Scalability of Hybrid Fuzzy C-Means Algorithm Based on Quantum-Behaved PSO

Abstract

A new hybrid fuzzy clustering algorithm that incorporates the fuzzy c-means (FCM) into the quantum-behaved particle swarm optimization (QPSO) algorithm is proposed in this paper (QPSO+FCM). The QPSO has less parameters and higher convergent capability of the global optimizing than particle swarm optimization algorithm (PSO). So the iteration algorithm is replaced by the QPSO based on the gradient descent of FCM, which makes the algorithm have a strong global searching capacity and avoids the local minimum problems of FCM and in a large degree avoids depending on the initialization values. This paper also investigates the ability of FCM algorithm, PSO+FCM algorithm and GA+FCM algorithm with Iris testing data and Wine testing data. The simulation result proves that compared with other algorithms, the new algorithm not only has the favorable convergence but also has been obviously improved the clustering effect.