loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Kris Cuppens 1 ; Peter Karsmakers 1 ; Anouk Van de Vel 2 ; Bert Bonroy 3 ; Milica Milosevic 4 ; Lieven Lagae 2 ; Berten Ceulemans 2 ; Sabine Van Huffel 4 and Bart Vanrumste 1

Affiliations: 1 Thomas More Kempen and KU Leuven, Belgium ; 2 University Hospital Leuven, Belgium ; 3 Thomas More Kempen, Belgium ; 4 KU Leuven, Belgium

Keyword(s): Epilepsy Detection, Acceleration Data, Unbalanced Data, Support Vector Machines.

Related Ontology Subjects/Areas/Topics: Applications ; Cardiovascular Imaging and Cardiography ; Cardiovascular Technologies ; Classification ; Health Engineering and Technology Applications ; Learning of Action Patterns ; Pattern Recognition ; Signal Processing ; Software Engineering ; Theory and Methods

Abstract: Data of nocturnal movements in epileptic patients is marked by an imbalance due to the relative small number of seizures compared to normal nocturnal movements. This makes developing a robust classifier more difficult, especially with respect to reducing the number of false positives while keeping a high sensitivity. In this paper we evaluated different ways to overcome this problem in our application, by using a different weighting of classes and by resampling the minority class. Furthermore, as we only have a limited number of training samples available per patient, additionally it was investigated in which manner the training set size affects the results. We observed that oversampling gives a higher performance than only adjusting the weights of both classes. Compared to its alternatives oversampling based on the probability density function gives the best results. On 2 of 3 patients, this technique gives a sensitivity of 95% or more and a PPV more than 70%. Furthermore, an increa sed imbalance in the dataset leads to lower performance, whereas the size of the dataset has little influence. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.117.8.177

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Cuppens, K.; Karsmakers, P.; Van de Vel, A.; Bonroy, B.; Milosevic, M.; Lagae, L.; Ceulemans, B.; Van Huffel, S. and Vanrumste, B. (2013). Handling Unbalanced Data in Nocturnal Epileptic Seizure Detection using Accelerometers. In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-8565-41-9; ISSN 2184-4313, SciTePress, pages 447-452. DOI: 10.5220/0004264704470452

@conference{icpram13,
author={Kris Cuppens. and Peter Karsmakers. and Anouk {Van de Vel}. and Bert Bonroy. and Milica Milosevic. and Lieven Lagae. and Berten Ceulemans. and Sabine {Van Huffel}. and Bart Vanrumste.},
title={Handling Unbalanced Data in Nocturnal Epileptic Seizure Detection using Accelerometers},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2013},
pages={447-452},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004264704470452},
isbn={978-989-8565-41-9},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - Handling Unbalanced Data in Nocturnal Epileptic Seizure Detection using Accelerometers
SN - 978-989-8565-41-9
IS - 2184-4313
AU - Cuppens, K.
AU - Karsmakers, P.
AU - Van de Vel, A.
AU - Bonroy, B.
AU - Milosevic, M.
AU - Lagae, L.
AU - Ceulemans, B.
AU - Van Huffel, S.
AU - Vanrumste, B.
PY - 2013
SP - 447
EP - 452
DO - 10.5220/0004264704470452
PB - SciTePress