Semi-supervised Affinity Propagation Clustering Algorithm Based on QPSO

The affinity propagation algorithm is a distance-based clustering algorithm, which has the advantages of fast clustering speed, high accuracy, and no need to specify the number of clusters. The quantum particles swarm optimization algorithm has powerful parameter optimization capabilities. In this paper, we use the quantum particles swarm optimization algorithm, named QPSO-SAP, to optimize the bias parameters. Experiments show that the improved AP algorithm improves the clustering performance significantly on complex structured data sets.