Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices

Zonglong Li; Laurie E. Calvet

doi:10.1109/SMACD58065.2023.10192147

Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices

Zonglong Li
, Laurie E. Calvet

Centre de Nanosciences et de Nanotechnologies

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In recent years, the computational efficiency of spike-based biomimetic information processing has received increasing interest. Here we show by simulation how two spiking neurons with different thresholds can be used to extract ECG features. One high-threshold neuron detects the location of the heartbeat, and the other low-threshold neuron detects other small-magnitude features. These detected features alone can then be transmitted to a nearby computer to classify the heartbeat instead of the entire ECG signal. Reducing transferred data by about 50 times, minimizing energy consumption and thus potentially extending the continuous use time for health monitoring applications. We show that a KNN algorithm classifies the heartbeat based on the obtained features with an overall accuracy of 96%, proving our method's feasibility.

Original language	English
Title of host publication	Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350332650
DOIs	https://doi.org/10.1109/SMACD58065.2023.10192147
Publication status	Published - 1 Jan 2023
Event	19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023 - Funchal, Portugal Duration: 3 Jul 2023 → 5 Jul 2023

Publication series

Name	Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023

Conference

Conference	19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023
Country/Territory	Portugal
City	Funchal
Period	3/07/23 → 5/07/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

ECG
data transmission reduction
health monitoring equipment
spike-based biomimetic information processing
spiking neuron circuit

Access to Document

10.1109/SMACD58065.2023.10192147

Cite this

Li, Z., & Calvet, L. E. (2023). Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices. In Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023 (Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMACD58065.2023.10192147

Li, Zonglong ; Calvet, Laurie E. / Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices. Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023).

@inproceedings{d463831ae83246c1afd5ed8c975e3b45,

title = "Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices",

abstract = "In recent years, the computational efficiency of spike-based biomimetic information processing has received increasing interest. Here we show by simulation how two spiking neurons with different thresholds can be used to extract ECG features. One high-threshold neuron detects the location of the heartbeat, and the other low-threshold neuron detects other small-magnitude features. These detected features alone can then be transmitted to a nearby computer to classify the heartbeat instead of the entire ECG signal. Reducing transferred data by about 50 times, minimizing energy consumption and thus potentially extending the continuous use time for health monitoring applications. We show that a KNN algorithm classifies the heartbeat based on the obtained features with an overall accuracy of 96\%, proving our method's feasibility.",

keywords = "ECG, data transmission reduction, health monitoring equipment, spike-based biomimetic information processing, spiking neuron circuit",

author = "Zonglong Li and Calvet, \{Laurie E.\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023 ; Conference date: 03-07-2023 Through 05-07-2023",

year = "2023",

month = jan,

day = "1",

doi = "10.1109/SMACD58065.2023.10192147",

language = "English",

series = "Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023",

}

Li, Z & Calvet, LE 2023, Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices. in Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023. Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023, Institute of Electrical and Electronics Engineers Inc., 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023, Funchal, Portugal, 3/07/23. https://doi.org/10.1109/SMACD58065.2023.10192147

Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices. / Li, Zonglong; Calvet, Laurie E.
Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices

AU - Li, Zonglong

AU - Calvet, Laurie E.

PY - 2023/1/1

Y1 - 2023/1/1

N2 - In recent years, the computational efficiency of spike-based biomimetic information processing has received increasing interest. Here we show by simulation how two spiking neurons with different thresholds can be used to extract ECG features. One high-threshold neuron detects the location of the heartbeat, and the other low-threshold neuron detects other small-magnitude features. These detected features alone can then be transmitted to a nearby computer to classify the heartbeat instead of the entire ECG signal. Reducing transferred data by about 50 times, minimizing energy consumption and thus potentially extending the continuous use time for health monitoring applications. We show that a KNN algorithm classifies the heartbeat based on the obtained features with an overall accuracy of 96%, proving our method's feasibility.

AB - In recent years, the computational efficiency of spike-based biomimetic information processing has received increasing interest. Here we show by simulation how two spiking neurons with different thresholds can be used to extract ECG features. One high-threshold neuron detects the location of the heartbeat, and the other low-threshold neuron detects other small-magnitude features. These detected features alone can then be transmitted to a nearby computer to classify the heartbeat instead of the entire ECG signal. Reducing transferred data by about 50 times, minimizing energy consumption and thus potentially extending the continuous use time for health monitoring applications. We show that a KNN algorithm classifies the heartbeat based on the obtained features with an overall accuracy of 96%, proving our method's feasibility.

KW - ECG

KW - data transmission reduction

KW - health monitoring equipment

KW - spike-based biomimetic information processing

KW - spiking neuron circuit

UR - https://www.scopus.com/pages/publications/85168685632

U2 - 10.1109/SMACD58065.2023.10192147

DO - 10.1109/SMACD58065.2023.10192147

M3 - Conference contribution

AN - SCOPUS:85168685632

T3 - Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023

BT - Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023

Y2 - 3 July 2023 through 5 July 2023

ER -

Li Z, Calvet LE. Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices. In Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (Proceedings - 2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, SMACD 2023). doi: 10.1109/SMACD58065.2023.10192147

Extraction of ECG features with spiking neurons for decreased power consumption in embedded devices

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this