Knee angle estimation based on imu data and artificial neural networks

Christopher Bennett, Crispin Odom, Matan Ben-Asher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

The measurement of joint angles is of profound importance in analysis of human gait. However, currently these measurements can be acquired only with the use of dedicated measuring devices such as a goniometer or in a gait lab with a motion capture system. The low-cost and portability of recent IMU technology makes them ideal for continuous monitoring of kinematic data. In this research we present an algorithm for estimating knee angles based on IMU data with the use of artificial neural networks. Two IMUs with tri-axis accelerometers and gyroscopes were used above and below the knee under investigation. Simultaneously, an electro-goniometer was used to measure the angle, acquired at 64 Hz. A feed-forward ANN with one hidden layer was fed IMU data from 25 of the acquired steps as inputs and trained against the goniometer angles. The ANN was evaluated on 25 trials for a single subject. The estimated knee angle exhibited strong correlation and minimal error compared to the actual angle.

Original languageEnglish
Title of host publicationProceedings - 29th Southern Biomedical Engineering Conference, SBEC 2013
Pages111-112
Number of pages2
DOIs
StatePublished - Aug 5 2013
Event29th Southern Biomedical Engineering Conference, SBEC 2013 - Miami, FL, United States
Duration: May 3 2013May 5 2013

Other

Other29th Southern Biomedical Engineering Conference, SBEC 2013
CountryUnited States
CityMiami, FL
Period5/3/135/5/13

Fingerprint

Goniometers
Neural networks
Gyroscopes
Accelerometers
Kinematics
Monitoring
Costs

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Bennett, C., Odom, C., & Ben-Asher, M. (2013). Knee angle estimation based on imu data and artificial neural networks. In Proceedings - 29th Southern Biomedical Engineering Conference, SBEC 2013 (pp. 111-112). [6525701] https://doi.org/10.1109/SBEC.2013.64

Knee angle estimation based on imu data and artificial neural networks. / Bennett, Christopher; Odom, Crispin; Ben-Asher, Matan.

Proceedings - 29th Southern Biomedical Engineering Conference, SBEC 2013. 2013. p. 111-112 6525701.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bennett, C, Odom, C & Ben-Asher, M 2013, Knee angle estimation based on imu data and artificial neural networks. in Proceedings - 29th Southern Biomedical Engineering Conference, SBEC 2013., 6525701, pp. 111-112, 29th Southern Biomedical Engineering Conference, SBEC 2013, Miami, FL, United States, 5/3/13. https://doi.org/10.1109/SBEC.2013.64
Bennett C, Odom C, Ben-Asher M. Knee angle estimation based on imu data and artificial neural networks. In Proceedings - 29th Southern Biomedical Engineering Conference, SBEC 2013. 2013. p. 111-112. 6525701 https://doi.org/10.1109/SBEC.2013.64
Bennett, Christopher ; Odom, Crispin ; Ben-Asher, Matan. / Knee angle estimation based on imu data and artificial neural networks. Proceedings - 29th Southern Biomedical Engineering Conference, SBEC 2013. 2013. pp. 111-112
@inproceedings{bb410717f5674fab811530ef61d9cd9c,
title = "Knee angle estimation based on imu data and artificial neural networks",
abstract = "The measurement of joint angles is of profound importance in analysis of human gait. However, currently these measurements can be acquired only with the use of dedicated measuring devices such as a goniometer or in a gait lab with a motion capture system. The low-cost and portability of recent IMU technology makes them ideal for continuous monitoring of kinematic data. In this research we present an algorithm for estimating knee angles based on IMU data with the use of artificial neural networks. Two IMUs with tri-axis accelerometers and gyroscopes were used above and below the knee under investigation. Simultaneously, an electro-goniometer was used to measure the angle, acquired at 64 Hz. A feed-forward ANN with one hidden layer was fed IMU data from 25 of the acquired steps as inputs and trained against the goniometer angles. The ANN was evaluated on 25 trials for a single subject. The estimated knee angle exhibited strong correlation and minimal error compared to the actual angle.",
author = "Christopher Bennett and Crispin Odom and Matan Ben-Asher",
year = "2013",
month = "8",
day = "5",
doi = "10.1109/SBEC.2013.64",
language = "English",
isbn = "9780769550329",
pages = "111--112",
booktitle = "Proceedings - 29th Southern Biomedical Engineering Conference, SBEC 2013",

}

TY - GEN

T1 - Knee angle estimation based on imu data and artificial neural networks

AU - Bennett, Christopher

AU - Odom, Crispin

AU - Ben-Asher, Matan

PY - 2013/8/5

Y1 - 2013/8/5

N2 - The measurement of joint angles is of profound importance in analysis of human gait. However, currently these measurements can be acquired only with the use of dedicated measuring devices such as a goniometer or in a gait lab with a motion capture system. The low-cost and portability of recent IMU technology makes them ideal for continuous monitoring of kinematic data. In this research we present an algorithm for estimating knee angles based on IMU data with the use of artificial neural networks. Two IMUs with tri-axis accelerometers and gyroscopes were used above and below the knee under investigation. Simultaneously, an electro-goniometer was used to measure the angle, acquired at 64 Hz. A feed-forward ANN with one hidden layer was fed IMU data from 25 of the acquired steps as inputs and trained against the goniometer angles. The ANN was evaluated on 25 trials for a single subject. The estimated knee angle exhibited strong correlation and minimal error compared to the actual angle.

AB - The measurement of joint angles is of profound importance in analysis of human gait. However, currently these measurements can be acquired only with the use of dedicated measuring devices such as a goniometer or in a gait lab with a motion capture system. The low-cost and portability of recent IMU technology makes them ideal for continuous monitoring of kinematic data. In this research we present an algorithm for estimating knee angles based on IMU data with the use of artificial neural networks. Two IMUs with tri-axis accelerometers and gyroscopes were used above and below the knee under investigation. Simultaneously, an electro-goniometer was used to measure the angle, acquired at 64 Hz. A feed-forward ANN with one hidden layer was fed IMU data from 25 of the acquired steps as inputs and trained against the goniometer angles. The ANN was evaluated on 25 trials for a single subject. The estimated knee angle exhibited strong correlation and minimal error compared to the actual angle.

UR - http://www.scopus.com/inward/record.url?scp=84880862809&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880862809&partnerID=8YFLogxK

U2 - 10.1109/SBEC.2013.64

DO - 10.1109/SBEC.2013.64

M3 - Conference contribution

SN - 9780769550329

SP - 111

EP - 112

BT - Proceedings - 29th Southern Biomedical Engineering Conference, SBEC 2013

ER -