Přístupnostní navigace
E-application
Search Search Close
Publication detail
SMÍŠEK, R. HEJČ, J. RONZHINA, M. NĚMCOVÁ, A. MARŠÁNOVÁ, L. CHMELÍK, J. KOLÁŘOVÁ, J. PROVAZNÍK, I. SMITAL, L. VÍTEK, M.
Original Title
SVM Based ECG Classification Using Rhythm and Morphology Features, Cluster Analysis and Multilevel Noise Estimation
Type
conference paper
Language
English
Original Abstract
Background: Smartphone-based ECG devices comprise great potential in screening for arrhythmias. However, its feasibility is limited by poor signal quality leading to incorrect rhythm classification. In this study, advanced method for automatic classification of normal rhythm (N), atrial fibrillation (A), other rhythm (O), and noisy records (P) is introduced. Methods: Two-step SVM approach followed by simple threshold based rules was used for data classification. In the first step, various features were derived from separate beats to represent particular events (normal as well as pathological and artefacts) in more detail. Output of the first classifier was used to calculate global features describing entire ECG. These features were then used to train the second classification model. Both classifiers were evaluated on training set via cross-validation technique, and additionally on hidden testing set. Results: In the Phase II of challenge, total F1 score of the method is 0.81 and 0.84 within hidden challenge dataset and training set, respectively. Particular F1 scores within hidden challenge dataset are 0.90 (N), 0.81 (A), 0.72 (O), and 0.55 (P). Particular F1 scores within training set are 0.91 (N), 0.85 (A), 0.76 (O), and 0.73 (P).
Keywords
ECG, Atrial fibrilation, ECG classification
Authors
SMÍŠEK, R.; HEJČ, J.; RONZHINA, M.; NĚMCOVÁ, A.; MARŠÁNOVÁ, L.; CHMELÍK, J.; KOLÁŘOVÁ, J.; PROVAZNÍK, I.; SMITAL, L.; VÍTEK, M.
Released
28. 9. 2017
Location
Rennes, France
ISBN
978-1-5090-0684-7
Book
Computing in Cardiology 2017
0276-6574
Periodical
Computers in Cardiology
State
United States of America
Pages from
1
Pages to
4
Pages count
BibTex
@inproceedings{BUT143520, author="Radovan {Smíšek} and Jakub {Hejč} and Marina {Filipenská} and Andrea {Němcová} and Lucie {Šaclová} and Jiří {Chmelík} and Jana {Kolářová} and Valentine {Provazník} and Lukáš {Smital} and Martin {Vítek}", title="SVM Based ECG Classification Using Rhythm and Morphology Features, Cluster Analysis and Multilevel Noise Estimation", booktitle="Computing in Cardiology 2017", year="2017", journal="Computers in Cardiology", pages="1--4", address="Rennes, France", doi="10.22489/CinC.2017.172-200", isbn="978-1-5090-0684-7", issn="0276-6574" }