Real-Time Personalized Atrial Fibrillation Prediction on Multi-Core Wearable Sensors
De Giovanni, Elisabetta ; Valdes, Adriana Arza ; Peon-Quiros, Miguel ; Aminifar, Amir LU
and Atienza, David
(2021)
In IEEE Transactions on Emerging Topics in Computing
9(4).
p.1654-1666
- Abstract
In the recent Internet-of-Things (IoT) era where biomedical applications require continuous monitoring of relevant data, edge computing keeps gaining more and more importance. These new architectures for edge computing include multi-core and parallel computing capabilities that can enable prevention diagnosis and treatment of diseases in ambulatory or home-based setups. In this article, we explore the benefits of the parallelization capabilities and computing heterogeneity of new wearable sensors in the context of a personalized online atrial fibrillation (AF) prediction method for daily monitoring. First, we apply optimizations to a single-core design to reduce energy, based on patient-specific training models. Second, we explore... (More)
In the recent Internet-of-Things (IoT) era where biomedical applications require continuous monitoring of relevant data, edge computing keeps gaining more and more importance. These new architectures for edge computing include multi-core and parallel computing capabilities that can enable prevention diagnosis and treatment of diseases in ambulatory or home-based setups. In this article, we explore the benefits of the parallelization capabilities and computing heterogeneity of new wearable sensors in the context of a personalized online atrial fibrillation (AF) prediction method for daily monitoring. First, we apply optimizations to a single-core design to reduce energy, based on patient-specific training models. Second, we explore multi-core and memory banks configuration changes to adapt the computation and storage requirements to the characteristics of each patient. We evaluate our methodology on the Physionet Prediction Challenge (2001) publicly available database, and assess the energy consumption of single-core (ARM Cortex-M3 based) and new ultra-low power multi-core architectures (open-source RISC-V based) for next-generation of wearable platforms. Overall, our exploration at the application level highlights that a parallelization approach for personalized AF in multi-core wearable sensors enables energy savings up to 24% with respect to single-core sensors. Moreover, including the adaptation of the memory subsystem (size and number of memory banks), in combination with deep sleep energy saving modes, can overall provide total energy savings up to 34%, depending on the specific patient.
(Less)
- author
- De Giovanni, Elisabetta
; Valdes, Adriana Arza
; Peon-Quiros, Miguel
; Aminifar, Amir
LU
and Atienza, David
- organization
- publishing date
- 2021
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- atrial fibrillation prediction, multi-core, Parallel computing, personalized, real-time, wearable sensors
- in
- IEEE Transactions on Emerging Topics in Computing
- volume
- 9
- issue
- 4
- pages
- 13 pages
- publisher
- IEEE Computer Society
- external identifiers
-
- scopus:85099549416
- ISSN
- 2168-6750
- DOI
- 10.1109/TETC.2020.3014847
- language
- English
- LU publication?
- yes
- id
- e162cb5d-4960-4728-b896-6d2d1ba9c986
- date added to LUP
- 2022-01-31 01:33:27
- date last changed
- 2022-04-27 07:28:24
@article{e162cb5d-4960-4728-b896-6d2d1ba9c986,
abstract = {{<p>In the recent Internet-of-Things (IoT) era where biomedical applications require continuous monitoring of relevant data, edge computing keeps gaining more and more importance. These new architectures for edge computing include multi-core and parallel computing capabilities that can enable prevention diagnosis and treatment of diseases in ambulatory or home-based setups. In this article, we explore the benefits of the parallelization capabilities and computing heterogeneity of new wearable sensors in the context of a personalized online atrial fibrillation (AF) prediction method for daily monitoring. First, we apply optimizations to a single-core design to reduce energy, based on patient-specific training models. Second, we explore multi-core and memory banks configuration changes to adapt the computation and storage requirements to the characteristics of each patient. We evaluate our methodology on the Physionet Prediction Challenge (2001) publicly available database, and assess the energy consumption of single-core (ARM Cortex-M3 based) and new ultra-low power multi-core architectures (open-source RISC-V based) for next-generation of wearable platforms. Overall, our exploration at the application level highlights that a parallelization approach for personalized AF in multi-core wearable sensors enables energy savings up to 24% with respect to single-core sensors. Moreover, including the adaptation of the memory subsystem (size and number of memory banks), in combination with deep sleep energy saving modes, can overall provide total energy savings up to 34%, depending on the specific patient.</p>}},
author = {{De Giovanni, Elisabetta and Valdes, Adriana Arza and Peon-Quiros, Miguel and Aminifar, Amir and Atienza, David}},
issn = {{2168-6750}},
keywords = {{atrial fibrillation prediction; multi-core; Parallel computing; personalized; real-time; wearable sensors}},
language = {{eng}},
number = {{4}},
pages = {{1654--1666}},
publisher = {{IEEE Computer Society}},
series = {{IEEE Transactions on Emerging Topics in Computing}},
title = {{Real-Time Personalized Atrial Fibrillation Prediction on Multi-Core Wearable Sensors}},
url = {{http://dx.doi.org/10.1109/TETC.2020.3014847}},
doi = {{10.1109/TETC.2020.3014847}},
volume = {{9}},
year = {{2021}},
}