Human activity recognition based on wrist PPG via the ensemble method

Omair Rashed Abdulwareth Almanifi; Ismail Mohd Khairuddin; Mohd Azraai Mohd Razman; Rabiu Muazu Musa; Anwar P.P. Abdul Majeed

doi:10.1016/j.icte.2022.03.006

Human activity recognition based on wrist PPG via the ensemble method

Omair Rashed Abdulwareth Almanifi, Ismail Mohd Khairuddin, Mohd Azraai Mohd Razman, Rabiu Muazu Musa, Anwar P.P. Abdul Majeed^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

16 Citations (Scopus)

Abstract

Human activity recognition via Electrocardiography (ECG) and Photoplethysmography (PPG) is extensively researched. While ECG requires less filtering and is less prone to disturbance and artifacts, nonetheless, PPG is cheaper and widely available in smart devices, making it a desired alternative. In this study, we explore the employment of the ensemble method with several pre-trained machine learning models namely Resnet50V2, MobileNetV2, and Xception for the classification of wrist PPG data of human activity, in comparison to its ECG counterpart. The study produced promising results with a test classification accuracy of 88.91% and 94.28% for PPG and ECG, respectively.

Original language	English
Pages (from-to)	513-517
Number of pages	5
Journal	ICT Express
Volume	8
Issue number	4
DOIs	https://doi.org/10.1016/j.icte.2022.03.006
Publication status	Accepted/In press - 2022

Keywords

Classification
ECG
Ensemble
Exercise
HAR
Machine learning
PPG
Transfer learning

Access to Document

10.1016/j.icte.2022.03.006

Cite this

@article{a3ca8fef704b4c28978afbe7fcb106cd,

title = "Human activity recognition based on wrist PPG via the ensemble method",

abstract = "Human activity recognition via Electrocardiography (ECG) and Photoplethysmography (PPG) is extensively researched. While ECG requires less filtering and is less prone to disturbance and artifacts, nonetheless, PPG is cheaper and widely available in smart devices, making it a desired alternative. In this study, we explore the employment of the ensemble method with several pre-trained machine learning models namely Resnet50V2, MobileNetV2, and Xception for the classification of wrist PPG data of human activity, in comparison to its ECG counterpart. The study produced promising results with a test classification accuracy of 88.91% and 94.28% for PPG and ECG, respectively.",

keywords = "Classification, ECG, Ensemble, Exercise, HAR, Machine learning, PPG, Transfer learning",

author = "Almanifi, {Omair Rashed Abdulwareth} and {Mohd Khairuddin}, Ismail and {Mohd Razman}, {Mohd Azraai} and Musa, {Rabiu Muazu} and {P.P. Abdul Majeed}, Anwar",

note = "Funding Information: The authors would like to give a special thanks to the providers of the dataset; Wrist PPG During Exercise [7]. Publisher Copyright: {\textcopyright} 2022 The Author(s)",

year = "2022",

doi = "10.1016/j.icte.2022.03.006",

language = "English",

volume = "8",

pages = "513--517",

journal = "ICT Express",

issn = "2405-9595",

number = "4",

}

TY - JOUR

T1 - Human activity recognition based on wrist PPG via the ensemble method

AU - Almanifi, Omair Rashed Abdulwareth

AU - Mohd Khairuddin, Ismail

AU - Mohd Razman, Mohd Azraai

AU - Musa, Rabiu Muazu

AU - P.P. Abdul Majeed, Anwar

PY - 2022

Y1 - 2022

N2 - Human activity recognition via Electrocardiography (ECG) and Photoplethysmography (PPG) is extensively researched. While ECG requires less filtering and is less prone to disturbance and artifacts, nonetheless, PPG is cheaper and widely available in smart devices, making it a desired alternative. In this study, we explore the employment of the ensemble method with several pre-trained machine learning models namely Resnet50V2, MobileNetV2, and Xception for the classification of wrist PPG data of human activity, in comparison to its ECG counterpart. The study produced promising results with a test classification accuracy of 88.91% and 94.28% for PPG and ECG, respectively.

AB - Human activity recognition via Electrocardiography (ECG) and Photoplethysmography (PPG) is extensively researched. While ECG requires less filtering and is less prone to disturbance and artifacts, nonetheless, PPG is cheaper and widely available in smart devices, making it a desired alternative. In this study, we explore the employment of the ensemble method with several pre-trained machine learning models namely Resnet50V2, MobileNetV2, and Xception for the classification of wrist PPG data of human activity, in comparison to its ECG counterpart. The study produced promising results with a test classification accuracy of 88.91% and 94.28% for PPG and ECG, respectively.

KW - Classification

KW - ECG

KW - Ensemble

KW - Exercise

KW - HAR

KW - Machine learning

KW - PPG

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85127321203&partnerID=8YFLogxK

U2 - 10.1016/j.icte.2022.03.006

DO - 10.1016/j.icte.2022.03.006

M3 - Article

AN - SCOPUS:85127321203

SN - 2405-9595

VL - 8

SP - 513

EP - 517

JO - ICT Express

JF - ICT Express

IS - 4

ER -

Human activity recognition based on wrist PPG via the ensemble method

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this