Embedded Neural Networks for Continuous Patient Posture Classification

Master Thesis (2018)
Author(s)

V.R. Koeten (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Przemyslaw Przemysław – Mentor

Fernando Kuipers – Graduation committee member

Joana Goncalves – Graduation committee member

Menno Gravemaker – Mentor

Ide Swager – Mentor

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2018 Vincent Koeten
More Info
expand_more
Publication Year
2018
Language
English
Copyright
© 2018 Vincent Koeten
Graduation Date
27-11-2018
Awarding Institution
Delft University of Technology
Sponsors
Momo Medical B.V.
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Current hospital protocols dictate patients be turned at least every three hours in the effort of preventing pressure ulcers. To reduce the workload of nurses, Momo Medical has created an embedded sensing device to track the patient's posture and notify nurses when it is time to turn them. The challenge presented and the focus of this thesis is classifying the posture of the patient based on the sensor data sampled, specifically, utilizing neural networks on an embedded platform.
Furthermore an optimization inspired by recurrent neural networks and ensemble neural networks is proposed, implemented, and compared against vanilla neural networks and pruned variants.

Files

Vincent_Koeten_Thesis_Report.p... (pdf)
(pdf | 1.87 Mb)
- Embargo expired in 30-11-2021
License info not available