2 Search Results for "Killijian, Marc-Olivier"

Document
DOI: 10.4230/LIPIcs.GIScience.2025.8
BERT4Traj: Transformer-Based Trajectory Reconstruction for Sparse Mobility Data

Authors: Hao Yang, Angela Yao, Christopher C. Whalen, and Gengchen Mai

Published in: LIPIcs, Volume 346, 13th International Conference on Geographic Information Science (GIScience 2025)

Abstract
Understanding human mobility is essential for applications in public health, transportation, and urban planning. However, mobility data often suffers from sparsity due to limitations in data collection methods, such as infrequent GPS sampling or call detail record (CDR) data that only capture locations during communication events. To address this challenge, we propose BERT4Traj, a transformer-based model that reconstructs complete mobility trajectories by predicting hidden visits in sparse movement sequences. Inspired by BERT’s masked language modeling objective and self-attention mechanisms, BERT4Traj leverages spatial embeddings, temporal embeddings, and contextual background features such as demographics and anchor points. We evaluate BERT4Traj on real-world CDR and GPS datasets collected in Kampala, Uganda, demonstrating that our approach significantly outperforms traditional models such as Markov Chains, KNN, RNNs, and LSTMs. Our results show that BERT4Traj effectively reconstructs detailed and continuous mobility trajectories, enhancing insights into human movement patterns.
Cite as

Hao Yang, Angela Yao, Christopher C. Whalen, and Gengchen Mai. BERT4Traj: Transformer-Based Trajectory Reconstruction for Sparse Mobility Data. In 13th International Conference on Geographic Information Science (GIScience 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 346, pp. 8:1-8:9, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{yang_et_al:LIPIcs.GIScience.2025.8,
  author =	{Yang, Hao and Yao, Angela and Whalen, Christopher C. and Mai, Gengchen},
  title =	{{BERT4Traj: Transformer-Based Trajectory Reconstruction for Sparse Mobility Data}},
  booktitle =	{13th International Conference on Geographic Information Science (GIScience 2025)},
  pages =	{8:1--8:9},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-378-2},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{346},
  editor =	{Sila-Nowicka, Katarzyna and Moore, Antoni and O'Sullivan, David and Adams, Benjamin and Gahegan, Mark},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GIScience.2025.8},
  URN =		{urn:nbn:de:0030-drops-238373},
  doi =		{10.4230/LIPIcs.GIScience.2025.8},
  annote =	{Keywords: Human Mobility, Trajectory Reconstruction, Deep Learning, CDR, GPS}
}
Document
DOI: 10.4230/OASIcs.ATMOS.2013.150
Carpooling: the 2 Synchronization Points Shortest Paths Problem

Authors: Arthur Bit-Monnot, Christian Artigues, Marie-José Huguet, and Marc-Olivier Killijian

Published in: OASIcs, Volume 33, 13th Workshop on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems (2013)

Abstract
Carpooling is an appropriate solution to address traffic congestion and to reduce the ecological footprint of the car use. In this paper, we address an essential problem for providing dynamic carpooling: how to compute the shortest driver's and passenger's paths. Indeed, those two paths are synchronized in the sense that they have a common subpath between two points: the location where the passenger is picked up and the one where he is dropped off the car. The passenger path may include time-dependent public transportation parts before or after the common subpath. This defines the 2 Synchronization Points Shortest Path Problem (2SPSPP). We show that the 2SPSPP has a polynomial worst-case complexity. However, despite this polynomial complexity, one needs efficient algorithms to solve it in realistic transportation networks. We focus on efficient computation of optimal itineraries for solving the 2SPSPP, i.e. determining the (optimal) pick-up and drop-off points and the two synchronized paths that minimize the total traveling time. We also define restriction areas for reasonable pick-up and drop-off points and use them to guide the algorithms using heuristics based on landmarks. Experiments are conducted on real transportation networks. The results show the efficiency of the proposed algorithms and the interest of restriction areas for pick-up or drop-off points in terms of CPU time, in addition to its application interest.
Cite as

Arthur Bit-Monnot, Christian Artigues, Marie-José Huguet, and Marc-Olivier Killijian. Carpooling: the 2 Synchronization Points Shortest Paths Problem. In 13th Workshop on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems. Open Access Series in Informatics (OASIcs), Volume 33, pp. 150-163, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2013)

Copy BibTex To Clipboard

@InProceedings{bitmonnot_et_al:OASIcs.ATMOS.2013.150,
  author =	{Bit-Monnot, Arthur and Artigues, Christian and Huguet, Marie-Jos\'{e} and Killijian, Marc-Olivier},
  title =	{{Carpooling: the 2 Synchronization Points Shortest Paths Problem}},
  booktitle =	{13th Workshop on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems},
  pages =	{150--163},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-939897-58-3},
  ISSN =	{2190-6807},
  year =	{2013},
  volume =	{33},
  editor =	{Frigioni, Daniele and Stiller, Sebastian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.ATMOS.2013.150},
  URN =		{urn:nbn:de:0030-drops-42517},
  doi =		{10.4230/OASIcs.ATMOS.2013.150},
  annote =	{Keywords: Dynamic Carpooling, Shortest Path Problem, Synchronized Paths}
}
  • Refine by Type
  • 2 Document/PDF
  • 1 Document/HTML

  • Refine by Publication Year
  • 1 2025
  • 1 2013

  • Refine by Author
  • 1 Artigues, Christian
  • 1 Bit-Monnot, Arthur
  • 1 Huguet, Marie-José
  • 1 Killijian, Marc-Olivier
  • 1 Mai, Gengchen
  • Show More...

  • Refine by Series/Journal
  • 1 LIPIcs
  • 1 OASIcs

  • Refine by Classification
  • 1 Computing methodologies → Machine learning

  • Refine by Keyword
  • 1 CDR
  • 1 Deep Learning
  • 1 Dynamic Carpooling
  • 1 GPS
  • 1 Human Mobility
  • Show More...

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact