A soft computing based multi-objective optimization approach for automatic prediction of software cost models

This paper tries to extend the idea of single-objective differential evolution (DE) algorithm to a multi-objective algorithm. Most of the existing algorithms face the problem of diversity loss and convergence rate. In this paper, we propose a novel multi-objective DE algorithm to deal with this problem. In the validation process, the proposed method is validated in two steps. Firstly, the new homeostasis factor-based mutation operator incorporates multi-objective differential evolution algorithms (MODE). In this method, we use the Pareto optimality principle. We incorporate a new adaptive-based mutation operator (MODE) to create more diversity and enhance convergence rate among candidate solutions which provide better solutions to help the evolution. The effectiveness of the proposed method is evaluated on eight benchmarks of bi-objective and tri-objective test functions. Our proposed method performed well compared to the latest variants of multi-objective evolutionary algorithms (MOEAs). Secondly, the proposed method is used for an application-based test by applying it for software cost estimation. This method also incorporates multi-objective parameters, i.e., two objectives-based software cost estimation and three objectives-based software cost estimation. The proposed approach achieves better results in most software projects in terms of reducing effort and minimum error.