Semi-supervised ECG Ventricular Beat Classification with Novelty Detection Based on Switching Kalman Filters. Oster, J., Behar, J., Sayadi, O., Nemati, S., Johnson, A., E., W., & Clifford, G., D. IEEE Transactions on Biomedical Engineering, PP(99):1-1, 2015. ![Semi-supervised ECG Ventricular Beat Classification with Novelty Detection Based on Switching Kalman Filters. [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website abstract bibtex Automatic processing and accurate diagnosis of pathological electrocardiogram (ECG) signals remains a challenge. As long-term ECG recordings continue to increase in prevalence, driven partly by the ease of remote monitoring technology usage, the need to automate ECG analysis continues to grow. In previous works a model-based ECG filtering approach to ECG data from healthy subjects has been applied to facilitate accurate online filtering and analysis of physiological signals. We propose an extension of this approach, which models not only normal and ventricular heartbeats, but also morphologies not previously encountered. A Switching Kalman Filter approach is introduced to enable the automatic selection of the most likely mode (beat type), while simultaneously filtering the signal using appropriate prior knowledge. Novelty detection is also made possible by incorporating a third mode for the detection of unknown (not previously observed) morphologies, and denoted as X-Factor. This new approach is compared to state-of-the-art techniques for the ventricular heartbeat classification in the MIT-BIH Arrhythmia and Incart databases. F1 scores of 98:3% and 99:5% were found on each database respectively, which are superior to other published algorithms' results reported on the same databases. Only 3% of all the beats were discarded as X-Factor, and the majority of these beats contained high levels of noise. The proposed technique demonstrates accurate beat classification in the presence of previously unseen (and unlearned) morphologies and noise, and provides an automated method for morphological analysis of arbitrary (unknown) ECG leads.
@article{
title = {Semi-supervised ECG Ventricular Beat Classification with Novelty Detection Based on Switching Kalman Filters.},
type = {article},
year = {2015},
identifiers = {[object Object]},
keywords = {Covariance matrices,Databases,Electrocardiogram,Electrocardiography,Heart beat,Heart rate variability,Morphology,Noise,heartbeat classification,switching Kalman filter},
pages = {1-1},
volume = {PP},
websites = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7038137},
id = {07a9bebb-f31b-3bd2-8ab6-dc66e65a6e4c},
created = {2016-03-29T20:33:58.000Z},
file_attached = {false},
profile_id = {8c4ca2d5-86de-3b5d-86be-8408415f34e0},
group_id = {d7b44578-07c1-3210-ae74-3bcd7f980767},
last_modified = {2017-03-14T15:45:25.917Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Oster2015},
private_publication = {false},
abstract = {Automatic processing and accurate diagnosis of pathological electrocardiogram (ECG) signals remains a challenge. As long-term ECG recordings continue to increase in prevalence, driven partly by the ease of remote monitoring technology usage, the need to automate ECG analysis continues to grow. In previous works a model-based ECG filtering approach to ECG data from healthy subjects has been applied to facilitate accurate online filtering and analysis of physiological signals. We propose an extension of this approach, which models not only normal and ventricular heartbeats, but also morphologies not previously encountered. A Switching Kalman Filter approach is introduced to enable the automatic selection of the most likely mode (beat type), while simultaneously filtering the signal using appropriate prior knowledge. Novelty detection is also made possible by incorporating a third mode for the detection of unknown (not previously observed) morphologies, and denoted as X-Factor. This new approach is compared to state-of-the-art techniques for the ventricular heartbeat classification in the MIT-BIH Arrhythmia and Incart databases. F1 scores of 98:3% and 99:5% were found on each database respectively, which are superior to other published algorithms' results reported on the same databases. Only 3% of all the beats were discarded as X-Factor, and the majority of these beats contained high levels of noise. The proposed technique demonstrates accurate beat classification in the presence of previously unseen (and unlearned) morphologies and noise, and provides an automated method for morphological analysis of arbitrary (unknown) ECG leads.},
bibtype = {article},
author = {Oster, Julien and Behar, Joachim and Sayadi, Omid and Nemati, Shamim and Johnson, Alistair E W and Clifford, Gari D},
journal = {IEEE Transactions on Biomedical Engineering},
number = {99}
}
Downloads: 0
{"_id":"NQjtkpueXQeFNEFHF","bibbaseid":"oster-behar-sayadi-nemati-johnson-clifford-semisupervisedecgventricularbeatclassificationwithnoveltydetectionbasedonswitchingkalmanfilters-2015","downloads":0,"creationDate":"2015-06-02T06:15:55.813Z","title":"Semi-supervised ECG Ventricular Beat Classification with Novelty Detection Based on Switching Kalman Filters.","author_short":["Oster, J.","Behar, J.","Sayadi, O.","Nemati, S.","Johnson, A., E., W.","Clifford, G., D."],"year":2015,"bibtype":"article","biburl":null,"bibdata":{"title":"Semi-supervised ECG Ventricular Beat Classification with Novelty Detection Based on Switching Kalman Filters.","type":"article","year":"2015","identifiers":"[object Object]","keywords":"Covariance matrices,Databases,Electrocardiogram,Electrocardiography,Heart beat,Heart rate variability,Morphology,Noise,heartbeat classification,switching Kalman