Tamás Dózsa, Gergö Bognar, Peter Kovacs,
"Ensemble Learning for Heartbeat Classification Using Adaptive Orthogonal Transformations"
: Computer Aided Systems Theory - EUROCAST 2019, Part II, Lecture Notes in Computer Science (LNCS), Serie Lecture Notes in Computer Science (LNCS), Vol. 12014, Springer, Seite(n) 355-363, 4-2020, ISBN: 978-3-030-45096-0
Original Titel:
Ensemble Learning for Heartbeat Classification Using Adaptive Orthogonal Transformations
Sprache des Titels:
Englisch
Original Buchtitel:
Computer Aided Systems Theory - EUROCAST 2019, Part II, Lecture Notes in Computer Science (LNCS)
Original Kurzfassung:
In this work, we are focusing on the problem of heartbeat classification in electrocardiogram (ECG) signals. First we develop a patient-specific feature extraction scheme by using adaptive orthogonal transformations based on wavelets, B-splines, Hermite and rational functions. The so-called variable projection provides the general framework to find the optimal nonlinear parameters of these transformations. After extracting the features, we train a support vector machine (SVM) for each model whose outputs are combined via ensemble learning techniques. In the experiments, we achieved an accuracy of 94.2% on the PhysioNet MIT-BIH Arrhythmia Database that shows the potential of the proposed signal models in arrhythmia detection.
Forschungs-