DocumentCode :
2387490
Title :
Improved Algorithm of BP Neural Network and its Application to Prediction of K/S Value in Dyeing with Reactive Dyes
Author :
Jiang, HuiYu ; Dong, Min ; Li, XiangPeng ; Yang, Feng
Author_Institution :
Wuhan Univ. of Sci. & Eng., Wuhan
fYear :
2007
fDate :
2-4 Nov. 2007
Firstpage :
534
Lastpage :
534
Abstract :
Traditional algorithm of BP neural network has been mended and an improved predictive model using L-M method has been carried out to calculate the K/S values in dyeing with reactive dyes in this article. The results showed L-M method is superior in the prediction by comparing traditional and improved algorithm. Shorter predictive time and higher predictive veracity were obtained in the later.
Keywords :
backpropagation; dyeing; dyes; neural nets; production engineering computing; BP neural network; K/S value; predictive model; predictive time; reactive dyes; Biological system modeling; Chemical engineering; Computer networks; Convergence; Educational institutions; Jacobian matrices; Neural networks; Neurons; Newton method; Optimization methods;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Granular Computing, 2007. GRC 2007. IEEE International Conference on
Conference_Location :
Fremont, CA
Print_ISBN :
978-0-7695-3032-1
Type :
conf
DOI :
10.1109/GrC.2007.25
Filename :
4403156
Link To Document :
بازگشت