Toward robust and platform-agnostic gait analysis

Yuchao Ma; Ramin Fallahzadeh; Hassan Ghasemzadeh

doi:10.1109/BSN.2015.7299366

Toward robust and platform-agnostic gait analysis

Yuchao Ma, Ramin Fallahzadeh, Hassan Ghasemzadeh

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

10 Scopus citations

Abstract

Biometric gait analysis using wearable sensors offers an objective and quantitative method for gait parameter extraction. However, current techniques are constrained to specific platform parameters, and hence significantly lack generality, scalability and sustainability. In this paper, we propose a platform-independent and self-adaptive approach for gait cycle detection and cadence estimation. Our algorithm utilizes physical kinematic properties and cyclic patterns of foot acceleration signals to automatically adjust internal parameters of the algorithm. As a result, the proposed approach is robust to noise and changes in sensor platform parameters such as sampling rate and sensor resolution. For the evaluation purpose, we use acceleration signals collected from 16 subjects in a clinical setting to examine the accuracy and robustness of the proposed algorithm. The results show that our approach achieves a precision above 98% and a recall above 95% in stride detection, and an average accuracy of 98% in cadence estimation under various uncertainty conditions such as noisy signals and changes in sampling frequency and sensor resolution.

Original language	English (US)
Title of host publication	2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467372015
DOIs	https://doi.org/10.1109/BSN.2015.7299366
State	Published - Oct 15 2015
Externally published	Yes
Event	12th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015 - Cambridge, United States Duration: Jun 9 2015 → Jun 12 2015

Publication series

Name	2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015

Conference

Conference	12th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015
Country/Territory	United States
City	Cambridge
Period	6/9/15 → 6/12/15

Keywords

cadence estimation
gait analysis
reliability
robustness
stride detection
wearable sensors

ASJC Scopus subject areas

Computer Networks and Communications
Health Informatics
Instrumentation
Signal Processing

Access to Document

10.1109/BSN.2015.7299366

Cite this

Ma, Y., Fallahzadeh, R., & Ghasemzadeh, H. (2015). Toward robust and platform-agnostic gait analysis. In 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015 Article 7299366 (2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BSN.2015.7299366

Toward robust and platform-agnostic gait analysis. / Ma, Yuchao; Fallahzadeh, Ramin; Ghasemzadeh, Hassan.
2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7299366 (2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015).

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

Ma, Y, Fallahzadeh, R & Ghasemzadeh, H 2015, Toward robust and platform-agnostic gait analysis. in 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015., 7299366, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015, Institute of Electrical and Electronics Engineers Inc., 12th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015, Cambridge, United States, 6/9/15. https://doi.org/10.1109/BSN.2015.7299366

Ma Y, Fallahzadeh R, Ghasemzadeh H. Toward robust and platform-agnostic gait analysis. In 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7299366. (2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015). doi: 10.1109/BSN.2015.7299366

Ma, Yuchao ; Fallahzadeh, Ramin ; Ghasemzadeh, Hassan. / Toward robust and platform-agnostic gait analysis. 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015. Institute of Electrical and Electronics Engineers Inc., 2015. (2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015).

@inproceedings{3bf14f94ac9047d3909ce8f48482ecb9,

title = "Toward robust and platform-agnostic gait analysis",

abstract = "Biometric gait analysis using wearable sensors offers an objective and quantitative method for gait parameter extraction. However, current techniques are constrained to specific platform parameters, and hence significantly lack generality, scalability and sustainability. In this paper, we propose a platform-independent and self-adaptive approach for gait cycle detection and cadence estimation. Our algorithm utilizes physical kinematic properties and cyclic patterns of foot acceleration signals to automatically adjust internal parameters of the algorithm. As a result, the proposed approach is robust to noise and changes in sensor platform parameters such as sampling rate and sensor resolution. For the evaluation purpose, we use acceleration signals collected from 16 subjects in a clinical setting to examine the accuracy and robustness of the proposed algorithm. The results show that our approach achieves a precision above 98% and a recall above 95% in stride detection, and an average accuracy of 98% in cadence estimation under various uncertainty conditions such as noisy signals and changes in sampling frequency and sensor resolution.",

keywords = "cadence estimation, gait analysis, reliability, robustness, stride detection, wearable sensors",

author = "Yuchao Ma and Ramin Fallahzadeh and Hassan Ghasemzadeh",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 12th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015 ; Conference date: 09-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "15",

doi = "10.1109/BSN.2015.7299366",

language = "English (US)",

series = "2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015",

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

booktitle = "2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015",

}

TY - GEN

T1 - Toward robust and platform-agnostic gait analysis

AU - Ma, Yuchao

AU - Fallahzadeh, Ramin

AU - Ghasemzadeh, Hassan

PY - 2015/10/15

Y1 - 2015/10/15

N2 - Biometric gait analysis using wearable sensors offers an objective and quantitative method for gait parameter extraction. However, current techniques are constrained to specific platform parameters, and hence significantly lack generality, scalability and sustainability. In this paper, we propose a platform-independent and self-adaptive approach for gait cycle detection and cadence estimation. Our algorithm utilizes physical kinematic properties and cyclic patterns of foot acceleration signals to automatically adjust internal parameters of the algorithm. As a result, the proposed approach is robust to noise and changes in sensor platform parameters such as sampling rate and sensor resolution. For the evaluation purpose, we use acceleration signals collected from 16 subjects in a clinical setting to examine the accuracy and robustness of the proposed algorithm. The results show that our approach achieves a precision above 98% and a recall above 95% in stride detection, and an average accuracy of 98% in cadence estimation under various uncertainty conditions such as noisy signals and changes in sampling frequency and sensor resolution.

AB - Biometric gait analysis using wearable sensors offers an objective and quantitative method for gait parameter extraction. However, current techniques are constrained to specific platform parameters, and hence significantly lack generality, scalability and sustainability. In this paper, we propose a platform-independent and self-adaptive approach for gait cycle detection and cadence estimation. Our algorithm utilizes physical kinematic properties and cyclic patterns of foot acceleration signals to automatically adjust internal parameters of the algorithm. As a result, the proposed approach is robust to noise and changes in sensor platform parameters such as sampling rate and sensor resolution. For the evaluation purpose, we use acceleration signals collected from 16 subjects in a clinical setting to examine the accuracy and robustness of the proposed algorithm. The results show that our approach achieves a precision above 98% and a recall above 95% in stride detection, and an average accuracy of 98% in cadence estimation under various uncertainty conditions such as noisy signals and changes in sampling frequency and sensor resolution.

KW - cadence estimation

KW - gait analysis

KW - reliability

KW - robustness

KW - stride detection

KW - wearable sensors

UR - http://www.scopus.com/inward/record.url?scp=84961595315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961595315&partnerID=8YFLogxK

U2 - 10.1109/BSN.2015.7299366

DO - 10.1109/BSN.2015.7299366

M3 - Conference contribution

AN - SCOPUS:84961595315

T3 - 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015

BT - 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2015

Y2 - 9 June 2015 through 12 June 2015

ER -

Toward robust and platform-agnostic gait analysis

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this