A Comprehensive Evaluation Method Based on PCA and BP Neural Network

Author

Xie, Xiaodan ; Xia, Bin ; Yu, Jun

Author_Institution

Sci. & Technol. on Opt. Radiat. Lab., Beijing, China

fYear

2012

fDate

24-25 July 2012

Firstpage

71

Lastpage

74

Abstract

Comprehensive evaluation is the base of modern management and the tool of evaluating research object, and it is now widely used. Methods of evaluation decide the evaluation result. There are a few of methods which can be divided to two kinds: subjective methods and objective methods, these two kinds have their advantages and defects. In this paper, we proposed a method based on Principle Component Analysis (PCA) and BP neural network. PCA is a kind of subjective evaluation method. We combine the result of PCA and expert by training BP neural network. The network implies result of PCA and expert knowledge and can be used to evaluate.

Keywords

backpropagation; business data processing; management; neural nets; principal component analysis; BP neural network; PCA; backpropagation; comprehensive evaluation method; evaluation method; management evaluation; neural network training; objective method; principle component analysis; subjective method; Biological neural networks; Indexes; Laboratories; Neurons; Principal component analysis; Training; BP neural network; PCA; comprehensive evaluation; numerical analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Computing Science (ICIC), 2012 Fifth International Conference on

Conference_Location

Liverpool

ISSN

2160-7443

Print_ISBN

978-1-4673-1985-0

Type

conf

DOI

10.1109/ICIC.2012.3

Filename

6258074