电子测量与仪器学报

蒋薇薇,鲁昌华,张玉钧,汪济洲,鞠薇,肖明霞.基于SiPLS和SPA波长选择的玉米组分测量研究[J].电子测量与仪器学报,2017,31(12):1960-1966

基于SiPLS和SPA波长选择的玉米组分测量研究

Research on maize component measurement of wavelength selection based on SiPLS and SPA

DOI：10.13382/j.jemi.2017.12.012

英文关键词:interval partial least squares combined interval partial least squares continuous projection algorithm quantitative analysis

基金项目:国家重大科学仪器设备开发专项(2013YQ220643)资助

作者	单位
蒋薇薇	合肥工业大学计算机与信息学院合肥230009
鲁昌华	1. 合肥工业大学计算机与信息学院合肥230009； 2. 中国科学院合肥物质科学研究院合肥230031
张玉钧	中国科学院合肥物质科学研究院合肥230031
汪济洲	1. 合肥工业大学计算机与信息学院合肥230009；3. 合肥学院合肥230061
鞠薇	合肥工业大学计算机与信息学院合肥230009
肖明霞	合肥工业大学计算机与信息学院合肥230009

Author	Institution
Jiang Weiwei	School of Computer and Information, Hefei University of Technology, Hefei 230009, China
Lu Changhua	1. School of Computer and Information, Hefei University of Technology, Hefei 230009, China; 2. Anhui Institute of Optics Fine Mechanics, Chinese Academy of Sciences, Hefei 230031,China
Zhang Yujun	Anhui Institute of Optics Fine Mechanics, Chinese Academy of Sciences, Hefei 230031,China
Wang Jizhou	1. School of Computer and Information, Hefei University of Technology, Hefei 230009, China; 3. Hefei University, Hefei 230061, China
Ju Wei	School of Computer and Information, Hefei University of Technology, Hefei 230009, China
Xiao Mingxia	School of Computer and Information, Hefei University of Technology, Hefei 230009, China

摘要点击次数: 2531

全文下载次数: 7764

中文摘要:

研究分析80个玉米实验光谱数据，经预处理后，分别进行区间偏最小二乘(iPLS)、组合区间偏最小二乘法(SiPLS)和连续投影算法(SPA)优选玉米水分组分的最佳波长，建立校正模型。结果表明，iPLS、SiPLS和SPA将建模变量从700个分别降低到70、140和2个，各占据全光谱的10%、20%和0.29%，而其建模精度比700个全谱变量建模精度甚至更好。其中SiPLS和SPA的建模精度相当，但是SPA方法将建模变量从700个降低到2个，计算复杂度得到最大程度的降低，并保持了建模精度，表明SPA是一种有效的特征波长提取方法，且这一研究方法可推广应用到对玉米中油脂、蛋白质和淀粉的含量检测中。

英文摘要:

After pretreatment of 80 samples of maize, interval partial least square (iPLS), combination of interval partial least squares (SiPLS) and successive projections algorithm (SPA) is respectively used to optimize the best wavelength of moisture components, and the correction model is established. The results show that iPLS, SiPLS and SPA method reduces the modeling variables from 700 to 70, 140 and 2, respectively, which occupies 10%, 20% and 0.29% of the whole spectrum. And, the modeling accuracy is even better than that of the 700 full spectral variables. The modeling accuracy of SiPLS and SPA is matched. But the SPA method reduces variables from 700 to 2. The complexity is minimized, and the precision of the model is kept, which show that the SPA method is an effective feature extraction method of wavelength. This research method can be extended to the application of fat, protein and starch components detection of corn.

查看全文查看/发表评论下载PDF阅读器