欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
基于最小二乘支持向量机建模方法,提出应用奶茶在可见/近红外光谱谱区的有效波长进行其品种鉴别的新方法.用225个样本建模,75个样本进行预测.通过对光谱数据进行偏最小二乘法分析,根据载荷图和回归系数图选择鉴别奶茶品种的有效波长（EW）,并建立EW与最小二乘支持向量机（LS-SVM）相结合的EW-LS-SVM模型,同时与应用主成分（PC）和小波变换（WT）建立的PC-LS-SVM和WT-LS-SVM模型进行判别准确率的比较.结果表明,应用EW、PC和WT建立的模型对建模样本的判别准确率均为100%,对预测集样本判别准确率分别为98.7%、98.7%和100%,获得了理想的鉴别效果.研究表明,应用可见/近红外光谱谱区的有效波长进行奶茶品种鉴别是可行的,且EW-LS-SVM模型能获得满意的鉴别精度.
英文摘要：
Based on least squares-support vector machine （LS-SVM）,the effective wavelength （EW） in visible/near infrared （Vis/NIR） region was proposed as a new approach for the variety discrimination of instant milk teas. This method uses 225 milk tea samples for the calibration set,while 75 samples for the validation set. After partial least squares （PLS） analysis,the EWs were selected according to the X-loading weights and regression coefficients,and an EW-LS-SVM model was developed for the variety discrimination. The PC-LS-SVM model using principal components （PCs） and the WT-LS-SVM model using wavelet transform （WT） were built for comparison. The recognition ratios of calibrations using EW,PC and WT were all 100%,for the calibration set,while 98.7%,98.7% and 100% for the validation set,respectively. An excellent recognition ratio was achieved by these three models. It is feasible to use effective wavelengths in Vis/NIR region for the variety discrimination of instant milk teas and the EW-LS-SVM model can achieve a satisfying recognition ratio.
同期刊论文项目
同项目期刊论文
Study on the relationship between spectral properties of oilseed rape leaves and their chlorophyll c
Spectral characterization and N content prediction of soil with different particle size and moisture
Variation rules of the nitrogen content of the oilseed rape at growth stage using SPAD and visible-N
Determination of Protein Content of Auricularia auricula Using Near Infrared Spectroscopy Combined w
Application of Successive Projections Algorithm to Nondestructive Determination of Total Amino Acids
Application of image texture for the sorting of tea categories using multi-spectral imaging techniqu
Chlorophyll assessment and sensitive wavelength exploration for tea (Camellia sinensis) based on ref
Non-destructive discrimination of paddy seeds of different storage age based on Vis/NIR spectroscopy
Discriminating varieties of tea plant based on Vis/NIR spectral characteristics and using artificial
Detecting the quality of glycerol monolaurate: A method for using Fourier transform infrared spectro
Study on Application of Multi-Spectral Image Texture to Discriminating Rice Categories Based on Wave
期刊信息
位置：