摘要
在VisualC++环境中采用面向对象技术,开发了PCA-MBP-NIR定量分析模型软件。通过40份小麦样品的原始光谱、加噪光谱(信噪比为14dB)与含水率所建立的PLS-NIR与PCA-MBP-NIR模型,对10份未知小麦样品的原始光谱、加噪光谱分别进行含水率的PLS-NIR与PCA-MBP-NIR预测分析。分析表明,对于含噪声的光谱,与PLS建模相比,使用PCA-MBP-NIR对未知样品预测结果具有更高的相关系数,更低的预测误差标准差。
An artificial neural network of matrix back propagation （MBP-ANN） combined with principal component analysis （PCA） for near infrared spectroscopy （NIR） quantitative analysis method is presented, and its principles is analyzed. A PCA-MBP-NIR quantitative analysis software system is developed based on object oriented programming technology in environment of Microsoft Visual C＋＋. The PCA-MBP-NIR model and partial least square（PLS） NIR model are built between the moisture and raw spectrum of 40 wheat samples, and the two models are also built for noise spectrum （r^max= 14 dB） in the same way. The moisture of 10 unknown wheat samples are predicted by this model. Results show that, using PCA-MBP-NIR method instead of PLS-NIR for noise spectrum, the correlation coefficient of predictied values and standard values of unknown samples can be increased, and the root mean square deviation （RMSD） can be decreased.
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2007年第1期108-111,共4页
Transactions of the Chinese Society for Agricultural Machinery
基金
国家自然科学基金资助项目(项目编号:30671198)
重庆市科委自然科学基金资助项目(项目编号:CSTC2005BB2211)
重庆市高等学校优秀青年骨干教师资助计划(2005)
关键词
农产品
品质检测
近红外光谱分析
主成分分析
人工神经网络
Agricultural product, Quality detection, Near infrared spectroscopy analysis, Principal component analysis, Artificial neural network
