论文部分内容阅读
We propose a novel clustering algorithm using fast global keel fuzzy c-means-F (FGKFCM-F), where F refers to keelized feature space. This algorithm proceeds in an incremental way to derive the near-optimal solution by solving all inter-mediate problems using keel-based fuzzy c-means-F (KFCM-F) as a local search procedure. Due to the incremental nature and the nonlinear properties inherited from KFCM-F, this algorithm overcomes the two shortcomings of fuzzy c-means (FCM):sen-sitivity to initialization and inability to use nonlinear separable data. An accelerating scheme is developed to reduce the compu-tational complexity without significantly affecting the solution quality. Experiments are carried out to test the proposed algorithm on a nonlinear artificial dataset and a real-world dataset of speech signals for consonant/vowel segmentation. Simulation results demonstrate the effectiveness of the proposed algorithm in improving clustering performance on both types of datasets.