-120
2016 Vol.35 No.1 Serial No.287
China Brewing
Innovation and Knowledge Transfer
遗传算法联合LS-SVM的果原醋成分定量分析
李子文12熊雅婷王健*李宗朋张海红”冯斯麦尹建军
（1.中国食品发酵工业研究院北京1000152.宁夏大学农学院食品科学系宁夏银川750021）
摘要利用近红外光谱技术对苹果原醋中的重要指标进行定量分析,并进行模型优化以提高性能。采用遗传偏最小二乘法外定量模型,并与建立的偏最小二乘(PLS)模型结果进行比较。用决定系数(R")、预测均方根误差(RMSEP)以及相对分析误差(RPD)对模型进行评价确定最佳建模方法。结果表明相比于PLS模型总酸及可溶性固形物指标的LS-SVM定量模型的R、 RMSEP以及RPD值均有更好的表现且在进行独立测试集验证时,LS-SVM模型的预测精度也明显优于PLS模型。说明速传算法
联合LS-SVM建立的定量模型有很高的准确度及稳定性,可以应用于苹果原醋总酸和可溶性固形物含量的快速检测关键词萍果原醋近红外光谱技术最小二票支持向量机遗传算法波段筛选
中图分类号：TS261.7
文章编号.0254-5071(2016)01-0120-05
doi:10.11882/j.issn.02545071.2016.01.026
Quantitative analysis of apple vinegar compositions based on genetic algorithm combined with LS-SVM
LI Ziwen'2, XIONG Yating', WANG Jian'*, LI Zongpeng', ZHANG Haihong*, FENG Siwen', YIN Jianjun
(I1.China National Research Institute of Food & Fermentation Industries, Bejing I00015, China, 2.Department of Food Science, College of Agriculture, Ningxia University, Yinchuan 750021, Chinaj
Abstract: The compositions of apple vinegar were analyzed quantitatively by near infrared spectroscopy technology, and the model was optimized to improve the performance. The characteristic wavelengths extracted by genetic algorithm partial least squares (GA-PLS) as least squares support vector machines (LS-SVM) of the input variables, NIR quantitative models of total acid and soluble solid in apple original vinegar were established, and the models were compared with partial least squares (PLS) model results. The established models were evaluated using R*, RMSEP and RPD to detemine the optimum modeling method. The results showed that R, RMSEP, RPD and prediction accuracy in independent test set of LS-SVM quantitative model of total acid and soluble solid had better perfomance than PLS models. The quantitative model established by genetic algorithm combined
with LS-SVM had high accuracy and stability. It could be used in the rapid detection of total acid and soluble solids content in the apple vinegar. Key words: apple vinegar; near infrared spectroscopy; LS-SVM; genetic algorithm; band selection
苹果原醋发酵是苹果醋饮料生产过程的重要环节，以苹果原醋为原料可调配形成苹果原醋饮料,即为日常所讲的“苹果醋”。但由于我国在苹果醋生产方面还远不如生产粮食醋般成熟和完善加上自前还没有苹果原醋生产的统一标准致使市场上苹果醋饮料鱼目混杂，有的甚至是用糖精、醋精等调配而成而苹果原醋发酵直接影响苹果醋的品质生产因此对于苹果原醋的质量监控需要引起高度重视。而原醋中的总酸及可溶性固形物等主要成分含量是微量平果原醋品质的重要指标自前常规的检测过程复杂耗时无法满足苹果醋饮料生产过程中品质快速检测的需求
近红外光谱分析技术是一种新兴的绿色检测技术，具有无需样品前处理、分析速度快、分析效率高、操作简
收稿日期2015-10-09
基金项目科技部科研院所技术开发研究专项(2013EG111212)
单、易于实现生产过程中的在线控制等优点口近年来在食醋及果醋安全检测等方面得到了广泛应用邹小波等3 的研究表明近红外光谱与食醋总酸含量呈非线性关系，采用最小二乘支持向量机(leastsquares-supportvectorma-chineLS-SVM)建立的模型预测性能良好有很高的预测精度。LIUF等利用连续投影算法结合最小二乘支持向量机等方法实现了不同浓度梅子醋中醋酸、酒石酸和乳酸等指标的快速检测。石吉勇等采用模拟退火算法优化并结合偏最小二乘法(partialleastsquaresPLS)建立的模型能够快速预测食醋中总酸指标含量。但是,目前对于苹果醋中各项指标的近红外研究分析仍较为少见尤其是针对于苹果原醋的研究更是未见报道
本研究拟采用遗传偏最小二乘法（geneticalgorithms
作者简介李子文(1992-）男士研究生研究方向为农产品无损检测
*通讯作者王健(1973-），男高级工程师，博士研究方向为农产品无损检测
?1994-2017 China Academic Journal Electronic Publishing House, All rights reserved.
http://ww.cnki.net