Weighted Conditional Random Fields for Supervised Interpatient Heartbeat Classification

被引:145
作者
de Lannoy, Gael [1 ,2 ]
Francois, Damien [1 ]
Delbeke, Jean [2 ]
Verleysen, Michel [1 ]
机构
[1] Catholic Univ Louvain, Machine Learning Grp, B-1348 Louvain, Belgium
[2] Catholic Univ Louvain, Inst Neurosci, B-1200 Brussels, Belgium
关键词
Classification; conditional random fields (CRFs); electrocardiogram (ECG); physiobank; unbalance;
D O I
10.1109/TBME.2011.2171037
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
This paper proposes a method for the automatic classification of heartbeats in an ECG signal. Since this task has specific characteristics such as time dependences between observations and a strong class unbalance, a specific classifier is proposed and evaluated on real ECG signals from the MIT arrhythmia database. This classifier is a weighted variant of the conditional random fields classifier. Experiments show that the proposed method outperforms previously reported heartbeat classification methods, especially for the pathological heartbeats.
引用
收藏
页码:241 / 247
页数:7
相关论文
共 24 条
[1]   Applying support vector machines to imbalanced datasets [J].
Akbani, R ;
Kwek, S ;
Japkowicz, N .
MACHINE LEARNING: ECML 2004, PROCEEDINGS, 2004, 3201 :39-50
[2]  
[Anonymous], 1998, TEST REP PERF RES CA
[3]  
Boyd S.P, 2004, Convex optimization, DOI [DOI 10.1017/CBO9780511804441, 10.1017/CBO9780511804441]
[4]   Comparative study of morphological and time-frequency ECG descriptors for heartbeat classification [J].
Christov, Ivaylo ;
Gomez-Herrero, German ;
Krasteva, Vessela ;
Jekova, Irena ;
Gotchev, Atanas ;
Egiazarian, Karen .
MEDICAL ENGINEERING & PHYSICS, 2006, 28 (09) :876-887
[5]   Automatic classification of heartbeats using ECG morphology and heartbeat interval features [J].
de Chazal, P ;
O'Dwyer, M ;
Reilly, RB .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2004, 51 (07) :1196-1206
[6]  
de Lannoy G, 2011, COMM COM INF SC, V127, P212
[7]  
DOQUIRE G, 2011, P 4 INT C BIOINSP SY, P67
[8]   PhysioBank, PhysioToolkit, and PhysioNet - Components of a new research resource for complex physiologic signals [J].
Goldberger, AL ;
Amaral, LAN ;
Glass, L ;
Hausdorff, JM ;
Ivanov, PC ;
Mark, RG ;
Mietus, JE ;
Moody, GB ;
Peng, CK ;
Stanley, HE .
CIRCULATION, 2000, 101 (23) :E215-E220
[9]  
Lafferty J.D., 2001, Conditional random fields: Probabilistic models for segmenting and labeling sequence data, P282, DOI DOI 10.5555/645530.655813
[10]   Clustering ECG complexes using Hermite functions and self-organizing maps [J].
Lagerholm, M ;
Peterson, C ;
Braccini, G ;
Edenbrandt, L ;
Sörnmo, L .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2000, 47 (07) :838-848