Information-Applied Technology in BP Neural Network Regression Algorithm with Feature Extraction Using Partial Least Squares

Xiao Hua Zhang; Hua Ping Li; Ke Qiao

doi:10.4028/www.scientific.net/AMR.952.299

Paper Titles

A Fuzzy PID Controller Design and Application
p.279

Research and Development of Automatic Control System for High Precision Cold Strip Rolling Mill
p.283

Mechanical Research with Intelligent Avatars for Robot Learning from Demonstration
p.287

The Design of Liquid Helium Temperature Zone Temperature Control System Based on G-M Refrigerator
p.291

Information-Applied Technology in BP Neural Network Regression Algorithm with Feature Extraction Using Partial Least Squares
p.299

Information-Applied Technology in Neural Network Prediction Model of Aviation Unsafe Event Based on PSO Algorithm with Gradient Acceleration
p.303

Information-Applied Technology with Nonlinear System Modeling Method of Elman Network Based on Particle Swarm Optimization
p.307

Research on Relevance Vector Machine Model Based on Kernel Partial Least Square in Properties of Engineering Materials
p.311

Applied-Information Technology in Stability and Existence of Solution for Functional Differential Equations with Impulses
p.315

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 952Information-Applied Technology in BP Neural...

Information-Applied Technology in BP Neural Network Regression Algorithm with Feature Extraction Using Partial Least Squares

Abstract:

A hybrid modeling algorithm based on partial least squares and neural network (BP algorithm) is proposed. First it extracts the feature from the original sample sets by partial least squares mehtod, and then the neural network regression using the extraction sets obtained is performed. Thus the hybrid modeling algorithm has the ability of feature extraction. The experiments results on the properties of engineering materials shows that the proposed hybrid algorithm can effectively modeling the properties of engineering materials with merits of dimensions reduction, elimination of noise and multiple correlations between independent variables.