Open Access
Abstract
Gait disorders accompany a number of neurological and musculoskeletal disorders that significantly reduce the quality of life. Motion sensors enable high-quality modelling of gait stereotypes. However, they produce large volumes of data, the evaluation of which is a challenge. In this publication, we compare different data reduction methods and classification of reduced data for use in clinical practice. The best accuracy achieved between a group of healthy individuals and patients with ataxic gait extracted from the records of 43 participants (23 ataxic, 20 healthy), forming 418 segments of straight gait pattern, is 98% by random forest classifier preprocessed by t-distributed stochastic neighbour embedding.Keywords
Funding Information
- Ministerstvo Zdravotnictví Ceské Republiky (FN HK 00179906)
- Charles University in Prague, Czech Republic (PROGRES Q40, CZ.02.1.01-0.0-0.0-17 048-0007441)
This publication has 40 references indexed in Scilit:
- Fuzzy human motion analysis: A reviewPattern Recognition, 2015
- Epidemiological, clinical, and molecular characterization of Cuban families with spinocerebellar ataxia type 3/Machado-Joseph diseaseCerebellum & Ataxias, 2015
- Remote physiological and GPS data processing in evaluation of physical activitiesMedical & Biological Engineering & Computing, 2013
- Reviews on Various Inertial Measurement Unit (IMU) Sensor ApplicationsInternational Journal of Signal Processing Systems, 2013
- Gait measures with a triaxial accelerometer among patients with neurological impairmentNeurological Sciences, 2012
- Multi-class AdaBoostStatistics and Its Interface, 2009
- Decision trees for hierarchical multi-label classificationMachine Learning, 2008
- Neurology and orthopaedicsJournal of Neurology, Neurosurgery & Psychiatry, 2006
- The Genetic Kernel Support Vector Machine: Description and EvaluationArtificial Intelligence Review, 2005
- Principal component analysisChemometrics and Intelligent Laboratory Systems, 1987