Open Access Open Access  Restricted Access Subscription or Fee Access

A Prediction Model of Pigment Formulation for Wood Dyeing based on Improved RBF Neural Network

Xuemei Guan, Minghui Guo

Abstract



Since RBF neural network is likely to converge to local minimum and has low learning efficiency, we proposed an improved neural network in this paper. Our proposed network transmit the output of the hidden node to its input, which take both hidden layer output and input layer output as the input of the hidden layer. The new network can do more precisely training and reduce network error. What more, we also proposed a simplified identification method based on central point and radial niche width to solve the problem of the huge calculation in improved network. We use the softwood (Pinus Sylvestris) as our research subject, considered tristimulus values before dyeing as network input and tristimulus values after dyeing as network output, and then established models using the improved algorithm. Result shows that the improved model could obviously accelerated prediction speed and modified generalization ability.


Keywords


Model for Pigment Formulation, Improved RBF Neural Network, Hidden Node Feedback.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.