| Title |
A Study on Model of Neural Networks Training by Genetic Algorithms for Predicting Cost Estimates of Apartment Projects at the Early Project Stage |
| Authors |
Kim Gwang-Hee ; Kang Kyung-In |
| Keywords |
신경망 ; 유전자 알고리즘 ; 공사비 예측신경망 ; 유전자 알고리즘 ; 공사비 예측 |
| Abstract |
The purpose of this study was to purpose a model of neural networks training by genetic algorithm for predicting preliminary cost estimates about apartment project at early project stage. In previous studies, neural network model is superior to the regression model in cost estimation, but has a problem that could be trapping local minima. Therefore, this study applied genetic algorithm?? train weights of neural networks. The result of the research revealed that training neural networks using genetic Algorithms is effective in estimating the preliminary costs of apartment projects at the early project stage. |