基于iPLS原理最优化信息区间的桃糖度组合权重PLS模型研究  

STUDY ON THE COMBINATION WEIGHT PLS MODEL FOR DETERMING SSC OF PEACH BASED ON THE OPTIMAL INFORMATION REGIONS OBTAINED FROM iPLS METHODS

作　　者：王加华[1] 李鹏飞[1] 曹楠宁[1] 韩东海[1] 

机构地区：[1]中国农业大学食品科学与营养工程学院,北京100083

出　　处：《红外与毫米波学报》2009年第5期386-391,共6页Journal of Infrared and Millimeter Waves

基　　金：国家自然科学基金(30571073);"十一五"国家科技支撑计划资助项目(2006BAD05A06-Z012)

摘　　要：采用反向区间偏最小二乘法和组合区间偏最小二乘法优化桃糖度可见/近红外光谱的信息区间组合,在选择的信息区间的基础上建立了一种线性组合权重PLS模型.对近红外光谱进行二阶导数处理、卷积平滑校正后,发现在区间分割数为15时筛选结果最优,BiPLS所选择的信息区间为742～770nm和862～920nm,SiPLS所选择的信息区间为742～770nm、832～860nm和892～920nm.直接组合信息区间BiPLS和SiPLS模型的RMSEP值分别为0.386和0.308,线性组合权重PLS模型的RMSEP值分别为0.351和0.364.结果说明在近红外定量分析中线性组合权重模型的建立克服了复杂样品各信息区间对PLS建模贡献率不一样的问题.Backward interval partial least squares （BiPLS） and synergy interval partial least squares （SiPLS） were proposed to search for an optimized combination of information spectral intervals about soluble solids content （SSC） from Vis/NIR spectra of peach. A linear combination weight PLS model was developed on the basis of the selected information intervals. The spectra were preprocessed by second-order derivative and Savitzky-Golay smoothing. It is found that the selected result is the best when the interval number is 15. The information intervals selected by BiPLS are 742770nm and 862920nm,while those selected by SiPLS are 742770nm,832860nm and 892920nm. For BiPLS and SiPLS models of direct combination intervals,the root mean square error of prediction （RMSEP） are 0.386 and 0.308,respectively. And for the PLS models of linear combination weight,the RMSEP are 0.351 and 0.364,respectively. The results reveal that the proposed method overcomes the difficulties that the different information intervals for the complicated samples have different contribution to PLS models. The metlod is very promising for vibrational spectroscopy and it gives much better prediction than the whole-spectrum PLS modeling.

关 键 词：可见/近红外光谱 区间偏最小二乘法 组合权重PLS模型 糖度 

分 类 号：O657.3[理学—分析化学] S123[理学—化学]