Fuzzy clustering-based model for productivity forcasting

Forecasting productivity of construction operations is a difficult but crucial task in planning construction projects. Over the past decades, many models have been developed to forecast productivity for different construction operations. Models made up of several functional relations and controlled by a specific number of control rules are more in line with human reasoning and logic. Neural-Network-Driven Fuzzy Reasoning (NNDFR) structure as one of these models shows a great performance for modeling datasets among which clear clusters are recognizable. Lack of the compatibility of conventional NNDFR with fuzzy clustering algorithms besides the insufficient attention paid to the optimization of number of clusters in this model, created a potential area for further research. The main contribution of the proposed model is to develop a modified NNDFR system to model construction data. To this end, Fuzzy C-Means (FCM) algorithm is substituted for K-means in NNDFR structure, and its parameters such as the number of clusters and weighting exponent are optimized through genetic algorithm. The proposed model is further verified through simulation of a construction operation in which several qualitative and quantitative factors are considered. Its implementation to the case study shows a considerable improvement of model performance with lower Mean Squared Error (MSE). The developed model assists researchers and practitioners in utilizing historical construction data to forecast productivity of construction operations with a high accuracy that could not be obtained by traditional techniques.