Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
5707910 | Gait & Posture | 2017 | 6 Pages |
Abstract
In this paper we propose a novel framework in which IMU gait measurement sequences sampled during a 10Â m walk are first encoded as hidden Markov models (HMMs) to extract their dynamics and provide a fixed-length representation. Given sufficient training samples, the distance between HMMs which optimises classification performance is learned and employed in a classical Nearest Neighbour classifier. Our tests demonstrate how this technique achieves accuracy of 85.51% over a 156 people with Parkinson's with a representative range of severity and 424 typically developed adults, which is the top performance achieved so far over a cohort of such size, based on single measurement outcomes. The method displays the potential for further improvement and a wider application to distinguish other conditions.
Keywords
Related Topics
Health Sciences
Medicine and Dentistry
Orthopedics, Sports Medicine and Rehabilitation
Authors
Fabio Cuzzolin, Michael Sapienza, Patrick Esser, Suman Saha, Miss Marloes Franssen, Johnny Collett, Helen Dawes,