A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System

Xiaoqing Chai; Boon Giin Lee; Matthew Pike; Renjie Wu; Xian Wu

doi:10.1109/ICPECA56706.2023.10075997

A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System

Xiaoqing Chai, Boon Giin Lee, Matthew Pike, Renjie Wu, Xian Wu

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

Abstract

Falling has become the leading cause of non-fatal and preventable injuries. The majority of existing fall detection systems (FDSs) rely on motion sensors. However, most of the applied feature extraction methods result in longer processing time and higher computation. This study proposes a novel attitude feature extraction (AFE) method that extract five feature sets from 54 raw measurements obtained from nine inertial measurement units (IMUs) placed on the firefighter's protective clothing. Our results indicate that the metrics of attitude feature extraction (AFEM) method outperforms the existing metrics of raw feature extraction (RFEM) method in the fall detection. In addition, the proposed method reduces the algorithm processing time and computations significantly. This enables on-device fall detection classification on constrained processing architectures.

Original language	English
Title of host publication	2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	99-103
Number of pages	5
ISBN (Electronic)	9781665472784
DOIs	https://doi.org/10.1109/ICPECA56706.2023.10075997
Publication status	Published - 2023
Event	3rd IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2023 - Shenyang, China Duration: 29 Jan 2023 → 31 Jan 2023

Publication series

Name	2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023

Conference

Conference	3rd IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2023
Country/Territory	China
City	Shenyang
Period	29/01/23 → 31/01/23

Keywords

Fall Detection System (FDS)
Feature Extraction
Inertial Measurement Unit (IMU)
Machine-Learning

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems and Management
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Control and Optimization

Access to Document

10.1109/ICPECA56706.2023.10075997

Cite this

Chai, X., Lee, B. G., Pike, M., Wu, R., & Wu, X. (2023). A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System. In 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023 (pp. 99-103). (2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPECA56706.2023.10075997

Chai, Xiaoqing ; Lee, Boon Giin ; Pike, Matthew et al. / A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System. 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 99-103 (2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023).

@inproceedings{e7c50e6c5cb748d3a60fa902845a61a5,

title = "A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System",

abstract = "Falling has become the leading cause of non-fatal and preventable injuries. The majority of existing fall detection systems (FDSs) rely on motion sensors. However, most of the applied feature extraction methods result in longer processing time and higher computation. This study proposes a novel attitude feature extraction (AFE) method that extract five feature sets from 54 raw measurements obtained from nine inertial measurement units (IMUs) placed on the firefighter's protective clothing. Our results indicate that the metrics of attitude feature extraction (AFEM) method outperforms the existing metrics of raw feature extraction (RFEM) method in the fall detection. In addition, the proposed method reduces the algorithm processing time and computations significantly. This enables on-device fall detection classification on constrained processing architectures.",

keywords = "Fall Detection System (FDS), Feature Extraction, Inertial Measurement Unit (IMU), Machine-Learning",

author = "Xiaoqing Chai and Lee, {Boon Giin} and Matthew Pike and Renjie Wu and Xian Wu",

note = "Funding Information: ACKNOWLEDGEMENT This research was supported by the Zhejiang Provincial Natural Science Foundation of China under Grant No. LQ21F020024; This work is supported by Ningbo Science and Technology Bureau under Major ST Program with project code 2021Z037; This work is supported by Ningbo Science and Technology Bureau under Commonweal Program with project code 2021S140. Publisher Copyright: {\textcopyright} 2023 IEEE.; 3rd IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2023 ; Conference date: 29-01-2023 Through 31-01-2023",

year = "2023",

doi = "10.1109/ICPECA56706.2023.10075997",

language = "English",

series = "2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023",

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

pages = "99--103",

booktitle = "2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023",

address = "United States",

}

Chai, X , Lee, BG , Pike, M , Wu, R & Wu, X 2023, A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System. in 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023. 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023, Institute of Electrical and Electronics Engineers Inc., pp. 99-103, 3rd IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2023, Shenyang, China, 29/01/23. https://doi.org/10.1109/ICPECA56706.2023.10075997

A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System. / Chai, Xiaoqing ; Lee, Boon Giin ; Pike, Matthew et al.
2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 99-103 (2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023).

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

TY - GEN

T1 - A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System

AU - Chai, Xiaoqing

AU - Lee, Boon Giin

AU - Pike, Matthew

AU - Wu, Renjie

AU - Wu, Xian

N1 - Funding Information: ACKNOWLEDGEMENT This research was supported by the Zhejiang Provincial Natural Science Foundation of China under Grant No. LQ21F020024; This work is supported by Ningbo Science and Technology Bureau under Major ST Program with project code 2021Z037; This work is supported by Ningbo Science and Technology Bureau under Commonweal Program with project code 2021S140. Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - Falling has become the leading cause of non-fatal and preventable injuries. The majority of existing fall detection systems (FDSs) rely on motion sensors. However, most of the applied feature extraction methods result in longer processing time and higher computation. This study proposes a novel attitude feature extraction (AFE) method that extract five feature sets from 54 raw measurements obtained from nine inertial measurement units (IMUs) placed on the firefighter's protective clothing. Our results indicate that the metrics of attitude feature extraction (AFEM) method outperforms the existing metrics of raw feature extraction (RFEM) method in the fall detection. In addition, the proposed method reduces the algorithm processing time and computations significantly. This enables on-device fall detection classification on constrained processing architectures.

AB - Falling has become the leading cause of non-fatal and preventable injuries. The majority of existing fall detection systems (FDSs) rely on motion sensors. However, most of the applied feature extraction methods result in longer processing time and higher computation. This study proposes a novel attitude feature extraction (AFE) method that extract five feature sets from 54 raw measurements obtained from nine inertial measurement units (IMUs) placed on the firefighter's protective clothing. Our results indicate that the metrics of attitude feature extraction (AFEM) method outperforms the existing metrics of raw feature extraction (RFEM) method in the fall detection. In addition, the proposed method reduces the algorithm processing time and computations significantly. This enables on-device fall detection classification on constrained processing architectures.

KW - Fall Detection System (FDS)

KW - Feature Extraction

KW - Inertial Measurement Unit (IMU)

KW - Machine-Learning

UR - http://www.scopus.com/inward/record.url?scp=85152223811&partnerID=8YFLogxK

U2 - 10.1109/ICPECA56706.2023.10075997

DO - 10.1109/ICPECA56706.2023.10075997

M3 - Conference contribution

AN - SCOPUS:85152223811

T3 - 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023

SP - 99

EP - 103

BT - 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2023

Y2 - 29 January 2023 through 31 January 2023

ER -

Chai X , Lee BG , Pike M , Wu R, Wu X. A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System. In 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 99-103. (2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications, ICPECA 2023). doi: 10.1109/ICPECA56706.2023.10075997

A Novel Attitude Feature Extraction Method for Multi-IMU Based Fall Detection System

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this