基于连续投影算法的油菜蜜近红外光谱真伪鉴别的研究  被引量:2

Authenticity of Brassica honey based on liner successive project algorithm and near infrared spectroscopy

在线阅读下载全文

作  者:李水芳[1] 单杨[2] 尹永 周孜 

机构地区:[1]中南林业科技大学理学院,湖南长沙410004 [2]湖南省食品测试分析中心,湖南长沙410025 [3]湖南明园蜂业有限公司,湖南长沙410005

出  处:《食品工业科技》2012年第4期89-91,96,共4页Science and Technology of Food Industry

基  金:国家科技支撑计划项目(2009BADB9B07)

摘  要:采用连续投影算法(successive project algorithm,SPA)对177个不同产地油菜蜜样本的近红外光谱做波长选择,然后以33个特征变量作线性识别分析(LDA)。同时,也采用了主成分分析(PCA)对变量进行压缩。比较了二次识别分析(QDA)和簇类独立软模式分类法(SIMCA)的鉴别结果。SPA-LDA模型预测集的鉴别准确率为97.7%,而PCA-LDA、全谱的SIMCA和SPA-QDA预测集的正确率分别为93.2%、95.4%和90.9%;上述四种方法ROC曲线下的面积分别为0.964、0.912、0.948和0.933。SPA-LDA性能比其他三种方法要好。该方法准确、可靠,为蜂蜜真实性的现场快速检测提供了一种新方法。Near infrared spectroscopy combined with chemometrics methods were used to detect Brassica honey samples.For this purpose,successive project algorithm(SPA) was employed to choose thirty-three spectral variables,which were used as input of liner discriminative analysis(LDA) model.For comparison,principal components analysis(PCA) was used to compress the high-dimensional data.Quadratic discriminative analysis(QDA) and soft independent modeling of class analogy(SIMCA) were also employed to classify authentic and adulterated honey.The classification accuracy rates of SPA-LDA,PCA-LDA,SPA-QDA,and SIMCA were 97.7%,93.2%,90.9% and 95.4%,respectively.The area under receiver operation characteristic(ROC) curves of the above mentioned four methods could reach 0.964,0.912,0.933,and 0.948,respectively.The performance of SPA-LDA was better than other three methods.The results showed that SPA-LDA could be a useful means for detect adulterated honey owning to its rapid,accuracy,and generalization.

关 键 词:油菜蜜 近红外光谱 真伪鉴别 连续投影算法 线性识别分析 

分 类 号:TS207.3[轻工技术与工程—食品科学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象