|
|
Deep-learning based localization of cardiac arrhythimas in ECG
Khaliullina, Sabina ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
The thesis deals with the localization and classification of atrial atrial fibrillation. In Python, a detection method using convolutional neural networks with multi-instance learning (MIL) and the method of local maxima for localization were implemented. Segments from two ECG leads were used. In the binary classification using the first subset and subsequent post processing, the F1 score reached 100 %, in the classification using the second subset 92 %. In the discussion and conclusion of the work, the success of classification and localization was evaluated, the achieved results were discussed and compared the with the results of other authors.
|
|
|
Detection of ventricular arrhythmia in long-term ECG signals
Khaliullina, Sabina ; Smital, Lukáš (referee) ; Maršánová, Lucie (advisor)
Detection of premature ventricular contraction in long-term ECG signals is an important task in medicine. This work briefly describes the cardiac activity and the manifestations of ventricular extrasystoles in the ECG record. Methods are described for automatic detection of premature contractions. The main content of the work is the implementation of two selected methods in the MATLAB program environment, combining the classifier from the first method and parameters from the second method, testing and evaluating the success of the obtained results.
|
|
|
Deep-learning based localization of cardiac arrhythimas in ECG
Khaliullina, Sabina ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
The thesis deals with the localization and classification of atrial atrial fibrillation. In Python, a detection method using convolutional neural networks with multi-instance learning (MIL) and the method of local maxima for localization were implemented. Segments from two ECG leads were used. In the binary classification using the first subset and subsequent post processing, the F1 score reached 100 %, in the classification using the second subset 92 %. In the discussion and conclusion of the work, the success of classification and localization was evaluated, the achieved results were discussed and compared the with the results of other authors.
|
|
|
Detection of ventricular arrhythmia in long-term ECG signals
Khaliullina, Sabina ; Smital, Lukáš (referee) ; Maršánová, Lucie (advisor)
Detection of premature ventricular contraction in long-term ECG signals is an important task in medicine. This work briefly describes the cardiac activity and the manifestations of ventricular extrasystoles in the ECG record. Methods are described for automatic detection of premature contractions. The main content of the work is the implementation of two selected methods in the MATLAB program environment, combining the classifier from the first method and parameters from the second method, testing and evaluating the success of the obtained results.
|
guest ::
