关键词: 工程造价估算, 神经网络, 自组织特征映射, 建筑施工, 特征

Abstract: The traditional project cost estimation in architecture has many problems such as huge time-consumption, complicated calculation, and frequent measurement error. Therefore, a method of clustering which could deal with architecture samples by Self-Organizing Feature Map (SOFM) network was proposed. This method did not need to identify training data set manually to get classification from different sorts of samples, and it did help to improve the efficiency of the traditional architectural project cost estimation. Finally, the availability of the algorithm in this method was proved. Compared with the traditional methods, the experimental results demonstrate that the improved method has a higher accuracy rate and a lower false positive rate.

Key words: project cost estimation, neural network, SOFM, building construction, feature