University of Twente Student Theses

Login

Therapeutic exercise assessment automation, a hidden Markov model approach.

Kleine Deters, Jan (2018) Therapeutic exercise assessment automation, a hidden Markov model approach.

[img] PDF
6MB
Abstract:In all kinds of research fields, the drive for automation seems to be rooted in the mindset of various stakeholders. Likewise, this is the case in clinical areas where specialist’s time is valuable and should be directed to patients who need it the most. In the case of physical rehabilitation training, supporting patients (automatically) who can perform therapeutic exercises without physical support can save valuable time and improve the overall rehabilitation. The therapists should however still be in charge of the rehabilitation program and thus needs to receive a qualitative overview of their patient’s exercise executions. Cost savings and flexible planning arise when patients can perform exercises at home and receive therapeutic valid feedback. The goal in this work is to deliver the first constituent, that of automatically generating a valid therapeutic assessment. Finding the key-elements in covering the assessment is breed by a constant dialogue with physiotherapists as they know, intrinsically, the art of ‘seeing’ quality and know how to approach patients in a favourable way. Using data mining, time series analyses and machine learning in a hybrid fashion, the resulting methodology can be described as a data and expert knowledge driven approach.
Item Type:Essay (Master)
Clients:
Universidad de las Américas, Quito, Ecuador
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Interaction Technology MSc (60030)
Link to this item:https://purl.utwente.nl/essays/74395
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page