
Journal of Software 2011
The Application of SOFM Fuzzy Neural Network in Project Cost EstimateDOI: 10.4304/jsw.6.8.14521459 Keywords: fuzzy neural network , selforganizing feature map , cost estimate Abstract: Applications of neural network were widely used in construct project cost estimate. Aim at handling weakness of poor convergence and insufficient forecast, an improved fuzzy neural network method based on SOFM (selforganizing feature map) was proposed to replace the fashionable TS fuzzy neural network. The method illustrated how to apply SOFM to improve the fault such as poor convergence and insufficient forecast. After optimizing of TS fuzzy neural network model, construct project cost estimate model had been built up. Finally, the model was set up with the purpose of comparing generalization ability by 18 examples and 2 testing samples. Comparing the simulation, a positive result was found that SOFM fuzzy neural network had a better performance in reducing the forecast error and iterating times than BP, and GABP. Therefore, this model is fit for handling construct project cost estimate.
