Arrhytmia classification using fuzzy-neuro generalized learning vector quantization

Automatic heart beats classification has attracted much interest for research recently and we are interested to determine the type of arrhythmia from electrocardiogram (ECG) signal automatically. This paper will discuss a new extension of GLVQ that employ fuzzy logic concept as the discriminant function in order to develop a robust algorithm and improve the classification performance. The overall classification system is comprised of three components including data preprocessing, feature extraction and classification. Data preprocessing related to how the initial data prepared, in this case, we cut the signal beat by beat using R peak as pivot point, while for the feature extraction, we used wavelet algorithm. The ECG signals were obtained from MIT-BIH arrhythmia database. Our experiment showed that our proposed method, FN-GLVQ, was able to increase the accuracy of classifier compared with original GLVQ that used euclidean distance. By using 10-Fold Cross Validation, the algorithm produced an average accuracy 93.36% and 95.52%, respectively for GLVQ and FNGLVQ.