Segmentation Ensemble - A Knowledge Reuse for Model Order Selection using Case-based Reasoning

• DOI: 10.5220/0004830102870295
• Publication Date: 2014-03-14T16:44:29Z
• Authors: Pakaket Wattuya; Ekkawut Rojsattarat
• Keywords: Robustness; Ensemble Learning; Ensemble forecasting

Cluster ensemble has emerged as a powerful technique for improving robustness, stability, and accuracy of clustering solutions. In this paper we present novel use cluster to handle another most difficult problem in data - model order selection. Each component is viewed an expert domain building the case-based reasoning. Our proposed method simple fast, but effective. Three simulations with different state-of-the-art segmentation algorithms are presented illustrate efficacy approach. We exten-sively evaluate our approach on large dataset comparison recent approaches determining number regions combination framework. Experiments demonstrate that can significantly reduce computational time required by existing methods, without loss accuracy. This contribution would make more feasible real-world applications.