Neuro-fuzzy models for constructability analysis

SUBMITTED: February 2004
REVISED: April 2004
PUBLISHED: May 2004
EDITOR: B.-C. Björk

S V Barai, Assistant Professor
Department of Civil Engineering, Indian Institute of Technology, India
email: skbarai@civil.iitkgp.ernet.in http://barai.sudhir.tripod.com

Rajeev S Nair, Former post graduate scholar
Department of Civil Engineering, Indian Institute of Technology, India

SUMMARY:With the emergence of the new computer science areas of artificial intelligence and neural networks, researchers have applied them in the construction industry successfully. This paper presents comparative studies of two machine learning models namely backpropagation (BP) and Fuzzy ARTMAP based neuro-fuzzy models for handling qualitative fuzzy information of constructability evaluation. These models not only perform like traditional machine algorithms, but also handle missing information with better accuracy. Performance evaluation of the network has been carried out using traditional statistical tests. From the study, it was found that the Fuzzy ARTMAP model performs much better than the BP model.

KEYWORDS: constructability, fuzzy logic, neural networks

FULL TEXT: file.pdf (223,129 bytes)

CITATION:

Barai S V and Nair R S (2004) Neuro-fuzzy models for constructability analysis, ITcon Vol. 9, pg. 65-73, http://www.itcon.org/2004/4