Pereira, RenatoRodrigues, PedroBispo, Bruno C.2021-05-142021-05-142019http://hdl.handle.net/10400.14/33149This work proposes to analyze the capacity of several ECG features ofLead I to discriminate 28 pairs of study groups, combining 7 patholog-ical groups and 1 control group, presented in the PTB Diagnostic ECGDatabase. For each pair, it was achieved an accuracy between 66.7% and96.9% using feature selection algorithm and SVM classifiers.engEvaluation of lead i ECG features discriminant power for cardiac diseases identificationconference object