Research seminar

Feasibility of using Dynamic Time warping to measure Parkinsons disease motor state

Research Seminar: Complex Systems & Microdata Analysis
When?
Friday
10:30
12:00
to
Where?
Dalarna University, Room 321
Borlänge

Presenter: Somayeh Aghanavesi

Title: Feasibility of using Dynamic Time warping to measure Parkinsons disease motor state

The aim of this paper is to investigate the feasibility of using
Dynamic Time Warping (DTW) method for assessment of motor states in
advanced Parkinsons disease. A DTW-based motor state distance score
(DDS) was constructed using the acceleration and gyroscope signals
gathered from foot tapping of advanced PD patients. The mean DDS vs
mean Treatment response scale (TRS) scores across the test occasions
and across groups of PD patients was assessed. Classification ability
of DDS for detecting the change in motor states of the PD patients was
examined. The PD patients who showed more response to medication were
picked from TRS scale, and the most related DTW-based features to their
TRS scores were investigated.