Proceedings of the 8th annual conference on Genetic and evolutionary computation
Particle swarm optimisation with spatial particle extension
CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
Division of labor in particle swarm optimisation
CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
Evolutionary programming made faster
IEEE Transactions on Evolutionary Computation
The particle swarm - explosion, stability, and convergence in amultidimensional complex space
IEEE Transactions on Evolutionary Computation
Evolutionary programming using mutations based on the Levy probability distribution
IEEE Transactions on Evolutionary Computation
Diversity in genetic programming: an analysis of measures and correlation with fitness
IEEE Transactions on Evolutionary Computation
Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients
IEEE Transactions on Evolutionary Computation
IEEE Transactions on Evolutionary Computation
| Hi-index | 12.05 |
The work and contribution of this study is not only to devise an improved PSO framework that is capable of wider search area and better fitness values, but also to realize a system that possesses the particle swarm intelligence via high diversity preserving and individual random walking. The purpose of this study is to interpret the processes of how to approach this framework, which consists of bilateral objective function (BOF) and random walking swarm intelligence (RW-PSO), and to provide the distinction from the current problems of PSO technique. Hence, this paper will present the ability of particles escaping from local optimum can be greatly improved because of the increase of exploration stage and scope and the global optimum can be obtained easily with the hybrid of BOF and RWSI, which may involve in searching for the solution from a more complicated test function. Subsequently, the results revealed the advantages of the proposed framework for improving the particle swarm optimization: (a) preserving the simple spirit of the conventional PSO; (b) achieving effective solutions for benchmark functions efficiently; (c) increasing no additional parameters to gain fitness improvement. Moreover, the superiority of the proposed framework has also been demonstrated the results via seven test functions defined to simulate some of complicated real-world problems and the better performance according to the experimental results with several benchmark functions.