文章摘要
引用本文:
基于近红外特征波长筛选对火麻油掺杂的快速检测
Fast Detecting the Adulteration of Hemp Seed Oil Based on Characteristic Wavelength Variable Optimization of NIR Spectroscopy
投稿时间:2017-05-02  修订日期:2017-07-08
DOI:
中文关键词: 近红外  特征波长  最小二乘支持向量机  连续投影法  竞争自适应重加权采样算法  
英文关键词: near-infrared spectroscopy  wavelength variable selection  least squares support vector machine  successive projections algorithm  competitive adaptive reweighted sampling
基金项目:科技部重点专项项目 (2016YFD0400202);国家自然科学基金(31571779);福建省科技厅计划项目(JA12032);福建省科技计划项目(82898324);福建省科技计划项目(2016S0042)
作者单位E-mail
李颖 福州大学生物科学与工程学院 635294279@qq.com 
陈元胜 福州大学生物科学与工程学院  
吕靓 福州大学生物科学与工程学院  
汪少芸 福州大学生物科学与工程学院  
王武 福州大学电气工程与自动化学院 wangwu@fzu.edu.cn 
付才力 福州大学生物科学与工程学院  
摘要点击次数: 53
全文下载次数: 
中文摘要:
      本文利用近红外光谱(near infrared spectrum,NIRs)技术对掺杂了大豆油、花生油、葵花籽油和玉米油的火麻油进行鉴定,结合偏最小二乘法(partial least squares,PLS)和最小二乘支持向量机(least squares support vector machine,LS-SVM)模型建立定量分析,并利用连续投影算法(successive projection algorithm,SPA)和竞争自适应重加权采样算法(competitive adaptive reweighted sampling,CARS)提取特征波长变量。结果表明,LS-SVM回归模型的准确度优于PLS模型,其预测相关系数(correlation coefficient of prediction,R2 p)分别达到0.9504、0.9058、0.8574和0.7673;SPA和CARS是两种有效的特征波长选择算法,能够提高模型的准确性,并且CARS效果优于SPA;其中,LS-SVM-CARS模型的R2 p分别达到0.9821、0.9075、0.9075和0.9249。因此,在油脂掺杂中,LS-SVM-CARS是一个准确度高、变量数少、传递性较强的模型,是一种快速检测油脂掺杂的定量分析模型。研究结果为近红外技术在检测食品品质方面提供一种有益的思路,并能在当前市场上油脂掺杂检测中产生实用价值。
英文摘要:
      In this paper, near-infrared spectroscopy (NIRs) was used to quantitative analyze the hemp seed oil adulterated with soybean oil, peanut oil, sunflower oil and corn oil. The partial least squares (PLS) and least squares support vector machine (LS-SVM) were applied to analyze NIRs, then the successive projection algorithm (SPA) and the competitive adaptive reweighted sampling (CARS) were used to extract the characteristic wavelength variables. The results showed that LS-SVM model was better than PLS mode. The wavelength variable optimization was satisfactory because that the correlation coefficient of prediction (R2 p) for hemp seed oil adulterated with soybean oil, peanut oil, sunflower oil and corn oil was 0.9504, 0.9058, 0.8574 and 0.7673, respectively. In addition, CARS showed better performance than SPA, and the accuracy of LS-SVM-CARS model was the most satisfied with R2 p of 0.9821, 0.9075, 0.9075 and 0.94249, respectively. So, the LS-SVM-CARS model is suitable to discriminate the oil adulteration due to its high accuracy, fewer variables and strong transitivity. The results provides a quantitative analysis model for oil adulteration and can be a promising method for the detection of food quality.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