Malmö University Publications
Change search
Link to record
Permanent link

Direct link
Bergkvist, Hannes
Publications (2 of 2) Show all publications
Bergkvist, H., Exner, P. & Davidsson, P. (2020). Constraining neural networks output by an interpolating loss function with region priors. In: Michael Lutter; Alexander Terenin; Shirley Ho; Lei Wang (Ed.), NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning: . Paper presented at NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning December 12th, 2020.
Open this publication in new window or tab >>Constraining neural networks output by an interpolating loss function with region priors
2020 (English)In: NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning / [ed] Michael Lutter; Alexander Terenin; Shirley Ho; Lei Wang, 2020Conference paper, Published paper (Refereed)
Abstract [en]

Deep neural networks have the ability to generalize beyond observed training data. However, for some applications they may produce output that apriori is known to be invalid. If prior knowledge of valid output regions is available, one way of imposing constraints on deep neural networks is by introducing these priors in a loss function. In this paper, we introduce a novel way of constraining neural network output by using encoded regions with a loss function based on gradient interpolation. We evaluate our method in a positioning task where a region map is used in order to reduce invalid position estimates. Results show that our approach is effective in decreasing invalid outputs for several geometrically complex environments.

Keywords
Deep neural networks, Loss function, Constraining, Adaptation
National Category
Computer Sciences
Identifiers
urn:nbn:se:mau:diva-41238 (URN)
Conference
NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning December 12th, 2020
Available from: 2021-03-12 Created: 2021-03-12 Last updated: 2022-03-11Bibliographically approved
Bergkvist, H., Davidsson, P. & Exner, P. (2020). Positioning with Map Matching using Deep Neural Networks. In: MobiQuitous '20: Proceedings of the 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services. Paper presented at 17th EAI International Conference on Mobile and Ubiquitous Systems (MobiQuitous 2020), 2020. Association for Computing Machinery (ACM)
Open this publication in new window or tab >>Positioning with Map Matching using Deep Neural Networks
2020 (English)In: MobiQuitous '20: Proceedings of the 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, Association for Computing Machinery (ACM), 2020Conference paper, Published paper (Refereed)
Abstract [en]

Deep neural networks for positioning can improve accuracy by adapting to inhomogeneous environments. However, they are still susceptible to noisy data, often resulting in invalid positions. A related task, map matching, can be used for reducing geographical invalid positions by aligning observations to a model of the real world. In this paper, we propose an approach for positioning, enhanced with map matching, within a single deep neural network model. We introduce a novel way of reducing the number of invalid position estimates by adding map information to the input of the model and using a map-based loss function. Evaluating on real-world Received Signal Strength Indicator data from an asset tracking application, we show that our approach gives both increased position accuracy and a decrease of one order of magnitude in the number of invalid positions.

Place, publisher, year, edition, pages
Association for Computing Machinery (ACM), 2020
Keywords
Deep neural networks, Localization, Positioning, Map matching, Loss function, Adaptation
National Category
Computer Sciences
Identifiers
urn:nbn:se:mau:diva-41240 (URN)10.1145/3448891.3448946 (DOI)000728389400019 ()2-s2.0-85112696255 (Scopus ID)
Conference
17th EAI International Conference on Mobile and Ubiquitous Systems (MobiQuitous 2020), 2020
Available from: 2021-04-06 Created: 2021-04-06 Last updated: 2024-02-05Bibliographically approved
Organisations

Search in DiVA

Show all publications