CARS-SPA算法结合高光谱检测马铃薯还原糖含量

以竞争性重加权自适应选择算法(CARS)结合连续投影算法(SPA)选择马铃薯还原糖含量特征波长,共制备238个样本,比色法测定马铃薯还原糖含量,选择190个样本作校正集,48个样本作验证集,与全光谱和经典变量提取方法比较。结果表明,CARS-SPA算法筛选波段效果最佳,相比于全谱建模其参与建模波长点由203个减少到17个,模型验证集决定系数r~2由0.8464提高到0.8965,均方根误差(RMSEP)由0.0758降到0.0490。结果表明,采用CARS-SPA结合高光谱成像技术检测马铃薯还原糖含量结果可行。...

Full description

Saved in:
Bibliographic Details
Published in东北农业大学学报 Vol. 47; no. 2; pp. 88 - 95
Main Author 姜微 房俊龙 王树文 王润涛
Format Journal Article
LanguageChinese
Published 东北农业大学电气与信息学院,哈尔滨150030 2016
哈尔滨金融学院计算机系,哈尔滨150030%东北农业大学电气与信息学院,哈尔滨,150030
Subjects
Online AccessGet full text
ISSN1005-9369

Cover

More Information
Summary:以竞争性重加权自适应选择算法(CARS)结合连续投影算法(SPA)选择马铃薯还原糖含量特征波长,共制备238个样本,比色法测定马铃薯还原糖含量,选择190个样本作校正集,48个样本作验证集,与全光谱和经典变量提取方法比较。结果表明,CARS-SPA算法筛选波段效果最佳,相比于全谱建模其参与建模波长点由203个减少到17个,模型验证集决定系数r~2由0.8464提高到0.8965,均方根误差(RMSEP)由0.0758降到0.0490。结果表明,采用CARS-SPA结合高光谱成像技术检测马铃薯还原糖含量结果可行。
Bibliography:The paper used competitive adaptive reweighed sampling(CARS) and successive projections algorithm(SPA) to select the characteristic wavelength for detecting the reducing sugar content in potato. A total of 238 samples were prepared and the potato reducing sugar content was determined by colorimetry. Among them, 190 samples were selected as the calibration set and 48 samples as the validation set. The performance of CARS-SPA was compared with full spectrum and classical variable extraction methods. Results showed that the band screened by algorithm CARS-SPA had the best effect, compared to full spectrum modeling, the wavelength of the model reduced from 203 to 17, the model validation set coefficient r~2 increased from 0.8464 to 0.8965, and the root mean square error of prediction(RMSEP) decreased from 0.0758 to 0.0490. The results demonstrated that it was feasible to detect the reducing sugar content of potato using CARS-SPA combined with hyperspectral imaging.
23-1391/S
hyperspectral; CARS; SPA; potato; reduci
ISSN:1005-9369