An Emotional Learning based Fuzzy Inference System (ELFIS) for improvement of the completion time of projects estimation

This study tries to examine the impacts of emotional learning based fuzzy inference system (ELFIS) on completion time of projects. For the project management team, on time delivery within budget is a fundamental and important factor that highlights the importance of estimating the completion time of a project during its execution. This study implies four soft computing methods which are artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), ELFIS and conventional regression to forecast the completion time of projects. Periodical time series for this study are generated by a progress generator program with typical resource constrained project scheduling (RCPS) problem projects library. Core variables in proposed model consist of known parameters in earned value management system which is SPI (schedule performance index), CPI (cost performance index) and AD (actual duration). Using ELFIS capability in modeling the expert emotion as appropriate emotional signal shows better performance compared with ANFIS, ANN and conventional regression.