Title :
Comparison of Density Forecasting Methods for Wood Growth Ring
Author :
Guangsheng Chen ; Li Ge
Author_Institution :
Coll. of Mater. Sci. & Eng., Northeast Forestry Univ., Harbin, China
Abstract :
The survival and development of human being are seriously threatened by the decrease of nature forest in all over the world. As a result, it has been widely focused on the intensive farming of plantation and scientific utilization of wood resource. The characteristics of regression analysis method, time series method and neural network method commonly used in wood quality forecast were analyzed. The modeling process and result of these forecasting methods were presented in terms of the density forecast of wood growth ring in this paper. The forecasting precisions were compared, and results indicated neural network method is the best method for wood quality forecast.
Keywords :
farming; forecasting theory; neural nets; regression analysis; time series; wood; density forecasting method; neural network method; regression analysis method; time series method; wood growth ring; wood resource utilization; Accuracy; Artificial neural networks; Fluctuations; Forecasting; Predictive models; Regression analysis; Time series analysis;
Conference_Titel :
Database Technology and Applications (DBTA), 2010 2nd International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-6975-8
Electronic_ISBN :
978-1-4244-6977-2
DOI :
10.1109/DBTA.2010.5658956
