Luciana Colella
Unsupervised Identification and Characterization of Motor Performance Profiles in Parkinson's Disease Using Exergame-Based Markerless Motion Tracking.
Rel. Gabriella Olmo, Guido Coppo. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2026
|
Preview |
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (23MB) | Preview |
Abstract
Parkinson’s disease (PD) is a chronic, heterogeneous neurological disorder whose motor manifestations affect mobility, coordination, balance, gait, and autonomy. Clinical assessments are essential for describing disease severity and motor impairment. However, they are usually performed during periodic visits and may only partially capture the variability of motor performance over time. Digital rehabilitation platforms combining exergames and markerless motion tracking can provide repeated quantitative information on movement execution during structured motor tasks, creating new opportunities for data-driven analysis of motor performance. This thesis explores whether heterogeneous data acquired through the ELEVATOR exergame-based rehabilitation platform can support the exploratory characterization of motor performance profiles in people with PD.
Data were collected during a supervised multi-session protocol involving patients assessed at baseline by an expert neurologist
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
