Modeling Wood Crystallinity with Multiple Linear Regression

被引：0
|
作者：
Li, Yaoxiang [2 ]
Jiang, Lichun [1 ]
机构：
[1] Northeast Forestry Univ, Coll Forestry, Harbin, Heilongjiang, Peoples R China
[2] Northeast Forestry Univ, Coll Engn & Technol, Harbin, Heilongjiang, Peoples R China
来源：
MATERIALS ENGINEERING FOR ADVANCED TECHNOLOGIES, PTS 1 AND 2 | 2011年 / 480-481卷
关键词：
multiple linear regression; wood crystallinity; near infrared spectroscopy; NEAR-INFRARED SPECTROSCOPY;
D O I：
10.4028/www.scientific.net/KEM.480-481.550
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
The crystallinity of wood has an important effect on the physical, mechanical and chemical properties of cellulose fibers. Crystallinity of larch plantation wood was investigated with near infrared spectroscopy and multiple linear regression. Five typical wave lengths were selected to establish prediction model for wood crystallinity. Full-cross validation was applied to the model development. The model performance is satisfied with prediction correlation coefficient of 0.896 and bias of 0.0004. The results indicated that prediction of wood crystallinity with near infrared spectroscopy and multiple linear regression is feasible, which provides a fast and nondestructive method for wood crystallinity prediction.
引用
收藏
页码：550 / +
页数：2
相关论文
共 50 条
12345