Ensemble Learning Method for Human Identification in Wearable Devices

Lucas Bastos; Bruno Martins; Iago Medeiros; Augusto Neto; Sherali Zeadally; Denis Rosario; Eduardo Cerqueira

doi:10.1109/IWCMC55113.2022.9824669

Ensemble Learning Method for Human Identification in Wearable Devices

Lucas Bastos, Bruno Martins, Iago Medeiros, Augusto Neto, Sherali Zeadally, Denis Rosario, Eduardo Cerqueira

School of Information Science

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

Abstract

Wearables today play a key role in E-Health computing, with investments expected to exceed $70 billion by 2024. With the massive use of apps on wearable devices, it is crucial to improve safety when using wearables, considering that important information about user information is stored on these devices. We present SOMEONE ensemble learning, a set machine learning algorithm for body recognition of wearable devices, which operates on the basis of both PhotoPlethysmoGram (PPG) and ElectroCardioGram (ECG) signals. We consider an individual's PPG and ECG signals, where algorithms process these signals stored on the wearable device to identify the user. The SOMEONE algorithm achieves better results on metrics such as F1 score, accuracy, false acceptance rate (FAR) and false rejection rate (FRR) for human recognition in MIMIC dataset of ECG signals and CapnoBase dataset of PPG signal.

Original language	English
Title of host publication	2022 International Wireless Communications and Mobile Computing, IWCMC 2022
Pages	1052-1057
Number of pages	6
ISBN (Electronic)	9781665467490
DOIs	https://doi.org/10.1109/IWCMC55113.2022.9824669
State	Published - 2022
Event	18th IEEE International Wireless Communications and Mobile Computing, IWCMC 2022 - Dubrovnik, Croatia Duration: May 30 2022 → Jun 3 2022

Publication series

Name	2022 International Wireless Communications and Mobile Computing, IWCMC 2022

Conference

Conference	18th IEEE International Wireless Communications and Mobile Computing, IWCMC 2022
Country/Territory	Croatia
City	Dubrovnik
Period	5/30/22 → 6/3/22

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work is supported by the MAYA project on the process number 2020/05155-6 via MCTIC/CGI/FAPESP, and by Coordenac¸ão de Aperfeic¸oamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code 001, and by CNPq.

Publisher Copyright:
© 2022 IEEE.

Keywords

body recognition
E-health
Ensemble learning
Machine learning
Signals
wearables

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Instrumentation

UN SDGs

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

Access to Document

10.1109/IWCMC55113.2022.9824669

Cite this

Bastos, L., Martins, B., Medeiros, I., Neto, A., Zeadally, S., Rosario, D., & Cerqueira, E. (2022). Ensemble Learning Method for Human Identification in Wearable Devices. In 2022 International Wireless Communications and Mobile Computing, IWCMC 2022 (pp. 1052-1057). (2022 International Wireless Communications and Mobile Computing, IWCMC 2022). https://doi.org/10.1109/IWCMC55113.2022.9824669

@inproceedings{e312c1fdadcc4e67941cb81e14cd9a6b,

title = "Ensemble Learning Method for Human Identification in Wearable Devices",

abstract = "Wearables today play a key role in E-Health computing, with investments expected to exceed $70 billion by 2024. With the massive use of apps on wearable devices, it is crucial to improve safety when using wearables, considering that important information about user information is stored on these devices. We present SOMEONE ensemble learning, a set machine learning algorithm for body recognition of wearable devices, which operates on the basis of both PhotoPlethysmoGram (PPG) and ElectroCardioGram (ECG) signals. We consider an individual's PPG and ECG signals, where algorithms process these signals stored on the wearable device to identify the user. The SOMEONE algorithm achieves better results on metrics such as F1 score, accuracy, false acceptance rate (FAR) and false rejection rate (FRR) for human recognition in MIMIC dataset of ECG signals and CapnoBase dataset of PPG signal.",

keywords = "body recognition, E-health, Ensemble learning, Machine learning, Signals, wearables",

author = "Lucas Bastos and Bruno Martins and Iago Medeiros and Augusto Neto and Sherali Zeadally and Denis Rosario and Eduardo Cerqueira",

note = "Funding Information: ACKNOWLEDGMENT This work is supported by the MAYA project on the process number 2020/05155-6 via MCTIC/CGI/FAPESP, and by Coordenac¸{\~a}o de Aperfeic¸oamento de Pessoal de N{\'i}vel Superior – Brasil (CAPES) – Finance Code 001, and by CNPq. Publisher Copyright: {\textcopyright} 2022 IEEE.; null ; Conference date: 30-05-2022 Through 03-06-2022",

year = "2022",

doi = "10.1109/IWCMC55113.2022.9824669",

language = "English",

series = "2022 International Wireless Communications and Mobile Computing, IWCMC 2022",

pages = "1052--1057",

booktitle = "2022 International Wireless Communications and Mobile Computing, IWCMC 2022",

