Neural networks based system for the supervision of therapeutic exercises

Authors:
Sven Nõmm;Alar Kuusik;Sergei Ovsjanski;Ines Malmberg;Marko Parve;L. Orunurm
Affiliations:
Institute of Cybernetics at Tallinn University of Technology, Tallinn, Estonia;Competence Center ELIKO, Tallinn, Estonia;T.J. Seebeck Institute of Electronics, Tallinn University of Technology, Tallinn, Estonia;East-Tallinn Central Hospital, Tallinn, Estonia;East-Tallinn Central Hospital, Tallinn, Estonia;East-Tallinn Central Hospital, Tallinn, Estonia
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part IV
Year:
2012

Citing 3
Cited 0

Mercury: a wearable sensor network platform for high-fidelity motion analysis

Proceedings of the 7th ACM Conference on Embedded Networked Sensor Systems
Online identification of the system order with ANARX structure

ICAIS'11 Proceedings of the Second international conference on Adaptive and intelligent systems
On realizability of neural networks-based input-output models in the classical state-space form

Automatica (Journal of IFAC)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Present contribution describes application of the neural networks based models to detect incorrectly performed therapeutic exercises within the frameworks of wearable supervision system. Electronic accelerometers and gyroscopes attached to the human upper and lower limbs gather information about performed exercise in real time. Trained, on the data describing correctly done exercises, neural network based dynamic model of the limb is used to find the difference between the actual and "ideal" performances and judge if exercises are performed in a correct way or not.