Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning

Emil Dark; Umer Saleem; Arttu Lämsä; Constantino Álvarez Casado; Miguel Bordallo López

doi:10.1145/3544793.3563407

Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning

Emil Dark, Umer Saleem, Arttu Lämsä, Constantino Álvarez Casado, Miguel Bordallo López

BA5610 Human-centric AI

University of Oulu

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

1 Citation (Scopus)

Abstract

In this article, we introduce a new approach for estimating the heart rate from noisy photoplethysmography (PPG) signals. We propose the use of two-dimensional representations of signals that are fed into a residual deep neural network that performs the regression task. Our approach leverages transfer learning and pre-trained models to further reduce the prediction error, resulting in state-of-the-art results in a challenging benchmark dataset.

Original language	English
Title of host publication	UbiComp/ISWC 2022 Adjunct - Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers
Publisher	Association for Computing Machinery ACM
Pages	163-167
Number of pages	5
ISBN (Electronic)	9781450394239
DOIs	https://doi.org/10.1145/3544793.3563407
Publication status	Published - 11 Sept 2022
MoE publication type	A4 Article in a conference publication
Event	2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2022 - Cambridge, United Kingdom Duration: 11 Sept 2022 → 15 Sept 2022

Conference

Conference	2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2022
Country/Territory	United Kingdom
City	Cambridge
Period	11/09/22 → 15/09/22

Keywords

Deep learning
Heart rate estimation
PPG

Access to Document

10.1145/3544793.3563407

Cite this

Dark, E., Saleem, U., Lämsä, A., Álvarez Casado, C., & Bordallo López, M. (2022). Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning. In UbiComp/ISWC 2022 Adjunct - Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers (pp. 163-167). Association for Computing Machinery ACM. https://doi.org/10.1145/3544793.3563407

Dark, Emil ; Saleem, Umer ; Lämsä, Arttu et al. / Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning. UbiComp/ISWC 2022 Adjunct - Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers. Association for Computing Machinery ACM, 2022. pp. 163-167

@inproceedings{8a603fcd3c0b40548043dc7833756a74,

title = "Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning",

abstract = "In this article, we introduce a new approach for estimating the heart rate from noisy photoplethysmography (PPG) signals. We propose the use of two-dimensional representations of signals that are fed into a residual deep neural network that performs the regression task. Our approach leverages transfer learning and pre-trained models to further reduce the prediction error, resulting in state-of-the-art results in a challenging benchmark dataset.",

keywords = "Deep learning, Heart rate estimation, PPG",

author = "Emil Dark and Umer Saleem and Arttu L{\"a}ms{\"a} and {{\'A}lvarez Casado}, Constantino and {Bordallo L{\'o}pez}, Miguel",

note = "Publisher Copyright: {\textcopyright} 2022 Owner/Author.; 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2022 ; Conference date: 11-09-2022 Through 15-09-2022",

year = "2022",

month = sep,

day = "11",

doi = "10.1145/3544793.3563407",

language = "English",

pages = "163--167",

booktitle = "UbiComp/ISWC 2022 Adjunct - Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers",

publisher = "Association for Computing Machinery ACM",

address = "United States",

}

Dark, E, Saleem, U, Lämsä, A, Álvarez Casado, C & Bordallo López, M 2022, Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning. in UbiComp/ISWC 2022 Adjunct - Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers. Association for Computing Machinery ACM, pp. 163-167, 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2022, Cambridge, United Kingdom, 11/09/22. https://doi.org/10.1145/3544793.3563407

Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning. / Dark, Emil; Saleem, Umer; Lämsä, Arttu et al.
UbiComp/ISWC 2022 Adjunct - Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers. Association for Computing Machinery ACM, 2022. p. 163-167.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning

AU - Dark, Emil

AU - Saleem, Umer

AU - Lämsä, Arttu

AU - Álvarez Casado, Constantino

AU - Bordallo López, Miguel

PY - 2022/9/11

Y1 - 2022/9/11

N2 - In this article, we introduce a new approach for estimating the heart rate from noisy photoplethysmography (PPG) signals. We propose the use of two-dimensional representations of signals that are fed into a residual deep neural network that performs the regression task. Our approach leverages transfer learning and pre-trained models to further reduce the prediction error, resulting in state-of-the-art results in a challenging benchmark dataset.

AB - In this article, we introduce a new approach for estimating the heart rate from noisy photoplethysmography (PPG) signals. We propose the use of two-dimensional representations of signals that are fed into a residual deep neural network that performs the regression task. Our approach leverages transfer learning and pre-trained models to further reduce the prediction error, resulting in state-of-the-art results in a challenging benchmark dataset.

KW - Deep learning

KW - Heart rate estimation

KW - PPG

UR - http://www.scopus.com/inward/record.url?scp=85158978444&partnerID=8YFLogxK

U2 - 10.1145/3544793.3563407

DO - 10.1145/3544793.3563407

M3 - Conference article in proceedings

AN - SCOPUS:85158978444

SP - 163

EP - 167

BT - UbiComp/ISWC 2022 Adjunct - Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers

PB - Association for Computing Machinery ACM

T2 - 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2022

Y2 - 11 September 2022 through 15 September 2022

ER -

Dark E, Saleem U, Lämsä A, Álvarez Casado C, Bordallo López M. Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning. In UbiComp/ISWC 2022 Adjunct - Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers. Association for Computing Machinery ACM. 2022. p. 163-167 doi: 10.1145/3544793.3563407

Heart Rate Estimation from Noisy PPGs Using 1D/2D Conversion and Transfer Learning

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this