Real-Time Event-Driven Classification Technique for Early Detection and Prevention of Myocardial Infarction on Wearable Systems
(2018) In IEEE Transactions on Biomedical Circuits and Systems 12(5). p.982-992- Abstract
A considerable portion of government health-care spending is allocated to the continuous monitoring of patients suffering from cardiovascular diseases, particularly myocardial infarction (MI). Wearable devices present a cost-effective means of monitoring patients' vital signs in ambulatory settings. A major challenge is to design such ultra-low energy devices for long-Term patient monitoring. In this paper, we present a real-Time event-driven classification technique based on the random forest classification scheme, which uses a confidence-related decision-making process. The main goal of this technique is to maintain a high classification accuracy while reducing the complexity of the classification algorithm. We validate our approach... (More)
A considerable portion of government health-care spending is allocated to the continuous monitoring of patients suffering from cardiovascular diseases, particularly myocardial infarction (MI). Wearable devices present a cost-effective means of monitoring patients' vital signs in ambulatory settings. A major challenge is to design such ultra-low energy devices for long-Term patient monitoring. In this paper, we present a real-Time event-driven classification technique based on the random forest classification scheme, which uses a confidence-related decision-making process. The main goal of this technique is to maintain a high classification accuracy while reducing the complexity of the classification algorithm. We validate our approach on a well-established and complete MI database (Physiobank, PTB Diagnostic ECG database [1]). Our experimental evaluation demonstrates that our real-Time classification scheme outperforms the existing approaches in terms of energy consumption and battery lifetime by a factor of 2.60, with no classification quality loss.
(Less)
- author
- Sopic, Dionisije ; Aminifar, Amin ; Aminifar, Amir LU and Atienza, David
- publishing date
- 2018-10
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- event-driven, Myocardial infraction, random forest, wearables
- in
- IEEE Transactions on Biomedical Circuits and Systems
- volume
- 12
- issue
- 5
- article number
- 8411147
- pages
- 11 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:85049937700
- ISSN
- 1932-4545
- DOI
- 10.1109/TBCAS.2018.2848477
- language
- English
- LU publication?
- no
- additional info
- Funding Information: Manuscript received February 14, 2018; revised April 12, 2018; accepted May 16, 2018. Date of publication July 16, 2018; date of current version October 19, 2018. This work was supported in part by the Hasler Foundation (Project 15048), and in part by the Office of Naval Research Global Award Grant N62909-17-1-2006. This paper was recommended by Associate Editor S. Carrara. (Corresponding Author: Dionisije Sopic.) D. Sopic, Amir Aminifar, and D. Atienza are with the Embedded Systems Laboratory, Swiss Federal Institute of Technology Lausanne (EPFL), Lausanne 1015, Switzerland (e-mail:,dionisije.sopic@epfl.ch; amir.aminifar@ epfl.ch; david.atienza@epfl.ch). Publisher Copyright: © 2007-2012 IEEE. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.
- id
- d9a5c5d9-f17a-4aea-99a8-47492faea5c3
- date added to LUP
- 2021-08-31 16:12:54
- date last changed
- 2022-04-19 07:54:50
@article{d9a5c5d9-f17a-4aea-99a8-47492faea5c3, abstract = {{<p>A considerable portion of government health-care spending is allocated to the continuous monitoring of patients suffering from cardiovascular diseases, particularly myocardial infarction (MI). Wearable devices present a cost-effective means of monitoring patients' vital signs in ambulatory settings. A major challenge is to design such ultra-low energy devices for long-Term patient monitoring. In this paper, we present a real-Time event-driven classification technique based on the random forest classification scheme, which uses a confidence-related decision-making process. The main goal of this technique is to maintain a high classification accuracy while reducing the complexity of the classification algorithm. We validate our approach on a well-established and complete MI database (Physiobank, PTB Diagnostic ECG database [1]). Our experimental evaluation demonstrates that our real-Time classification scheme outperforms the existing approaches in terms of energy consumption and battery lifetime by a factor of 2.60, with no classification quality loss.</p>}}, author = {{Sopic, Dionisije and Aminifar, Amin and Aminifar, Amir and Atienza, David}}, issn = {{1932-4545}}, keywords = {{event-driven; Myocardial infraction; random forest; wearables}}, language = {{eng}}, number = {{5}}, pages = {{982--992}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Transactions on Biomedical Circuits and Systems}}, title = {{Real-Time Event-Driven Classification Technique for Early Detection and Prevention of Myocardial Infarction on Wearable Systems}}, url = {{http://dx.doi.org/10.1109/TBCAS.2018.2848477}}, doi = {{10.1109/TBCAS.2018.2848477}}, volume = {{12}}, year = {{2018}}, }