A multiple-classifier architecture for ECG beat classification

We investigate the use of the modular architecture of multiple clustering based pattern classifiers for ECG beat classification using the MIT/BIH arrhythmia database. The feature space is divided into several regions and individual classifiers are developed for each region separately. Then the outputs of these classifiers are combined using two competing combination rules: a winner decides all method and a distance-based combination method. Experiment results indicated that multiple classifier approach yields better sensitivity and classification rate.