Inequality indexes as sparsity measures applied to ventricular ectopic beats detection and its efficient hardware implementation.

Hdl Handle:
http://hdl.handle.net/10545/622053
Title:
Inequality indexes as sparsity measures applied to ventricular ectopic beats detection and its efficient hardware implementation.
Authors:
Baali, Hamza; Zhai, Xiaojun ( 0000-0002-1030-8311 ) ; Djelouat, Hamza; Amira, Abbes; Bensaali, Faycal ( 0000-0002-9273-4735 )
Abstract:
Meeting application requirements under a tight power budget is of a primary importance to enable connected health internet of things (IoT) applications. This paper considers using sparse representation and well-defined inequality indexes drawn from the theory of inequality to distinguish ventricular ectopic beats (VEBs) from non-VEBs. Our approach involves designing a separate dictionary for each arrhythmia class using a set of labelled training QRS complexes. Sparse representation, based on the designed dictionaries of each new test QRS complex is then calculated. Following this, its class is predicted using the winner-takes-all principle by selecting the class with the highest inequality index. Our experiments showed promising results ranging between 80% and 100% for the detection of VEBs considering the patient-specific approach, 80% using cross-validation and 70% on unseen data using independent sets for training and testing respectively. An efficient hardware implementation of the alternating direction method of multipliers (ADMM) algorithm is also presented. The results show that the proposed hardware implementation can classify a QRS complex in 69.3 ms that use only 0.934 W energy.
Affiliation:
Qatar University; University of Derby
Citation:
Baali, H. et al (2017) 'Inequality Indexes as Sparsity Measures Applied to Ventricular Ectopic Beats Detection and its Efficient Hardware Implementation', IEEE Access, DOI: 10.1109/ACCESS.2017.2780190.
Publisher:
IEEE
Journal:
IEEE Access
Issue Date:
27-Dec-2017
URI:
http://hdl.handle.net/10545/622053
DOI:
10.1109/ACCESS.2017.2780190
Additional Links:
http://ieeexplore.ieee.org/document/8240906/
Type:
Article
Language:
en
ISSN:
21693536
Sponsors:
This research work was supported by National Priorities Research Program (NPRP) grant No. 9-114-2-055 from the Qatar National Research Fund (a member of Qatar Foundation)
Appears in Collections:
Department of Electronics, Computing & Maths

Full metadata record

DC FieldValue Language
dc.contributor.authorBaali, Hamzaen
dc.contributor.authorZhai, Xiaojunen
dc.contributor.authorDjelouat, Hamzaen
dc.contributor.authorAmira, Abbesen
dc.contributor.authorBensaali, Faycalen
dc.date.accessioned2018-01-12T15:37:32Z-
dc.date.available2018-01-12T15:37:32Z-
dc.date.issued2017-12-27-
dc.identifier.citationBaali, H. et al (2017) 'Inequality Indexes as Sparsity Measures Applied to Ventricular Ectopic Beats Detection and its Efficient Hardware Implementation', IEEE Access, DOI: 10.1109/ACCESS.2017.2780190.en
dc.identifier.issn21693536-
dc.identifier.doi10.1109/ACCESS.2017.2780190-
dc.identifier.urihttp://hdl.handle.net/10545/622053-
dc.description.abstractMeeting application requirements under a tight power budget is of a primary importance to enable connected health internet of things (IoT) applications. This paper considers using sparse representation and well-defined inequality indexes drawn from the theory of inequality to distinguish ventricular ectopic beats (VEBs) from non-VEBs. Our approach involves designing a separate dictionary for each arrhythmia class using a set of labelled training QRS complexes. Sparse representation, based on the designed dictionaries of each new test QRS complex is then calculated. Following this, its class is predicted using the winner-takes-all principle by selecting the class with the highest inequality index. Our experiments showed promising results ranging between 80% and 100% for the detection of VEBs considering the patient-specific approach, 80% using cross-validation and 70% on unseen data using independent sets for training and testing respectively. An efficient hardware implementation of the alternating direction method of multipliers (ADMM) algorithm is also presented. The results show that the proposed hardware implementation can classify a QRS complex in 69.3 ms that use only 0.934 W energy.en
dc.description.sponsorshipThis research work was supported by National Priorities Research Program (NPRP) grant No. 9-114-2-055 from the Qatar National Research Fund (a member of Qatar Foundation)en
dc.language.isoenen
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/8240906/en
dc.rightsArchived with thanks to IEEE Accessen
dc.subjectInequality indexesen
dc.subjectDictionary learningen
dc.subjectInternet of Thingsen
dc.subjectArrhythmiaen
dc.titleInequality indexes as sparsity measures applied to ventricular ectopic beats detection and its efficient hardware implementation.en
dc.typeArticleen
dc.contributor.departmentQatar Universityen
dc.contributor.departmentUniversity of Derbyen
dc.identifier.journalIEEE Accessen
All Items in UDORA are protected by copyright, with all rights reserved, unless otherwise indicated.