Influence of LPLS Algorithm Parameters on NIR Veracity
LI Jun-hui1,QIN Xi-yun2,ZHANG Wen-juan1,CAI Gui-min1,YANG Yu-hong2,ZHAO Long-lian1,CHANG Zhi-qiang1,ZHAO Li-li1,ZHANG Lu-da3
1. College of Information and Electrical Engineering, China Agricultural University, Beijing 100094, China 2. Yunnan Tobacco Science Research Institute, Yuxi 653100, China 3. College of Science, China Agricultural University, Beijing 100094, China
Abstract:The theory of local partial least square (LPLS) algorithm was described based on locally weighted regression algorithm(LWR). The influence of data processing parameters, such as principal component numbers and local set-up sample number in LPLS mode, on the NIR veracity was studied with homemade grating diffuse NIR instrument using Yunnan flue-cured tobacco. Results showed that for nicotine model, the principal component number decided by cross validation was not the best choice, and better results could be achieved by reducing the principal component number; using 30-50 samples to set up NIR model, the veracity of total sugar, total nitrogen, and nicotine could be improved by 7%, 14% and 10%, respectively. So, LPLS algorithm can effectively improve NIR model’s veracity, and is a good method to set up robust NIR models.
Key words:NIR;Flue-cured tobacco;Principal component;Local partial least square