Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Parameter Selection in Particle Swarm Optimization
EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Evolutionary Optimization Versus Particle Swarm Optimization: Philosophy and Performance Differences
EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Genetic learning for combinational logic design
Soft Computing - A Fusion of Foundations, Methodologies and Applications
Statistical exploratory analysis of genetic algorithms
IEEE Transactions on Evolutionary Computation
Hi-index | 0.00 |
This work analyzes the internal behavior of particle swarm optimization (PSO) algorithm when the complexity of the problem increased. The impact of number of dimensions for three well-known benchmark functions, DeJong, Rosenbrock and Rastrigin, were tested using PSO. A Problem-Specific Distance Function (PSDF) was defined to evaluate the fitness of individual solutions and test the diversity in neighboring individuals. The PSDF started with a large value, but converged to the optimum in few generations, irrespective of complexity of problem or objective benchmark function. The simulation illustrates that all parameters in any dimension behave in similar pattern and we can expect similar behavior for additional complexity in the problem.