Detection of premature ventricular contractions in ECG

This thesis focusses on the detection methods of extrasystoles from ECG and description of electrocardiogram, cardiac conduction system, extrasystoles and ventricular tachycardia. Extrasystoles are premature ventricular contraction caused by ectopic heartbeats. Classification is based on signal preprocessing, detection of R peak, the heartbeat segmentation, the feature description methods, normalization of features and the learning algorithms used. Selected and realized methods achieved classification accuracy ACC = 98 %, sensitivity SE = 100 % and specificity SP = 96,1 %. Gained features are also used for detection bundle branch block