Cyber-Physical System for Gait Analysis and Fall-risk Evaluation by Embedded Cortico-muscular Coupling Computing

Annese, V. F. , Mezzina, G. and De Venuto, D. (2016) Cyber-Physical System for Gait Analysis and Fall-risk Evaluation by Embedded Cortico-muscular Coupling Computing. In: Tenth International Conference on Advances in Semantic Processing (SEMAPRO 2016), Venice, Italy, 9-13 Oct 2016, pp. 71-76. ISBN 9781612085074

Full text not currently available from Enlighten.

Publisher's URL: http://www.thinkmind.org/articles/semapro_2016_5_10_30050.pdf

Abstract

The paper describes the architecture of a non-invasive, wireless embedded system for gait analysis and preventing involuntary movements including fall. The system operates with synchronized and digitized data samples from 8 EMG (limbs) and 8 EEG (motor-cortex) channels. An embedded Altera Cyclone V FPGA operates the real-time signal pre-processing and the computation (resource utilization: 85.95% ALMs, 43283 ALUTs, 73.0% registers, 9.9% block memory; processing latency < 1ms). The system has been tested on patients affected by Parkinson disease (PD) under physician guide and compared with healthy subjects’ results. Both PD and healthy subjects have been involved in the standard diagnostic protocol (normal gait and pull test). The developed cyber-physical system detects differences between the PD and the healthy subjects in terms of walking pattern, i.e., agonist-antagonist co-contractions (Typ time: PD’s 148ms vs Healthy 88ms; Max: PD’s 388ms vs Healthy 314ms). The PD’s cerebral Movement Related Potentials (i.e., Bereitschaft) analysis during the pull-test showed an increasing from 59dBμ to 66dBμ after 3 settling steps while measurements on healthy subject return, respectively, 57dBμ, 62dBμ in 1 settling step. The system is able to prevent fall enabling the actuator in 168ms, i.e., better than the normal human time reaction (300ms).

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Annese, Dr Valerio
Authors: Annese, V. F., Mezzina, G., and De Venuto, D.
College/School:College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering
Journal Name:SEMAPRO 2016
ISSN:2308-4510
ISBN:9781612085074
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record