Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Prediction of blood glucose using contextual LifeLog data

Palbar, Tenzin, Kesavulu, Manoj orcid logoORCID: 0000-0001-5505-9593, Gurrin, Cathal orcid logoORCID: 0000-0003-4395-7702 and Verbruggen, Renaat (2022) Prediction of blood glucose using contextual LifeLog data. In: MultiMedia Modeling: 28th International Conference, MMM 2022, 6–10 June 2022, Phu Quoc, Vietnam.

Abstract
In this paper, we describe a novel approach to the prediction of human blood glucose levels by analysing rich biometric human contextual data from a pioneering lifelog dataset. Numerous prediction models (RF, SVM, XGBoost and Elastic-Net) along with different combinations of input attributes are compared. An efficient ensemble method of stacking of multiple combination of prediction models was also implemented as our contribution. It was found that XGBoost outperformed three other models and that a stacking ensemble method further improved the performance.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Human context; Lifelogging; Blood glucose
Subjects:Computer Science > Lifelog
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: MultiMedia Modeling: 28th International Conference, MMM 2022, Proceedings. Lecture Notes in Computer Science (LNCS) 13141. Springer-Verlag.
Publisher:Springer-Verlag
Official URL:https://doi.org/10.1007/978-3-030-98358-1_32
Copyright Information:© 2022 Springer
ID Code:27658
Deposited On:07 Sep 2022 17:40 by Cathal Gurrin . Last Modified 07 Sep 2022 17:40
Documents

Full text available as:

[thumbnail of MACHU___MMM22___TenzinP.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
882kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record