Embedded Neural Networks for Continuous Patient Posture Classification

Title

Embedded Neural Networks for Continuous Patient Posture Classification

 Author

Koeten, Vincent (TU Delft Electrical Engineering, Mathematics and Computer Science)

Contributor

Pawełczak, Przemysław (mentor) ORCID 0000-0002-1302-1148
Kuipers, F.A. (graduation committee) ORCID 0000-0002-6686-8350
P. Gonçalves, Joana (graduation committee) ORCID 0000-0001-6072-9627
Gravemaker, Menno (mentor)
Swager, Ide (mentor)

Degree granting institution

Delft University of Technology

 Date

2018-11-27

 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.

 Subject

Neural Networks
Embedded Systems
Posture Classification
Momo Medical
pressure ulcers

 To reference this document use:

http://resolver.tudelft.nl/uuid:c8852206-ea81-4e59-bdc4-aa7d673f1f69

 Embargo date

2021-11-30

 Part of collection

Student theses

 Document type

master thesis

 Rights

© 2018 Vincent Koeten
Files
PDF Vincent_Koeten_Thesis_Report.pdf 1.87 MB
Close viewer