Human activity recognition based on wrist PPG via the ensemble method

被引：12

作者：

Almanifi, Omair Rashed Abdulwareth ^{[1
]}

Khairuddin, Ismail Mohd ^{[1
]}

Razman, Mohd Azraai Mohd ^{[1
]}

Musa, Rabiu Muazu ^{[2
]}

Majeed, Anwar P. P. Abdul ^{[1
,3
,4
,5
,6
]}

机构：

[1] Univ Malaysia Pahang, Fac Mfg & Mechatron Engn Technol, Innovat Mfg Mechatron & Sports Lab, Pahang, Pahang Darul Ma, Malaysia

[2] Univ Malaysia Terengganu, Ctr Fundamental & Continuing Educ, Dept Credited Cocurriculum, Terengganu, Malaysia

[3] Xian Jiaotong Liverpool Univ, Sch Robot, XJTLU Entrepreneur Coll Taicang, Suzhou 215123, Peoples R China

[4] Cardiff Metropolitan Univ, EUREKA Robot Ctr, Cardiff Sch Technol, Cardiff, Wales

[5] Univ Malaysia Pahang, Ctr Software Dev & Integrated Comp, Gambang, Pahang Darul Ma, Malaysia

[6] UCSI Univ, Fac Engn Technol & Built Environm, Kuala Lumpur Campus, Kuala Lumpur, Malaysia

来源：

ICT EXPRESS | 2022年 / 8卷 / 04期

关键词：

HAR; Exercise; PPG; ECG; Classification; Ensemble; Machine learning; Transfer learning;

D O I：

10.1016/j.icte.2022.03.006

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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. (C) 2022 The Author(s). Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences.

引用

页码：513 / 517

页数：5

共 15 条

[1]

Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265

[2] Human Activity Analysis: A Review [J].

Aggarwal, J. K. ;

Ryoo, M. S. .

ACM COMPUTING SURVEYS, 2011, 43 (03)

[3]

Albawi S, 2017, I C ENG TECHNOL

[4]

Alian A.A., 2014, Monitoring Technologies in Acute Care Environments: A Comprehensive Guide to Patient Monitoring Technology, P165, DOI 10.1007/978-1-4614-8557-519

[5]

[Anonymous], 2017, NUMPY NUMPY NUMPY NU, DOI [10.1017/CBO9781107415324.004, DOI 10.1017/CBO9781107415324.004]

[6]

Brophy E, 2018, 2018 29TH IRISH SIGNALS AND SYSTEMS CONFERENCE (ISSC)

[7]

Chollet F, 2015, Keras Documentation

[8] ON THE THEORY OF THE ELECTROCARDIOGRAM [J].

GESELOWITZ, DB .

PROCEEDINGS OF THE IEEE, 1989, 77 (06) :857-876

[9] Description of a database containing wrist PPG signals recorded during physical exercise with both accelerometer and gyroscope measures of motion [J].

Jarchi, Delaram ;

Casson, Alexander J. .

Data, 2017, 2 (01)

[10]

Jia R., 2013, 2013 IEEE Int. Conf. Signal Process. Commun. Comput. ICSPCC 2013, P1, DOI DOI 10.1109/ICSPCC.2013.6664056

← 1 2 →