Abstract
Hyperbox classifiers have been investigated for the detection and classification of different types of heartbeats in the ECG, which is of major importance in the diagnosis of cardiac dysfunctions. In particular, the learning capacity and the classification ability for normal beats (N) and premature ventricular contractions (P VC) have been tested, with particular interest in the aspect Of the interpretability of the results. The MIT-BIH arrhythmia database has been used for testing and validating the proposed method A total of 26 morphology features have been extracted from ECG and reconstructed VCG signals. Three learning process have been tested combining the fuzzy clustering and the genetic algorithm for identifying the optimal hyperboxes and for testing a family of hyperellipsoid. The results showed that a limited number of hyperboxes increased the geometrical interpretability without a significant reduction of the accuracy.