J
Juha Pärkkä
Researcher at VTT Technical Research Centre of Finland
Publications - 36
Citations - 3407
Juha Pärkkä is an academic researcher from VTT Technical Research Centre of Finland. The author has contributed to research in topics: Feature selection & Activity recognition. The author has an hindex of 19, co-authored 35 publications receiving 3156 citations. Previous affiliations of Juha Pärkkä include Tampere University of Technology.
Papers
More filters
Journal ArticleDOI
Neighbourhood and path-based greenspace in three European countries: associations with objective physical activity
William Mueller,Paul Wilkinson,James Milner,Sotiris Vardoulakis,Susanne Steinle,Juha Pärkkä,Eija Parmes,Luc Cluitmans,Eelco Kuijpers,Anjoeka Pronk,Denis Sarigiannis,Spyros Karakitsios,Dimitris Chapizanis,Thomas Maggos,Asimina Stamatelopoulou,Miranda Loh +15 more
TL;DR: More strenuous or longer walking and cycling trips occurred in environments with more greenspace, but levels of residential greenspace did not have a clear link with outdoor MVPA, and greenspace markers were positively linked to intensity and duration of activity.
Journal ArticleDOI
Gait Disturbances are Associated with Increased Cognitive Impairment and Cerebrospinal Fluid Tau Levels in a Memory Clinic Cohort
Marijn Muurling,Hanneke F.M. Rhodius-Meester,Juha Pärkkä,Mark van Gils,Kristian Steen Frederiksen,Marie Bruun,Steen G. Hasselbalch,Hilkka Soininen,Sanna-Kaisa Herukka,Merja Hallikainen,Charlotte E. Teunissen,Pieter Jelle Visser,Pieter Jelle Visser,Philip Scheltens,Wiesje M. van der Flier,Jussi Mattila,Jyrki Lötjönen,Casper de Boer +17 more
TL;DR: Findings suggest that gait — particularly measures related to pace and rhythm — are altered in dementia and have a direct link with measures of neurodegeneration.
Book ChapterDOI
Estimating older people's physical functioning with automated health monitoring technologies at home: feature correlations and multivariate analysis
TL;DR: Created multivariate model to estimate holistic functional status has statistically significant correlation with ADL and two lower limb muscle strength tests, and almost statistically significant correlated with balance and walk tests.
Proceedings ArticleDOI
A computationally light classification method for mobile wellness platforms
TL;DR: A simple linear classifier is studied and it is shown that the simple classifier performs comparable to more complex nonlinear k-Nearest Neighbor Classifier, depicting great potential in implementing the classifier in small mobile wellness devices.