Study on a New RPCCL Clustering Algorithm

Based on further study on the existing RPCCL (rival penalized controlled competitive learning) algorithms and discovering some drawbacks, a new advanced RPCCL clustering algorithm is proposed. The new algorithm initializes the clustering centers according to the density of sample points, and the weights are updated according to the location of input data. The simulation results show that the new advanced algorithm can perform clustering more accurately and rapidly.

[1]  Erkki Oja,et al.  Rival penalized competitive learning for clustering analysis, RBF net, and curve detection , 1993, IEEE Trans. Neural Networks.

[2]  Lei Xu,et al.  Data smoothing regularization, multi-sets-learning, and problem solving strategies , 2003, Neural Networks.

[3]  Man Lan,et al.  Initialization of cluster refinement algorithms: a review and comparative study , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[4]  Yu-ming Cheung.  Rival penalization controlled competitive learning for data clustering with unknown cluster number , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[5]  Adam Krzyżak,et al.  Unsupervised and supervised classifications by rival penalized competitive learning , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[6]  N. Ansari,et al.  A novel algorithm to configure RBF networks , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).