Classification of Gait Phases Based on Bilateral EMG Data Using Support Vector Machines

Jakob Ziegler; Hubert Gattringer; Andreas Müller

doi:10.1109/BIOROB.2018.8487750

Classification of Gait Phases Based on Bilateral EMG Data Using Support Vector Machines

Jakob Ziegler, Hubert Gattringer, Andreas Müller

Institute of Robotics

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

Abstract

Robotic systems for rehabilitation of movement disorders and motion assistance are gaining increased attention. Robust classification of motion data as well as reliable recognition of the user's intended movement play a major role in order to maximize wearability and effectiveness of such systems. Biological signals like electromyography (EMG) provide a direct connection to the motion intention of the wearer. This work comprises the classification of stance phase and swing phase during healthy human gait based on the muscle activity in both legs using the theory of Support Vector Machines (SVM). A novel EMG feature calculated from the bilateral EMG signals of muscle pairs is introduced. The presented method shows promising results with classification accuracies of up to 96%.

Original language	English
Title of host publication	2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob)
Pages	978-983
Number of pages	6
DOIs	https://doi.org/10.1109/BIOROB.2018.8487750
Publication status	Published - Oct 2018

Fields of science

203015 Mechatronics
203022 Technical mechanics
202 Electrical Engineering, Electronics, Information Engineering
202035 Robotics
203013 Mechanical engineering

JKU Focus areas

Mechatronics and Information Processing

Access to Document

10.1109/BIOROB.2018.8487750

Cite this

@inproceedings{16e589ca82bc4d8796f452431d1ec919,

title = "Classification of Gait Phases Based on Bilateral EMG Data Using Support Vector Machines",

abstract = "Robotic systems for rehabilitation of movement disorders and motion assistance are gaining increased attention. Robust classification of motion data as well as reliable recognition of the user's intended movement play a major role in order to maximize wearability and effectiveness of such systems. Biological signals like electromyography (EMG) provide a direct connection to the motion intention of the wearer. This work comprises the classification of stance phase and swing phase during healthy human gait based on the muscle activity in both legs using the theory of Support Vector Machines (SVM). A novel EMG feature calculated from the bilateral EMG signals of muscle pairs is introduced. The presented method shows promising results with classification accuracies of up to 96%.",

author = "Jakob Ziegler and Hubert Gattringer and Andreas M{\"u}ller",

year = "2018",

month = oct,

doi = "10.1109/BIOROB.2018.8487750",

language = "English",

isbn = "978-1-5386-8183-1",

pages = "978--983",

booktitle = "2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob)",

}

TY - GEN

T1 - Classification of Gait Phases Based on Bilateral EMG Data Using Support Vector Machines

AU - Ziegler, Jakob

AU - Gattringer, Hubert

AU - Müller, Andreas

PY - 2018/10

Y1 - 2018/10

N2 - Robotic systems for rehabilitation of movement disorders and motion assistance are gaining increased attention. Robust classification of motion data as well as reliable recognition of the user's intended movement play a major role in order to maximize wearability and effectiveness of such systems. Biological signals like electromyography (EMG) provide a direct connection to the motion intention of the wearer. This work comprises the classification of stance phase and swing phase during healthy human gait based on the muscle activity in both legs using the theory of Support Vector Machines (SVM). A novel EMG feature calculated from the bilateral EMG signals of muscle pairs is introduced. The presented method shows promising results with classification accuracies of up to 96%.

AB - Robotic systems for rehabilitation of movement disorders and motion assistance are gaining increased attention. Robust classification of motion data as well as reliable recognition of the user's intended movement play a major role in order to maximize wearability and effectiveness of such systems. Biological signals like electromyography (EMG) provide a direct connection to the motion intention of the wearer. This work comprises the classification of stance phase and swing phase during healthy human gait based on the muscle activity in both legs using the theory of Support Vector Machines (SVM). A novel EMG feature calculated from the bilateral EMG signals of muscle pairs is introduced. The presented method shows promising results with classification accuracies of up to 96%.

U2 - 10.1109/BIOROB.2018.8487750

DO - 10.1109/BIOROB.2018.8487750

M3 - Conference proceedings

SN - 978-1-5386-8183-1

SP - 978

EP - 983

BT - 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob)

ER -