Title :
Neural network modeling study of one dimension gray problem GNNM (1, 1)
Author :
Song, Huazhu ; Han, Bo
Author_Institution :
Dept. of Comput. Sci., Wuhan Univ. of Technol., China
Abstract :
The study on representing and processing uncertain information is an important subject in information era. This paper combines gray system with neural network in processing one dimension gray problem, which is common in practice. Based on analyzing the feature of gray system and neural network, the initial model is discussed at first. The gray neural network model GNNM (1, 1) is given after improving the initial model including its theory, gray neural network model GNNM (1, 1) and the learning algorithm. In addition, GNNM (1, 1) is applied in a sample of material science to forecast the abrasion rate and it has proved GNNM (1, 1) is feasible and correct which is much better than tradition methods
Keywords :
grey systems; learning (artificial intelligence); neural nets; 1D gray problem; GNNM (1,1); abrasion rate forecasting; gray neural network model; material science; uncertain information processing; uncertain information representation; Cities and towns; Computer science; Differential equations; Economic forecasting; Eigenvalues and eigenfunctions; Information representation; Materials science and technology; Neural networks; Predictive models; Time factors;
Conference_Titel :
Info-tech and Info-net, 2001. Proceedings. ICII 2001 - Beijing. 2001 International Conferences on
Conference_Location :
Beijing
Print_ISBN :
0-7803-7010-4
DOI :
10.1109/ICII.2001.983105