A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier

N. Shibuya; B. T. Nukala; A. I. Rodriguez; J. Tsay; T. Q. Nguyen; S. Zupancic; D. Y.C. Lie

doi:10.1109/ICMU.2015.7061032

A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier

N. Shibuya, B. T. Nukala, A. I. Rodriguez, J. Tsay, T. Q. Nguyen, S. Zupancic, D. Y.C. Lie

Electrical and Computer Engineering

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

56 Scopus citations

Abstract

In this study, we report a custom designed wireless gait analysis sensor (WGAS) system for real-time fall detection using a Support Vector Machine (SVM) classifier. Our WGAS includes a tri-axial accelerometer, 2 gyroscopes and a MSP430 micro-controller. It was worn by the subjects at either the T4 or at the waist level for various intentional falls, Activities of Daily Living (ADL) and the Dynamic Gait Index (DGI) test. The raw data of tri-axial acceleration and angular velocity is wirelessly transmitted from the WGAS to a nearby PC, and then 6 features were extracted for fall classification using a SVM (Support Vector Machine) classifier. We achieved 98.8% and 98.7% fall classification accuracies from the data at the T4 and belt positions, respectively. Moreover, the preliminary data demonstrates an impressive overall specificity of 99.5% and an overall sensitivity of 97.0% for this WGAS real-time fall detection system.

Original language	English
Title of host publication	2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	66-67
Number of pages	2
ISBN (Electronic)	9784907626129
DOIs	https://doi.org/10.1109/ICMU.2015.7061032
State	Published - Mar 13 2015
Event	2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015 - Hakodate, Japan Duration: Jan 20 2015 → Jan 22 2015

Publication series

Name	2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015

Conference

Conference	2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015
Country/Territory	Japan
City	Hakodate
Period	01/20/15 → 01/22/15

Access to Document

10.1109/ICMU.2015.7061032

Cite this

Shibuya, N., Nukala, B. T., Rodriguez, A. I., Tsay, J., Nguyen, T. Q., Zupancic, S., & Lie, D. Y. C. (2015). A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier. In 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015 (pp. 66-67). Article 7061032 (2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMU.2015.7061032

Shibuya, N. ; Nukala, B. T. ; Rodriguez, A. I. et al. / A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier. 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 66-67 (2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015).

@inproceedings{1e191981c37c4b99b28ba07af08ee1ff,

title = "A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier",

abstract = "In this study, we report a custom designed wireless gait analysis sensor (WGAS) system for real-time fall detection using a Support Vector Machine (SVM) classifier. Our WGAS includes a tri-axial accelerometer, 2 gyroscopes and a MSP430 micro-controller. It was worn by the subjects at either the T4 or at the waist level for various intentional falls, Activities of Daily Living (ADL) and the Dynamic Gait Index (DGI) test. The raw data of tri-axial acceleration and angular velocity is wirelessly transmitted from the WGAS to a nearby PC, and then 6 features were extracted for fall classification using a SVM (Support Vector Machine) classifier. We achieved 98.8% and 98.7% fall classification accuracies from the data at the T4 and belt positions, respectively. Moreover, the preliminary data demonstrates an impressive overall specificity of 99.5% and an overall sensitivity of 97.0% for this WGAS real-time fall detection system.",

author = "N. Shibuya and Nukala, {B. T.} and Rodriguez, {A. I.} and J. Tsay and Nguyen, {T. Q.} and S. Zupancic and Lie, {D. Y.C.}",

note = "Publisher Copyright: {\textcopyright} 2015 IPSJ.; 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015 ; Conference date: 20-01-2015 Through 22-01-2015",

year = "2015",

month = mar,

day = "13",

doi = "10.1109/ICMU.2015.7061032",

language = "English",

series = "2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015",

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

pages = "66--67",

booktitle = "2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015",

}

Shibuya, N, Nukala, BT, Rodriguez, AI, Tsay, J, Nguyen, TQ, Zupancic, S & Lie, DYC 2015, A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier. in 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015., 7061032, 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015, Institute of Electrical and Electronics Engineers Inc., pp. 66-67, 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015, Hakodate, Japan, 01/20/15. https://doi.org/10.1109/ICMU.2015.7061032

A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier. / Shibuya, N.; Nukala, B. T.; Rodriguez, A. I. et al.
2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 66-67 7061032 (2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015).

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

TY - GEN

T1 - A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier

AU - Shibuya, N.

AU - Nukala, B. T.

AU - Rodriguez, A. I.

AU - Tsay, J.

AU - Nguyen, T. Q.

AU - Zupancic, S.

AU - Lie, D. Y.C.

PY - 2015/3/13

Y1 - 2015/3/13

N2 - In this study, we report a custom designed wireless gait analysis sensor (WGAS) system for real-time fall detection using a Support Vector Machine (SVM) classifier. Our WGAS includes a tri-axial accelerometer, 2 gyroscopes and a MSP430 micro-controller. It was worn by the subjects at either the T4 or at the waist level for various intentional falls, Activities of Daily Living (ADL) and the Dynamic Gait Index (DGI) test. The raw data of tri-axial acceleration and angular velocity is wirelessly transmitted from the WGAS to a nearby PC, and then 6 features were extracted for fall classification using a SVM (Support Vector Machine) classifier. We achieved 98.8% and 98.7% fall classification accuracies from the data at the T4 and belt positions, respectively. Moreover, the preliminary data demonstrates an impressive overall specificity of 99.5% and an overall sensitivity of 97.0% for this WGAS real-time fall detection system.

AB - In this study, we report a custom designed wireless gait analysis sensor (WGAS) system for real-time fall detection using a Support Vector Machine (SVM) classifier. Our WGAS includes a tri-axial accelerometer, 2 gyroscopes and a MSP430 micro-controller. It was worn by the subjects at either the T4 or at the waist level for various intentional falls, Activities of Daily Living (ADL) and the Dynamic Gait Index (DGI) test. The raw data of tri-axial acceleration and angular velocity is wirelessly transmitted from the WGAS to a nearby PC, and then 6 features were extracted for fall classification using a SVM (Support Vector Machine) classifier. We achieved 98.8% and 98.7% fall classification accuracies from the data at the T4 and belt positions, respectively. Moreover, the preliminary data demonstrates an impressive overall specificity of 99.5% and an overall sensitivity of 97.0% for this WGAS real-time fall detection system.

UR - http://www.scopus.com/inward/record.url?scp=84926435344&partnerID=8YFLogxK

U2 - 10.1109/ICMU.2015.7061032

DO - 10.1109/ICMU.2015.7061032

M3 - Conference contribution

AN - SCOPUS:84926435344

T3 - 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015

SP - 66

EP - 67

BT - 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015

Y2 - 20 January 2015 through 22 January 2015

ER -

Shibuya N, Nukala BT, Rodriguez AI, Tsay J, Nguyen TQ, Zupancic S et al. A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier. In 2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 66-67. 7061032. (2015 8th International Conference on Mobile Computing and Ubiquitous Networking, ICMU 2015). doi: 10.1109/ICMU.2015.7061032

A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this