TY - GEN

T1 - Mobile Quantification and Therapy Course Tracking for Gait Rehabilitation

AU - Alcaraz, Javier Conte

AU - Moghaddamnia, Sanam

AU - Peissig, Jürgen

N1 - Publisher Copyright: © 2017 IEEE. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2017/11/7

Y1 - 2017/11/7

N2 - In this paper we present a novel autonomous quality metric to quantify the rehabilitation progress of subjects with knee/hip operations. Our method supports digital analysis of human gait patterns using smartphones. The system uses data from seven calibrated (Inertial Measurement Units (IMUs)s) attached on the lower body, measuring acceleration, gyroscope, and magnetometer signals in order to classify and generate the grading system values. Our Android application communicates with the seven IMUss via Bluetooth® and performs the data acquisition and processing in real-time. In total nine features per acceleration direction and lower body joint angle are calculated and extracted to achieve a fast feedback to the user. We compare the classification accuracy and quantification capabiUties of the Linear Discriminant Analysis (LDA), Principal Component Analysis (PCA) and Naive Bayes (NB) algorithms. Our system is able to classify patients and control subjects with an accuracy of up to 100%. The outcomes can be saved on the device or transmitted to treating physicians for later control of the subjects improvements and the efficiency of physiotherapy treatments in motor rehabilitation. The proposed autonomous quality metric solution shows great potential to be used and deployed to support digital healthcare and therapy.

AB - In this paper we present a novel autonomous quality metric to quantify the rehabilitation progress of subjects with knee/hip operations. Our method supports digital analysis of human gait patterns using smartphones. The system uses data from seven calibrated (Inertial Measurement Units (IMUs)s) attached on the lower body, measuring acceleration, gyroscope, and magnetometer signals in order to classify and generate the grading system values. Our Android application communicates with the seven IMUss via Bluetooth® and performs the data acquisition and processing in real-time. In total nine features per acceleration direction and lower body joint angle are calculated and extracted to achieve a fast feedback to the user. We compare the classification accuracy and quantification capabiUties of the Linear Discriminant Analysis (LDA), Principal Component Analysis (PCA) and Naive Bayes (NB) algorithms. Our system is able to classify patients and control subjects with an accuracy of up to 100%. The outcomes can be saved on the device or transmitted to treating physicians for later control of the subjects improvements and the efficiency of physiotherapy treatments in motor rehabilitation. The proposed autonomous quality metric solution shows great potential to be used and deployed to support digital healthcare and therapy.

KW - Classification

KW - Digital healthcare

KW - Feature extraction

KW - Gait pattern

KW - Kalman Filter

KW - Machine Learning

KW - Rehabilitation

KW - Supervised Learning

KW - Unsupervised Learning

UR - http://www.scopus.com/inward/record.url?scp=85040370849&partnerID=8YFLogxK

U2 - 10.1109/ICDSP.2017.8096106

DO - 10.1109/ICDSP.2017.8096106

M3 - Conference contribution

AN - SCOPUS:85040370849

SN - 9781538618967

T3 - International Conference on Digital Signal Processing (DSP)

BT - 2017 22nd International Conference on Digital Signal Processing (DSP)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 22nd International Conference on Digital Signal Processing, DSP 2017

Y2 - 23 August 2017 through 25 August 2017

ER -