}

Bastos, L, Martins, B, Medeiros, I, Neto, A, Zeadally, S, Rosario, D & Cerqueira, E 2022, Ensemble Learning Method for Human Identification in Wearable Devices. in 2022 International Wireless Communications and Mobile Computing, IWCMC 2022. 2022 International Wireless Communications and Mobile Computing, IWCMC 2022, pp. 1052-1057, 18th IEEE International Wireless Communications and Mobile Computing, IWCMC 2022, Dubrovnik, Croatia, 5/30/22. https://doi.org/10.1109/IWCMC55113.2022.9824669

Ensemble Learning Method for Human Identification in Wearable Devices. / Bastos, Lucas; Martins, Bruno; Medeiros, Iago et al.

2022 International Wireless Communications and Mobile Computing, IWCMC 2022. 2022. p. 1052-1057 (2022 International Wireless Communications and Mobile Computing, IWCMC 2022).

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

TY - GEN

T1 - Ensemble Learning Method for Human Identification in Wearable Devices

AU - Bastos, Lucas

AU - Martins, Bruno

AU - Medeiros, Iago

AU - Neto, Augusto

AU - Zeadally, Sherali

AU - Rosario, Denis

AU - Cerqueira, Eduardo

N1 - Funding Information: ACKNOWLEDGMENT This work is supported by the MAYA project on the process number 2020/05155-6 via MCTIC/CGI/FAPESP, and by Coordenac¸ão de Aperfeic¸oamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code 001, and by CNPq. Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - Wearables today play a key role in E-Health computing, with investments expected to exceed $70 billion by 2024. With the massive use of apps on wearable devices, it is crucial to improve safety when using wearables, considering that important information about user information is stored on these devices. We present SOMEONE ensemble learning, a set machine learning algorithm for body recognition of wearable devices, which operates on the basis of both PhotoPlethysmoGram (PPG) and ElectroCardioGram (ECG) signals. We consider an individual's PPG and ECG signals, where algorithms process these signals stored on the wearable device to identify the user. The SOMEONE algorithm achieves better results on metrics such as F1 score, accuracy, false acceptance rate (FAR) and false rejection rate (FRR) for human recognition in MIMIC dataset of ECG signals and CapnoBase dataset of PPG signal.

AB - Wearables today play a key role in E-Health computing, with investments expected to exceed $70 billion by 2024. With the massive use of apps on wearable devices, it is crucial to improve safety when using wearables, considering that important information about user information is stored on these devices. We present SOMEONE ensemble learning, a set machine learning algorithm for body recognition of wearable devices, which operates on the basis of both PhotoPlethysmoGram (PPG) and ElectroCardioGram (ECG) signals. We consider an individual's PPG and ECG signals, where algorithms process these signals stored on the wearable device to identify the user. The SOMEONE algorithm achieves better results on metrics such as F1 score, accuracy, false acceptance rate (FAR) and false rejection rate (FRR) for human recognition in MIMIC dataset of ECG signals and CapnoBase dataset of PPG signal.

KW - body recognition

KW - E-health

KW - Ensemble learning

KW - Machine learning

KW - Signals

KW - wearables

UR - http://www.scopus.com/inward/record.url?scp=85135359454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85135359454&partnerID=8YFLogxK

U2 - 10.1109/IWCMC55113.2022.9824669

DO - 10.1109/IWCMC55113.2022.9824669

M3 - Conference contribution

AN - SCOPUS:85135359454

T3 - 2022 International Wireless Communications and Mobile Computing, IWCMC 2022

SP - 1052

EP - 1057

BT - 2022 International Wireless Communications and Mobile Computing, IWCMC 2022

Y2 - 30 May 2022 through 3 June 2022

ER -

Ensemble Learning Method for Human Identification in Wearable Devices

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this