A Quantum-inspired Particle Swarm Optimization K-means++ Clustering Algorithm

Abstract

Hybrid clustering algorithm that combine the swarm intelligence algorithm and K-means is widely used in clustering areas. Such as But, the hybrid particle swarm optimization clustering algorithm, the hybrid genetic clustering algorithm and ant colony algorithm. In which, the hybrid particle swarm optimization algorithm clustering algorithm may appear empty cluster in the iteration process, which will result in a bad clustering results. To improve this phenomenon, we combine the particle swarm algorithm with K-means++ (PSOK-means++), to some extent, which improve the clustering result. But, empty clusters may appear during the iteration of PSOK-means++, as a remedy, we introduce the empty-cluster-reassignment technique and use it to modify particle swarm optimization K-means++, resulting in a particle swarm optimization K-means++ clustering algorithm with empty cluster reassignment (EPSOK-means++). Furthermore, we combine the EPSOK-means++ with quantum computing theory, referred to as QEPSOK-means++ clustering algorithm. The experimental results show that QEPSOK-means++ is effective and promising.