This paper presents an innovative approach to the feature extraction for reliable heart rhythm
recognition. This classification of the system is comprised of three stages including data acquisition,
preprocessing, feature extraction and classification of ECG signals. The first step is Preprocessing of ECGs which
removes noise by using adaptive filters. Two different feature extraction methods are applied simultaneously to
obtain the feature vector of ECG data. The wavelet transform is used to extract the important coefficients of the
transform as the features of each ECG segment. Simultaneously, Enhanced Bat Algorithm is also applied to obtain
the temporal structures of ECG waveforms. Then the Adaptive Neuro Fuzzy Inference (ANFIS) is used to classify
different ECG heart rhythm. From computer simulations, the overall accuracy of classification for recognition of
ventricular arrhythmia heart rhythm types reaches 99.90%.
