USING PRINCIPAL COMPONENT ANALYSIS WITH A BACK-PROPAGATION NEURAL NETWORK TO PREDICT INDUSTRIAL BUILDING CONSTRUCTION DURATION

Authors

Sou-Sen Leu, Department of Civil and Construction Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, R.O.C
Chi-Min Liu, Construction Engineering division of Formosa Plastic Group, Tunhwa N. Rd., Songshan District, Taipei City, Taiwan, R.O.C.Follow

Abstract

Industrial businesses must respond efficiently to market demands; therefore, industrial construction must accurately predict the project duration at the pre-investment stage. In practice, project duration predictions rely on the experience of project managers. To provide impartial expertise and quantitative estimate the predicted duration of constructing an industrial building, an extensive history of industrial building cases were collected to form a database. Principal component analysis was applied to the database to identify key factors to serve as input data for a back-propagation neural network (BP-NN) that was used to estimate the project duration. Three prediction models were identified and developed separately based on the total cost for large, medium, and small construction projects. The derived BP-NN prediction models are applicable for estimating construction duration during the initial stages of a projec

Recommended Citation

Leu, Sou-Sen and Liu, Chi-Min (2016) "USING PRINCIPAL COMPONENT ANALYSIS WITH A BACK-PROPAGATION NEURAL NETWORK TO PREDICT INDUSTRIAL BUILDING CONSTRUCTION DURATION," Journal of Marine Science and Technology: Vol. 24: Iss. 2, Article 2.
DOI: 10.6119/JMST-015-0325-2
Available at: https://jmstt.ntou.edu.tw/journal/vol24/iss2/2