Detection of Gait Phases Using Orient Specks for Mobile Clinical Gait Analysis

R.L. Evans; D.K. Arvind

doi:10.1109/BSN.2014.22

Detection of Gait Phases Using Orient Specks for Mobile Clinical Gait Analysis

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

Abstract

This paper presents a hybrid method based on a feed-forward neural network (FNN) embedded in a hidden Markov model (HMM), for detecting phases in a gait cycle, based on data from inertial sensors attached to the lower body. The method was validated against the ground truth obtained concurrently from a Vicon optical motion capture system for five volunteers. The method was characterised using metrics such as sensitivity and specificity for sensor placements, and gait analysis. The results demonstrate that the proposed method is accurate within 23 milliseconds with the added advantages of mobility afforded by wireless sensors and the flexibility of the classification method.

Original language	English
Title of host publication	Wearable and Implantable Body Sensor Networks (BSN), 2014 11th International Conference on
Publisher	Institute of Electrical and Electronics Engineers
Pages	149-154
Number of pages	6
ISBN (Print)	978-1-4799-4932-8
DOIs	https://doi.org/10.1109/BSN.2014.22
Publication status	Published - Jun 2014

Keywords / Materials (for Non-textual outputs)

biomedical telemetry
body sensor networks
feedforward neural nets
gait analysis
hidden Markov models
medical signal processing
portable instruments
signal classification
telemedicine
FNN embedding
HMM
Orient specks
Vicon optical motion capture system
classification method flexibility
feedforward neural network
gait cycle
gait phase detection
hidden Markov model
hybrid method
lower body inertial sensor
mobile clinical gait analysis
mobility
sensitivity metrics
sensor placements
specificity metrics
wireless sensors
Hidden Markov models
Neural networks
Phase detection
Sensitivity
Sensitivity and specificity
Sensors
Training
feed-forward neural network
inertial sensors
mobile gait analysis

Access to Document

10.1109/BSN.2014.22

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6855633

D K Arvind
- School of Informatics - Chair of Distributed Wireless Computation
- Artificial Intelligence and its Applications Institute
- Data Science and Artificial Intelligence
Person: Academic: Research Active

Cite this

@inproceedings{c901daa18a6e457c93e5f37ac6d61cf1,

title = "Detection of Gait Phases Using Orient Specks for Mobile Clinical Gait Analysis",

abstract = "This paper presents a hybrid method based on a feed-forward neural network (FNN) embedded in a hidden Markov model (HMM), for detecting phases in a gait cycle, based on data from inertial sensors attached to the lower body. The method was validated against the ground truth obtained concurrently from a Vicon optical motion capture system for five volunteers. The method was characterised using metrics such as sensitivity and specificity for sensor placements, and gait analysis. The results demonstrate that the proposed method is accurate within 23 milliseconds with the added advantages of mobility afforded by wireless sensors and the flexibility of the classification method.",

keywords = "biomedical telemetry, body sensor networks, feedforward neural nets, gait analysis, hidden Markov models, medical signal processing, portable instruments, signal classification, telemedicine, FNN embedding, HMM, Orient specks, Vicon optical motion capture system, classification method flexibility, feedforward neural network, gait cycle, gait phase detection, hidden Markov model, hybrid method, lower body inertial sensor, mobile clinical gait analysis, mobility, sensitivity metrics, sensor placements, specificity metrics, wireless sensors, Hidden Markov models, Neural networks, Phase detection, Sensitivity, Sensitivity and specificity, Sensors, Training, feed-forward neural network, inertial sensors, mobile gait analysis",

author = "R.L. Evans and D.K. Arvind",

year = "2014",

month = jun,

doi = "10.1109/BSN.2014.22",

language = "English",

isbn = "978-1-4799-4932-8",

pages = "149--154",

booktitle = "Wearable and Implantable Body Sensor Networks (BSN), 2014 11th International Conference on",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

TY - GEN

T1 - Detection of Gait Phases Using Orient Specks for Mobile Clinical Gait Analysis

AU - Evans, R.L.

AU - Arvind, D.K.

PY - 2014/6

Y1 - 2014/6

N2 - This paper presents a hybrid method based on a feed-forward neural network (FNN) embedded in a hidden Markov model (HMM), for detecting phases in a gait cycle, based on data from inertial sensors attached to the lower body. The method was validated against the ground truth obtained concurrently from a Vicon optical motion capture system for five volunteers. The method was characterised using metrics such as sensitivity and specificity for sensor placements, and gait analysis. The results demonstrate that the proposed method is accurate within 23 milliseconds with the added advantages of mobility afforded by wireless sensors and the flexibility of the classification method.

AB - This paper presents a hybrid method based on a feed-forward neural network (FNN) embedded in a hidden Markov model (HMM), for detecting phases in a gait cycle, based on data from inertial sensors attached to the lower body. The method was validated against the ground truth obtained concurrently from a Vicon optical motion capture system for five volunteers. The method was characterised using metrics such as sensitivity and specificity for sensor placements, and gait analysis. The results demonstrate that the proposed method is accurate within 23 milliseconds with the added advantages of mobility afforded by wireless sensors and the flexibility of the classification method.

KW - biomedical telemetry

KW - body sensor networks

KW - feedforward neural nets

KW - gait analysis

KW - hidden Markov models

KW - medical signal processing

KW - portable instruments

KW - signal classification

KW - telemedicine

KW - FNN embedding

KW - HMM

KW - Orient specks

KW - Vicon optical motion capture system

KW - classification method flexibility

KW - feedforward neural network

KW - gait cycle

KW - gait phase detection

KW - hidden Markov model

KW - hybrid method

KW - lower body inertial sensor

KW - mobile clinical gait analysis

KW - mobility

KW - sensitivity metrics

KW - sensor placements

KW - specificity metrics

KW - wireless sensors

KW - Hidden Markov models

KW - Neural networks

KW - Phase detection

KW - Sensitivity

KW - Sensitivity and specificity

KW - Sensors

KW - Training

KW - feed-forward neural network

KW - inertial sensors

KW - mobile gait analysis

U2 - 10.1109/BSN.2014.22

DO - 10.1109/BSN.2014.22

M3 - Conference contribution

SN - 978-1-4799-4932-8

SP - 149

EP - 154

BT - Wearable and Implantable Body Sensor Networks (BSN), 2014 11th International Conference on

PB - Institute of Electrical and Electronics Engineers

ER -

Detection of Gait Phases Using Orient Specks for Mobile Clinical Gait Analysis

Abstract

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Profiles

D K Arvind

Cite this