检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]河南工业大学化学化工学院,河南郑州450001
出 处:《河南工业大学学报(自然科学版)》2015年第6期69-73,共5页Journal of Henan University of Technology:Natural Science Edition
基 金:河南工业大学创新基金(2014JCYJ08)
摘 要:应用近红外光谱分析技术,结合偏最小二乘辨别分析(PLS-DA)和支持向量机(SVM)两种模式识别方法用于5种食盐的品种追溯识别研究.将5种食盐250个样品分别在波长范围400-1 198 nm光谱条件下扫描并获取数据.从得到的每种食盐的光谱数据中随机选取34个样品利用SVM建立模型,用模型对其余16个样本进行预测,用网格寻优的方法选择最优参数,然后进行分类预测,5种食盐的准确识别率分别达到100%、93.8%、87.5%、100%和93.8%.通过PLSDA方法构建模型时采用二阶求导对近红外光谱数据进行预处理,并用留一法交互检验确定PLS模型的隐变量数,该模型对5种食盐的预测准确率分别达到93.75%、100%、100%、100%和100%,结果表明PLS-DA预测效果较SVM稍好.该研究为实现不同品种食盐的鉴定以及成品食盐的品种溯源提供了一种参考方法.The present study was to investigate the identification and traceability of salt material cultivar. Five kinds of salts,which cultivated from five regions,were discriminated by pattern recognitions methods. NIR spectra of 250 samples of 5 kinds of salt were scanned by a NIR spectrometer at the wavelength range of 400-1 1 98 nm. Thereafter,two pattern recognitions methods,partial least squares discriminant analysis(PLS-DA)and support vector machine(SVM) were used to classify the salt data sets. The spectral data of 34 samples were selected randomly as a model set,and the rest samples were validation set. Grid search technique was first used to search the optimal parameters. The final classification results of the SVM model of the five kinds of salt were100%,93.8%,87.5%,100% and 93.8%,respectively. PLS-DA was also used to discriminate the salt varieties.First the spectral data were preprocessed by the second derivative,and then Leave-One-Out cross validation was used to select the latent variables number for the PLS algorithm. The classification accuracy rates of five kinds of salt were 93.7%,100%,100%,100% and 100%,respectively. The ultimate result showed that PLS provided results of slightly better quality than SVM. It was concluded that NIR spectra coupling with chemometrics methodologies supplied a feasible method to identify the different varieties of salt.
分 类 号:TS207.3[轻工技术与工程—食品科学]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.60