业酿酒生物技术及智能制造重点实验室,四川宜宾644000 [5]四川轻化工大学工程实践中心,四川宜宾644000 [6]四川轻化工大学计算机科学与工程学院,四川宜宾644000

出　　处：《食品科学》2025年第6期275-284,共10页Food Science

基　　金：酿酒生物技术及应用四川省重点实验室开放课题(NJ2022-06);劲酒产学研合作项目(HX2021041);四川轻化工大学“652”科研创新团队计划资助项目(SUSE652B005);中国轻工业酿酒生物技术及智能制造重点实验室开放基金项目(2023-01);五粮液产学研合作项目(CXY2022ZR007);企业信息化与物联网测控技术四川省高校重点实验室开放基金资助项目(2023WYY02)。

摘　　要：基酒组分具有复杂多样性,为提高其等级分类预测模型的精度和泛化能力,在基酒气相色谱-质谱数据基础上设计评价模型,提出一种结合遗传算法(genetic algorithm,GA)和引导聚集算法(Bootstrap aggregating,Bagging)优化支持向量机(support vector machine,SVM)分类器的方法,以解决单一SVM分类器在分类精度和泛化能力的不足。研究使用Spearman相关性筛选了36种关键物质,选择核主成分分析法提取了12个核主成分,并使累计贡献率达到96.06%,将其作为模型输入。选择性能最优的径向基核函数支持向量机,使用对数据多样性适应较强的并行计算Bagging集成算法,构建Bagging-SVM分类器进行基酒等级分类,最后,通过GA优化Bagging-SVM分类器的参数(C、γ、N),构建GA-Bagging-SVM模型。结果显示,GA-Bagging-SVM模型的准确率、精确度、召回率、F1-Score分别为96.77%、96.90%、96.77%、96.78%,优于Bagging-SVM和SVM模型,相比单一SVM模型提升了6.45%、5.61%、6.45%、6.42%,比Bagging-SVM模型提升了3.22%、2.29%、3.22%和3.15%。该方法可作为白酒基酒品质评估模型的优化方法。The chemical composition of base baijiu is complex and diverse.A classification model for base baijiu of different sensory grades was established based on the gas chromatography-mass spectrometric(GC-MS)data for their volatile composition. In order to improve the accuracy and generalization capacity of the classification model, a methodcombining genetic algorithm (GA) and bootstrap aggregating (Bagging) was proposed to optimize the support vectormachine (SVM) classifier. Using Spearman’s correlation analysis, 36 key substances were selected, and 12 kernel principalcomponents were extracted as input to the model by kernel principal component analysis, which together accounted for96.06% of the total variance. The radial basis kernel function support vector machine with the best performance was selected,and the parallel computing Bagging ensemble algorithm with strong adaptability to data diversity was used to construct aBagging-SVM classifier for base baijiu classification. Finally, GA was used to optimize the parameters (C, γ, and N) of theBagging-SVM classifier to construct a GA-Bagging-SVM model. The results showed that the accuracy, precision, recall rate,and F1-Score of the GA-Bagging-SVM model were 96.77%, 96.90%, 96.77%, and 96.78%, respectively, which were 6.45%,5.61%, 6.45%, and 6.42% higher than those of the SVM model, and 3.22%, 2.29%, 3.22%, and 3.15% higher than those ofthe Bagging-SVM model, respectively. This method can be used as an optimization method for the quality evaluation modelfor base baijiu.

关 键 词：基酒 支持向量机 引导聚集算法 遗传算法 分类预测 

分 类 号：TS261.4[轻工技术与工程—发酵工程]