摘要
大多数短波CCD硅检测器为2 048或3 648像元,相邻波长间隔小,预处理算法对其适用性差。本文在600.09～980.47 nm光谱范围内,采用等间隔抽取方法重构光谱矩阵。经不同光谱预处理后,分别采用遗传算法(GA)和连续投影算法(SPA),筛选偏最小二乘法(PLS)建模变量。采用留一法交叉验证评价模型的预测能力,经比较,SPA筛选变量建立的PLS模型的预测效果最优,南丰蜜桔可溶性固形物、总酸和维生素C的PLS模型交叉验证标准差分别为0.661°Brix,0.067%和2.91 mg.(100 g)-1。结果表明光谱抽取结合SPA的变量筛选方法可提高南丰蜜桔品质可见近红外光谱模型的预测能力。
The pixels were 2 048 or 3 648 for the most Si charge coupled device dector. The interval between the adjacent wavelengths was few. The pretreatment could not deal with the spectra well. Spectral matrix was reconstructed by equal interval extraction in the wavelength range of 600.09~980.47nm. The variables for developing partial least squares （PLS） models were chosen by genetic algorithm （GA） and successive projections algorithm （SPA） from the pretreatment spectra. The models＇ predictive ability was evaluated by leave-one-out cross validation. By comparison, the best results were obtained by the SPA-PLS models. The standard errors of cross validation （SECV） were 0. 661°Brix, 0. 067% and 2. 91mg ·（100 g）^-1 for soluble solids, total adieity and vitamin C, respectively. The results suggested that the predictive ability can he improved by equal interval extraction method and SPA for determinating the quality of Nanfeng mandarin fruits.
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2011年第9期2399-2402,共4页
Spectroscopy and Spectral Analysis
基金
国家科技支撑计划项目(2008BAD96B04)
江西省对外科技合作计划项目(2009BHB15200)
江西省主要学科学术和技术带头人培养对象计划项目(2009DD00700)资助
关键词
可见近红外
光谱抽取
连续投影
南丰蜜桔
Visible-NIR
Spectra extraction
Successive projections algorithm
Nanfeng mandari
