Output details

Clustering-Based Leaders’ Selection in Multi-Objective Particle Swarm Optimisation

The originality is in implementing a mapping between the objective and solution spaces based on spatial clustering. The most significant outcome of this research is the utilization of representation properties of potential solutions, which enabled a better exploration of the solution space without resorting to heavier computation. The rigour of performance evaluation was achieved by comparing the developed algorithm with alternative implementations and achieving either superior or comparable. The idea was later explored in the context of complex network clustering (DOI: 10.1109/TEVC.2013.2260862). This paper appears in the proceedings of a well-established international conference on data engineering and machine learning..