[Back]


Talks and Poster Presentations (with Proceedings-Entry):

A. Salihu, S. Schwarz, M. Rupp:
"Towards Scalable Uncertainty Aware DNN-based Wireless Localisation";
Talk: 29th European Signal Processing Conference (EUSIPCO), Dublin, Ireland; 08-23-2021 - 08-27-2021; in: "Proceedings of 29th European Signal Processing Conference, EUSIPCO 2021", IEEE, (2021).



English abstract:
Existing deep neural network (DNN) based wireless
localization approaches typically do not capture uncertainty
inherent in their estimates. In this work, we propose and
evaluate variational and scalable DNN approaches to measure
the uncertainty as a result of changing propagation conditions
and the finite number of training samples. Furthermore, we show
that data uncertainty is sufficient to capture the uncertainty due
to non-line-of-sight (NLOS) and, model uncertainty improves
the overall reliability. To assess the robustness due to channel
conditions and out-of-set regions, we evaluate the methods
on challenging massive multiple-input multiple-output (MIMO)
scenarios.


Electronic version of the publication:
https://publik.tuwien.ac.at/files/publik_298426.pdf


Created from the Publication Database of the Vienna University of Technology.