Generalized Regression Neural Nets in Estimating the High-Tech Equipment Project Cost

Author

Chou, Jui-Sheng ; Tai, Yian

Author_Institution

Nat. Taiwan Univ. of Sci. & Technol. (Taiwan Tech) Taipei, Taipei, Taiwan

Volume

2

fYear

2010

fDate

19-21 March 2010

Firstpage

281

Lastpage

284

Abstract

This study assesses the predictability of neural networks to estimate the cost of thin-film transistor liquid-crystal display (TFT-LCD) equipment. Newly completed equipment-development projects are provided by departments in a Taiwanese high-tech company. Cross-fold validation method is applied to measure model performance and reliability. Analytical results show the generalized regression neural net outperforms multi-layer feed-forward net when used for cost estimation during conceptual stages. Project managers can benefit from applying the approach to establish functional relationships for the high-tech TFT-LCD equipment manufacturing industry.

Keywords

costing; liquid crystal displays; multilayer perceptrons; production engineering computing; regression analysis; thin film transistors; cross fold validation method; equipment development projects; generalized regression neural nets; high tech equipment project cost estimation; multi layer feed forward net; neural networks predictability; thin film transistor liquid crystal display equipment cost estimation; Artificial intelligence; Costs; Fabrication; Manufacturing industries; Manufacturing processes; Neural networks; Predictive models; Project management; Semiconductor device manufacture; Thin film transistors; cost estimate; high-tech equipment; manufacturing; neural nets; project management;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Engineering and Applications (ICCEA), 2010 Second International Conference on

Conference_Location

Bali Island

Print_ISBN

978-1-4244-6079-3

Electronic_ISBN

978-1-4244-6080-9

Type

conf

DOI

10.1109/ICCEA.2010.206

Filename

5445656