Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 31st European Signal Processing Conference |
| Untertitel | EUSIPCO 2023 |
| Seiten | 1375-1379 |
| Seitenumfang | 5 |
| ISBN (elektronisch) | 9789464593600 |
| Publikationsstatus | Veröffentlicht - 2023 |
| Veranstaltung | 31st European Signal Processing Conference, EUSIPCO 2023 - Helsinki, Finnland Dauer: 4 Sept. 2023 → 8 Sept. 2023 |
Publikationsreihe
| Name | European Signal Processing Conference |
|---|---|
| ISSN (Print) | 2219-5491 |
Abstract
Atrial fibrillation (AF) is the most common cardiac arrhythmia and associated with a high risk for serious conditions like stroke. The use of wearable devices embedded with automatic and timely AF assessment from electrocardiograms (ECGs) has shown to be promising in preventing life-threatening situations. Although deep neural networks have demonstrated superiority in model performance, their use on wearable devices is limited by the trade-off between model performance and complexity. In this work, we propose to use lightweight convolutional neural networks (CNNs) with parameterised hypercomplex (PH) layers for AF detection based on ECGs. The proposed approach trains small-scale CNNs, thus overcoming the limited computing resources on wearable devices. We show comparable performance to corresponding real-valued CNNs on two publicly available ECG datasets using significantly fewer model parameters. PH models are more flexible than other hypercomplex neural networks and can operate on any number of input ECG leads.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Signalverarbeitung
- Ingenieurwesen (insg.)
- Elektrotechnik und Elektronik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
31st European Signal Processing Conference: EUSIPCO 2023. 2023. S. 1375-1379 (European Signal Processing Conference).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Efficient ECG-based Atrial Fibrillation Detection via Parameterised Hypercomplex Neural Networks
AU - Basso, Leonie
AU - Ren, Zhao
AU - Nejdl, Wolfgang
N1 - Funding Information: This research was funded by the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizKILabor with grant No. 01DD20003.
PY - 2023
Y1 - 2023
N2 - Atrial fibrillation (AF) is the most common cardiac arrhythmia and associated with a high risk for serious conditions like stroke. The use of wearable devices embedded with automatic and timely AF assessment from electrocardiograms (ECGs) has shown to be promising in preventing life-threatening situations. Although deep neural networks have demonstrated superiority in model performance, their use on wearable devices is limited by the trade-off between model performance and complexity. In this work, we propose to use lightweight convolutional neural networks (CNNs) with parameterised hypercomplex (PH) layers for AF detection based on ECGs. The proposed approach trains small-scale CNNs, thus overcoming the limited computing resources on wearable devices. We show comparable performance to corresponding real-valued CNNs on two publicly available ECG datasets using significantly fewer model parameters. PH models are more flexible than other hypercomplex neural networks and can operate on any number of input ECG leads.
AB - Atrial fibrillation (AF) is the most common cardiac arrhythmia and associated with a high risk for serious conditions like stroke. The use of wearable devices embedded with automatic and timely AF assessment from electrocardiograms (ECGs) has shown to be promising in preventing life-threatening situations. Although deep neural networks have demonstrated superiority in model performance, their use on wearable devices is limited by the trade-off between model performance and complexity. In this work, we propose to use lightweight convolutional neural networks (CNNs) with parameterised hypercomplex (PH) layers for AF detection based on ECGs. The proposed approach trains small-scale CNNs, thus overcoming the limited computing resources on wearable devices. We show comparable performance to corresponding real-valued CNNs on two publicly available ECG datasets using significantly fewer model parameters. PH models are more flexible than other hypercomplex neural networks and can operate on any number of input ECG leads.
KW - Atrial fibrillation
KW - ECG analysis
KW - hypercomplex domain
KW - lightweight neural networks
UR - http://www.scopus.com/inward/record.url?scp=85178373424&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2211.02678
DO - 10.48550/arXiv.2211.02678
M3 - Conference contribution
AN - SCOPUS:85178373424
SN - 979-8-3503-2811-0
T3 - European Signal Processing Conference
SP - 1375
EP - 1379
BT - 31st European Signal Processing Conference
T2 - 31st European Signal Processing Conference, EUSIPCO 2023
Y2 - 4 September 2023 through 8 September 2023
ER -