Automatic detection of ventricular and atrial premature contractions

Electrocardiogram (ECG) is a type of bioelectric signal obtained by the time-dependent recording of the electrical activity of the heart. Analysis and evaluation of ECG signals is one of the important methods used in the determination of heart diseases. In particular, it is frequently used to observe the amplitude and duration of waves on the ECG and define the conduction in the heart, and also, to detect patients with arrhythmia (rhythm disturbances). Since the interpretation of these signals is a time consuming and demanding process for physicians, detailed analysis and interpretation software that gives the same result as the diagnosis of the physician at high rates by interpreting these signals in the computer environment is being developed and its usage is increasing. The purpose of this study is to provide the convenience of to the physician by automatically detecting the Atrial Premature Complex and Ventricular Premature Complex, which are heart arrhythmias, in the computer environment. In this context, ECG signals were first taken from the MIT-BIH Arrhythmia database and the critical points P, Q, R, S, T on the signals were determined using time-frequency analysis methods. After then, QT, QTc, QTd analyzes, which is thought to be an information source in determining arrhythmia, Heart Rate Variability Spectral Analyzes in time and frequency domain was performed. In the last chapter of the study, Sinus Bradycardia and Sinus Tachycardia regions were determined according to the obtained results and were arrhythmia classification as Atrial Premature Complex, Ventricular Premature Complex and Sinus Sinus Rhythm using artificial neural networks.