filter","pages":"1-1","volume":"PP","websites":"http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7038137","id":"07a9bebb-f31b-3bd2-8ab6-dc66e65a6e4c","created":"2016-03-29T20:33:58.000Z","file_attached":false,"profile_id":"8c4ca2d5-86de-3b5d-86be-8408415f34e0","group_id":"d7b44578-07c1-3210-ae74-3bcd7f980767","last_modified":"2017-03-14T15:45:25.917Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Oster2015","private_publication":false,"abstract":"Automatic processing and accurate diagnosis of pathological electrocardiogram (ECG) signals remains a challenge. As long-term ECG recordings continue to increase in prevalence, driven partly by the ease of remote monitoring technology usage, the need to automate ECG analysis continues to grow. In previous works a model-based ECG filtering approach to ECG data from healthy subjects has been applied to facilitate accurate online filtering and analysis of physiological signals. We propose an extension of this approach, which models not only normal and ventricular heartbeats, but also morphologies not previously encountered. A Switching Kalman Filter approach is introduced to enable the automatic selection of the most likely mode (beat type), while simultaneously filtering the signal using appropriate prior knowledge. Novelty detection is also made possible by incorporating a third mode for the detection of unknown (not previously observed) morphologies, and denoted as X-Factor. This new approach is compared to state-of-the-art techniques for the ventricular heartbeat classification in the MIT-BIH Arrhythmia and Incart databases. F1 scores of 98:3% and 99:5% were found on each database respectively, which are superior to other published algorithms' results reported on the same databases. Only 3% of all the beats were discarded as X-Factor, and the majority of these beats contained high levels of noise. The proposed technique demonstrates accurate beat classification in the presence of previously unseen (and unlearned) morphologies and noise, and provides an automated method for morphological analysis of arbitrary (unknown) ECG leads.","bibtype":"article","author":"Oster, Julien and Behar, Joachim and Sayadi, Omid and Nemati, Shamim and Johnson, Alistair E W and Clifford, Gari D","journal":"IEEE Transactions on Biomedical Engineering","number":"99","bibtex":"@article{\n title = {Semi-supervised ECG Ventricular Beat Classification with Novelty Detection Based on Switching Kalman Filters.},\n type = {article},\n year = {2015},\n identifiers = {[object Object]},\n keywords = {Covariance matrices,Databases,Electrocardiogram,Electrocardiography,Heart beat,Heart rate variability,Morphology,Noise,heartbeat classification,switching Kalman filter},\n pages = {1-1},\n volume = {PP},\n websites = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7038137},\n id = {07a9bebb-f31b-3bd2-8ab6-dc66e65a6e4c},\n created = {2016-03-29T20:33:58.000Z},\n file_attached = {false},\n profile_id = {8c4ca2d5-86de-3b5d-86be-8408415f34e0},\n group_id = {d7b44578-07c1-3210-ae74-3bcd7f980767},\n last_modified = {2017-03-14T15:45:25.917Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Oster2015},\n private_publication = {false},\n abstract = {Automatic processing and accurate diagnosis of pathological electrocardiogram (ECG) signals remains a challenge. As long-term ECG recordings continue to increase in prevalence, driven partly by the ease of remote monitoring technology usage, the need to automate ECG analysis continues to grow. In previous works a model-based ECG filtering approach to ECG data from healthy subjects has been applied to facilitate accurate online filtering and analysis of physiological signals. We propose an extension of this approach, which models not only normal and ventricular heartbeats, but also morphologies not previously encountered. A Switching Kalman Filter approach is introduced to enable the automatic selection of the most likely mode (beat type), while simultaneously filtering the signal using appropriate prior knowledge. Novelty detection is also made possible by incorporating a third mode for the detection of unknown (not previously observed) morphologies, and denoted as X-Factor. This new approach is compared to state-of-the-art techniques for the ventricular heartbeat classification in the MIT-BIH Arrhythmia and Incart databases. F1 scores of 98:3% and 99:5% were found on each database respectively, which are superior to other published algorithms' results reported on the same databases. Only 3% of all the beats were discarded as X-Factor, and the majority of these beats contained high levels of noise. The proposed technique demonstrates accurate beat classification in the presence of previously unseen (and unlearned) morphologies and noise, and provides an automated method for morphological analysis of arbitrary (unknown) ECG leads.},\n bibtype = {article},\n author = {Oster, Julien and Behar, Joachim and Sayadi, Omid and Nemati, Shamim and Johnson, Alistair E W and Clifford, Gari D},\n journal = {IEEE Transactions on Biomedical Engineering},\n number = {99}\n}","author_short":["Oster, J.","Behar, J.","Sayadi, O.","Nemati, S.","Johnson, A., E., W.","Clifford, G., D."],"urls":{"Website":"http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7038137"},"bibbaseid":"oster-behar-sayadi-nemati-johnson-clifford-semisupervisedecgventricularbeatclassificationwithnoveltydetectionbasedonswitchingkalmanfilters-2015","role":"author","keyword":["Covariance matrices","Databases","Electrocardiogram","Electrocardiography","Heart beat","Heart rate variability","Morphology","Noise","heartbeat classification","switching Kalman filter"],"downloads":0},"search_terms":["semi","supervised","ecg","ventricular","beat","classification","novelty","detection","based","switching","kalman","filters","oster","behar","sayadi","nemati","johnson","clifford"],"keywords":["covariance matrices","databases","electrocardiogram","electrocardiography","heart beat","heart rate variability","morphology","noise","heartbeat classification","switching kalman filter"],"authorIDs":[]}