Methodology and validation for identifying gait type using machine learning on IMU data

Research output: Contribution to journalArticle

Abstract

With the rising popularity of activity tracking, there is a desire to not only count the number of steps a person takes, but also identify the type of step (e.g., walking or running) they are taking. For rehabilitation and athletic training, this difference is important to the prescribed regiment. Fourteen healthy adults walked, jogged and ran on a treadmill at three different constant speeds (1.21, 2.01, 2.68 m/s) for 90 s. An inertial measurement unit (IMU) with accelerometer and gyroscope was affixed to their left ankle. Collected acceleration and angular velocity data were partitioned into individual time-normalised strides. These data were used as features in the artificial neural network (ANN) that classified the type of stride. Several ANN models were tested: using only acceleration, only angular velocity and both. Using primarily acceleration data in the trained ANN yielded the best results (>94% correct stride-type identification) after cross-validation. The ANN models were able to accurately classify the gait type of each stride using a single wearable IMU. The accuracy of the method should improve further as more data is added to the ANN training.

Original languageEnglish (US)
Pages (from-to)25-32
Number of pages8
JournalJournal of Medical Engineering and Technology
Volume43
Issue number1
DOIs
StatePublished - Jan 2 2019

Fingerprint

Units of measurement
Learning systems
Neural networks
Angular velocity
Exercise equipment
Gyroscopes
Accelerometers
Patient rehabilitation
Identification (control systems)

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

@article{883e5d57efe647ceaaab9de7578f82b6,
title = "Methodology and validation for identifying gait type using machine learning on IMU data",
abstract = "With the rising popularity of activity tracking, there is a desire to not only count the number of steps a person takes, but also identify the type of step (e.g., walking or running) they are taking. For rehabilitation and athletic training, this difference is important to the prescribed regiment. Fourteen healthy adults walked, jogged and ran on a treadmill at three different constant speeds (1.21, 2.01, 2.68 m/s) for 90 s. An inertial measurement unit (IMU) with accelerometer and gyroscope was affixed to their left ankle. Collected acceleration and angular velocity data were partitioned into individual time-normalised strides. These data were used as features in the artificial neural network (ANN) that classified the type of stride. Several ANN models were tested: using only acceleration, only angular velocity and both. Using primarily acceleration data in the trained ANN yielded the best results (>94{\%} correct stride-type identification) after cross-validation. The ANN models were able to accurately classify the gait type of each stride using a single wearable IMU. The accuracy of the method should improve further as more data is added to the ANN training.",
author = "Mahoney, {Joseph Michael} and Rhudy, {Matthew Brandon}",
year = "2019",
month = "1",
day = "2",
doi = "10.1080/03091902.2019.1599073",
language = "English (US)",
volume = "43",
pages = "25--32",
journal = "Journal of Medical Engineering and Technology",
issn = "0309-1902",
publisher = "Informa Healthcare",
number = "1",

}

TY - JOUR

T1 - Methodology and validation for identifying gait type using machine learning on IMU data

AU - Mahoney, Joseph Michael

AU - Rhudy, Matthew Brandon

PY - 2019/1/2

Y1 - 2019/1/2

N2 - With the rising popularity of activity tracking, there is a desire to not only count the number of steps a person takes, but also identify the type of step (e.g., walking or running) they are taking. For rehabilitation and athletic training, this difference is important to the prescribed regiment. Fourteen healthy adults walked, jogged and ran on a treadmill at three different constant speeds (1.21, 2.01, 2.68 m/s) for 90 s. An inertial measurement unit (IMU) with accelerometer and gyroscope was affixed to their left ankle. Collected acceleration and angular velocity data were partitioned into individual time-normalised strides. These data were used as features in the artificial neural network (ANN) that classified the type of stride. Several ANN models were tested: using only acceleration, only angular velocity and both. Using primarily acceleration data in the trained ANN yielded the best results (>94% correct stride-type identification) after cross-validation. The ANN models were able to accurately classify the gait type of each stride using a single wearable IMU. The accuracy of the method should improve further as more data is added to the ANN training.

AB - With the rising popularity of activity tracking, there is a desire to not only count the number of steps a person takes, but also identify the type of step (e.g., walking or running) they are taking. For rehabilitation and athletic training, this difference is important to the prescribed regiment. Fourteen healthy adults walked, jogged and ran on a treadmill at three different constant speeds (1.21, 2.01, 2.68 m/s) for 90 s. An inertial measurement unit (IMU) with accelerometer and gyroscope was affixed to their left ankle. Collected acceleration and angular velocity data were partitioned into individual time-normalised strides. These data were used as features in the artificial neural network (ANN) that classified the type of stride. Several ANN models were tested: using only acceleration, only angular velocity and both. Using primarily acceleration data in the trained ANN yielded the best results (>94% correct stride-type identification) after cross-validation. The ANN models were able to accurately classify the gait type of each stride using a single wearable IMU. The accuracy of the method should improve further as more data is added to the ANN training.

UR - http://www.scopus.com/inward/record.url?scp=85065178277&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065178277&partnerID=8YFLogxK

U2 - 10.1080/03091902.2019.1599073

DO - 10.1080/03091902.2019.1599073

M3 - Article

C2 - 31037995

AN - SCOPUS:85065178277

VL - 43

SP - 25

EP - 32

JO - Journal of Medical Engineering and Technology

JF - Journal of Medical Engineering and Technology

SN - 0309-1902

IS - 1

ER -