EMODE23
1st ACM SIGSPATIAL International Workshop on Methods for Enriched Mobility Data:
Emerging issues and Ethical perspectives 2023 (EMODE23)
November 13, 2023
Hamburg, Germany
- Submission deadline: September 15, 2023 *NEW DEADLINE
- Authors notification: October 6, 2023
- Camera-ready due: October 20, 2023
- Workshop day: November 13, 2023
Joint with ACM SIGSPATIAL 2023, International Conference on Advances in Geographic Information Systems
Mobility data collection and analysis is nowadays essential in many domains such as understanding human mobility, predicting diseases, building urban and transportation infrastructure, sustainable mobility, improving tourism, and many other applications.
Mobility data has generally the form of trajectories that represent the tracks of a moving object (human, vehicle, or animal). Methods for collecting, representing, and analysing trajectories have reached a certain maturity level in the literature. However, new challenges arise in the context of a more general mobility enrichment, fostered by the increasing data availability like the initiatives of mobility data sharing and mobility data spaces. In particular, many unresolved questions remain regarding the management and analysis of mobility data that is enriched with various forms of heterogeneous semantic information.Furthermore, when analysing this new kind of enriched mobility data, one should take into account possible misuses.
Societal good applications and methods for collecting, processing, and using these data and the results of analyses should be identified and chosen in order to ensure ethically desirable outcomes. The results of the algorithms and the suggestions provided should not be biased or discriminatory towards particular groups or populations. There is a need for an interdisciplinary approach to these semantically enriched spatio-temproal data and there is therefore a need to exploit methods from other disciplines like AI, NLP, and Ethics.
The EMODE23 Workshop focuses on all these novel aspects and issues for managing and analysing the enriched mobility data. The scope of the workshop is to bring together researchers in the SIGSPATIAL community as well as researchers in related disciplines that can be synergistic and complementary to advance the state-of-the-art techniques.
November 13th 2023
13.00 – 13.10 Welcome from Organizers
13.10 – 14.10 Invited Talk:
Spatial Fairness: Definitions and Mitigation Strategies
Prof. Dimitris Sacharidis (Université Libre de Bruxelles)
Session 1 Methods for Maritime Data Querying and Analysis
14.10 – 14.35 RDF Benchmark for Enriched Maritime Data. Georgios Santipantakis (University of Piraeus) and Christos Doulkeridis (University of Piraeus)
14.35 – 14.55 A real-time trajectory classification module. Ioannis Kontopoulos (Harokopio University), Antonios Makris (Harokopio University) and Konstantinos Tserpes (Harokopio University)
15.00 – 15.30 Coffee break
Session 2 Methods for Incomplete data and data augmentation
15.30 – 15.55 A Traffic Simulation with Incomplete Data: the Case of Brussels. Davide Andrea Guastella (Université Libre de Bruxelles), Bruno Cornelis (Macq Mobility, Vrije Universiteit Brussel) and Gianluca Bontempi (Université Libre de Bruxelles)
15.55 – 16.15 A Data Augmentation Algorithm for Trajectory Data. Yaksh J. Haranwala (Memorial University of Newfoundland), Gabriel Spadon (Dalhousie University) , Chiara Renso (ISTI-CNR) and Amilcar Soares (Linnaeus University)
Session 3 Methods for higher dimensional spatio temporal data
16.15 – 16.40 A Data Model and Operations for Higher-Dimensional Moving Objects in Databases. Florian Heinz (Ostbayerische Technische Hochschule Regensburg) and Johannes Schildgen (OTH Regensburg)
16.40 – 17.00 MAT-CA: a tool for Multiple Aspect Trajectory Clustering Analysis. Yuri Santos (Universidade Federal de Santa Catarina), Ricardo Giuliani (Universidade Federal de Santa Catarina), Tarlis Portela (Instituto Federal do Paraná (IFPR)) Chiara Renso (ISTI-CNR) and Jônata Carvalho (Universidade Federal de Santa Catarina)
Prof. Dimitris Sacharidis (Université Libre de Bruxelles)
Spatial Fairness: Definitions and Mitigation Strategies
Abstract
Algorithmic fairness refers to the notion that the algorithm, e.g., a machine learning (ML) model, should not discriminate against individuals on the basis of protected attributes, e.g., like race or gender. This talk will discuss the case when location, e.g., place of origin, home address, is considered a protected attribute, and thus the algorithm is required to exhibit spatial fairness. For example, an algorithm that assesses mortgage loan applications should not discriminate on home address. This could be to avoid redlining, i.e., indirectly discriminating based on ethnicity/race due to strong correlations between the home address and certain ethnic/racial groups, or to avoid gentrification, e.g., when applications in a poor urban area are systematically rejected to attract wealthier people. The talk will start by motivating the problem and presenting definitions of spatial fairness, and then discuss techniques to mitigate the effects of spatially unfair ML models.
