Solving multi-objective functions for cancer treatment by using Metaheuristic Algorithms.

Abstract

In this context, we introduce a multi-objective optimization problem (MOOP) to simultaneously minimize the objectives of cancerous cells density as well as the approved drug amount in order to optimize the medical remedy of a tumor. The main aim is gaining a proper pattern for medical supervision to sick people with malignant cancer. To this end, a comparison is made between the two important and useful methods of non-dominated sorting genetic algorithm II (NSGA-II) and multi-objective particle swarm optimization (MOPSO). The gained Pareto's Curve here yields a series of optimal protocols. A desired optimal technique is then selected from these optimal protocols for drug supervision, relating to an under consideration criterion. The results show that in both criterions the convergence and expansion of Pareto optimal fronts of the performance of the NSGA-II method is better compared to MOPSO.