Parallel neural-based hybrid data mining ensemble

This paper presents a novel hybrid data mining ensemble approach which is an effective combination of various clustering methods, in order to utilize the strengths of individual technique and compensate for each other’s weaknesses. The proposed approach is formulated to cluster extracted features into ‘soft’ clusters using unsupervised learning strategies and fuse the cluster decisions using parallel fusion in conjunction with a neural classifier. The proposed approach has been implemented and evaluated on the benchmark databases such as Digita lDatabase for Screening Mammograms, Wisconsin Breast Cancer and ECG Arrhythmia. A comparative performance analysis of the proposed hybrid data mining approach with other existing approaches is presented. The experimental results demonstrate the effectiveness of the proposed approach.