Short Bio
Dimitris Sacharidis is an assistant professor at the Data Science and Engineering Lab of the Université Libre de Bruxelles. Prior to that he was an assistant professor at the Technical University of Vienna, and a Marie Skłodowska Curie fellow at the “Athena” Research Center and at the Hong Kong University of Science and Technology. He finished his PhD and undergraduate studies on Computer Engineering at the National Technical University of Athens, while in between he obtained an MSc in Computer Science from the University of Southern California. His research interests revolve around the topic of responsible data science, addressing issues related to trust, explainability and fairness.
- Giuseppina Andresini, University of Bari (Italy)
- Natalia Andrienko, Fraunhofer (Germany) and City Univ (London)
- Bruno Baruque Zanon, Universidad de Burgos (Spain)
- Jonata Carvalho, Federal University of Santa Catarina (Brazil)
- Christos Doulkeridis, University of Piraeus (Greece)
- Francesco Lettich, ISTI-CNR Pisa Italy
- Ticiana Linhares, Federal University of Ceará (Brazil)
- Fran Meissner, University of Twente (The Netherlands)
- Fabio Pinelli, IMT Lucca (Italy)
- Chiara Pugliese, ISTI-CNR and University of Pisa (Italy)
- Geoffrey Rockwell, Univ of Alberta (Canada)
- Mahammod Sakr, Universite’ Libre Brussels (Belgium)
- Mahtab Sarvmaili, Dalhousie University (Canada)
- Marta Simeoni, University Ca’ Foscari Venice (Italy)
- Amilcar Soares University of Linnaeus (Sweden)
- Panagiotis Tampakis, University southern Denmark (Denmark)
- Konstantinos Tserpes, Harokopio Univ (Greece)
- Baihua Zheng, Singapore Management University (Singapore)
- Bettina Berendt, TU Berlin, Weizenbaum Institute (Germany), and KU Leuven (Belgium), email: berendt AT tu-berlin.de
- Nikos Pelekis, University of Piraeus (Greece), email: npelekis AT unipi.gr
- Alessandra Raffaetà, Ca’ Foscari University of Venice (Italy), email: raffaeta AT unive.it
- Chiara Renso, ISTI-CNR, Pisa (Italy), email: chiara.renso AT isti.cnr.it
Beatrice Rapisarda, ISTI-CNR, Pisa (Italy)
Topics of interest include, but are not limited to the following, where a specific focus on semantically enriched mobility data is particularly welcome:
- *Mobility data analytics: novel methods and platforms
- *AI methods for mobility data management and analysis
- *NLP methods for mobility data management and analysis
- *Federated learning for mobility analysis
- *Parallel / distributed / streaming data processing for mobility analytics
- *Cloud / fog / edge data processing for mobility analytics
- *Visual analytics on mobility data
- *Generating synthetic mobility datasets
- *Mobility data sharing: methods for analysis of heterogeneous mobility data
- *Urban / maritime / aviation / animal ecology applications for semantically enriched data analysis
- *Integration / interlinking of mobility with societal data
- *Fairness, explainability, privacy, and further ethical (and/or legal) requirements in the collection, analysis and uses of mobility data, including privacy, fairness and explainability
- *Societally “good” applications
- *Sustainability of mobility and of the mobility data processing
- *Trustworthy and privacy preserving mobility data spaces
Full research papers should present mature research on a specific problem or topic in the context of the workshop topics. We also welcome demonstrations of existing or developing methods, toolkits, and best practices.
All submitted papers will be peer reviewed. Once accepted, at least one author is required to register for the workshop and the ACM SIGSPATIAL conference, as well as attend the workshop to present the accepted work which will then appear in the ACM Digital Library.
The workshop will nominate a best paper award.
Manuscripts should be submitted in PDF format and formatted using the ACM camera-ready templates available at http://www.acm.org/publications/proceedings-template. * Check the SIG fomat for conferences, it is a double column format *
All submitted papers will be peer reviewed to ensure the quality and the clarity of the presented research work. Specifically research papers will be evaluated for novelty, quality and potential impact of the proposed approach. Demo papers will be evaluated on the novelty and usefulness of the system for the society and the research community, attractiveness for the attendees.
Submissions will be single-blind — i.e., the names and affiliations of the authors should be listed in the submitted version.
The EMODE23 workshop accepts three kinds of submissions:
*Long research papers 8 to 10 pages
*Short research papers 4 to 6 pages
*Demo papers max length 4 pages
Papers should be submitted using EasyChair at URL https://easychair.org/conferences/?conf=emode23