NEURAL-NETWORK METHOD OF ESTIMATING CONSTRUCTION TECHNOLOGY ACCEPTABILITY

A neural network (NN) based approach is proposed for predicting the ad option potential or acceptability of a new construction technology. Th e acceptability of a technology for a target operation is defined as t he proportion of users that choose to use the technology in comparison to a conventional (base) technology. All existing alternative technol ogies for the considered operation are collected as samples for study. The performance characteristics of each sample technology are stored in a vector comprising eigenvalues determined by using the analytical hierarchy process (AHP) method, and its acceptability is determined us ing a poll. The obtained performance-acceptability pairs are used to t rain a neural network using the back-propagation algorithm. The traine d network can then be used to predict the acceptability of a new techn ology in question, given its performance attributes. Possible informat ion sources for training set construction and possible applications of the approach are discussed. An example estimate of the adoption prosp ect of a new concrete distribution system for concrete placement on a mid-rise building project is provided. Tests of the presented NN appro ach with simulated data show a promising result, especially when the p oll size used is sufficiently large.