摘要：The basic goal of project planning is to look into the future, identify the activities that need to be done to complete the project successfully and plan scheduling and resource allocation for these activities. Software effort estimation is the most important activity in project planning. So far many models are proposed by using machine learning algorithms, but no model is proved successful for efficiently and consistently predicting the effort. In this study we proposed two models using particle swarm optimization (PSO) with Constriction Factor for fine tuning of parameters of the constructive cost model (COCOMO) effort estimation. The models deals efficiently with imprecise and uncertain input and enhances the reliability of software effort estimation. The experimental part of the study illustrates the approach and contrast it with the standard numeric version of the COCOMO, standard singal variable models, Triangular Membership Function and Gbell function Models.
