近红外光谱技术检测石榴汁酸度的研究  

Study on determination of acidity in pomegranate juice by near infrared spectroscopy

作　　者：赵武奇[1] 石珂心[1] 谷月[1] 姜长松[2] 

机构地区：[1]陕西师范大学食品工程与营养科学学院,陕西西安710062 [2]吉林大学植物科学学院,吉林长春130062

出　　处：《食品工业科技》2014年第16期68-70,75,共4页Science and Technology of Food Industry

基　　金：陕西省自然科学基础研究计划项目(2011JM3011)

摘　　要：目的:研究石榴汁酸度的近红外光谱检测技术。方法:实验以不同产地的石榴汁样品为对象,对其近红外光谱数据进行预处理和通过主成分分析法提取光谱特征后,采用遗传算法(GA)对支持向量机(SVM)的三个参数进行优化,建立了石榴汁酸度近红外光谱检测的模型。结果:所建的模型对验证集预测的决定系数为0.9928,均方根误差(RMSE)为0.01359,模型预测性能良好。结论:近红外光谱技术能用于石榴汁酸度的定量检测。Objective .The technique for determination acidity of pomegranate juice was studied by using nearinfrared spectroscopy. Methods=Pomegranate juices from different origins were served as thesample. Preprocessing method of near infrared spectroscopy data was determined and the feature were extracted by principal components analysis. The three parameters of support vector machine （SVM） were optimized by genetic algorithms （GA）. The model for determination of acidity in pomegranate juice by near infrared spectroscopy was established. Results,The root mean squared error（RMSE） and the determination coefficients of the models for validation were 0.01359 and 0.9928 respectively. The model had a good prediction performance. Conclusion,Near-infrared spectroscopy technology could be used for the quantitative detection of pomegranate juice acidity.

关 键 词：近红外光谱 石榴汁 酸度 支持向量机 

分 类 号：TS255.1[轻工技术与工程—农产品加工及贮藏工程]