Abstract :
In construction cost forecasting system, a great many uncertain factors effect the cost decision-making, so it is difficult to do effective forecasting by using traditional methods such as time series approach, regression analysis. In this paper, a nonlinear model based on RBF neural network is presented. There are some ameliorated measures in leaning algorithm of radial basis function (RBF) neural network. The number and the centric value of hidden layer are determined by using immune algorithm. The supervisory algorithm is taken as method of adjustable weight of output layer. Using above measures, the network is optimized, and the forecast model obtains the precise and objective solution. The construction cost forecasting model based on RBF neural network, realized the classification, analysed and forecasted the construction cost and realized the intellectualized management of construction project., which also provide the construction manager with better decision-making basis. After considering a number of uncertain factors, the result is more accurate. Moreover, the result of the experiment had indicated that the validity and superiority of the method of RBF neural network, comparing to artificial neural network (back propagation, BP). So it has broad application prospect in other fields.
Keywords :
artificial immune systems; construction; costing; decision making; project management; radial basis function networks; regression analysis; time series; construction cost forecasting; construction management; construction project; decision making; immune algorithm; intellectualized management; network optimization; nonlinear model; radial basis function neural network; regression analysis; supervisory algorithm; time series; Artificial neural networks; Costs; Decision making; Economic forecasting; Electronic mail; Multi-layer neural network; Neural networks; Predictive models; Regression analysis; Signal processing algorithms; BP; RBF; construction cost; forecasting; neural network;