作者: Ziyang Li , Panchi Li
DOI: 10.4236/OJAPPS.2015.56028
关键词: Data stream clustering 、 k-medians clustering 、 Algorithm 、 Cluster analysis 、 Mathematics 、 DBSCAN 、 CURE data clustering algorithm 、 Theoretical computer science 、 FLAME clustering 、 Canopy clustering algorithm 、 Correlation clustering
摘要: To enhance the clustering ability of self-organization network, this paper introduces a quantum inspired algorithm. First, samples and weight values in competitive layer are mapped to qubits on Bloch sphere, then, winning node is obtained by computing spherical distance between sample value. Finally, nodes its neighborhood updated rotating them sphere until convergence. The results IRIS show that proposed approach obviously superior classical network K-mean