Martin Raubal


Last Name

Raubal

First Name

Martin

ORCID

0000-0001-5951-6835

Organisational unit

03901 - Raubal, Martin / Raubal, Martin

Search Results

Publications 1 - 10 of 253
  • Adding Social Constraints to Location Based Services
    Item type: Other Conference Item
    McKenzie, Grant; Raubal, Martin (2011)
  • Gaze-Based Interaction with Maps and Panoramas
    Item type: Conference Paper
    Schalbetter, Laura; Kwok, Tiffany C.K.; Kiefer,Peter; et al. (2019)
    Adjunct Proceedings of the 15th International Conference on Location Based Services (LBS 2019)
    Novel interaction methods based on eye tracking can help users of location-based tourist guides to retrieve information about touristic features in the environment. However, these Gaze-Informed Location-Based Services (GAIN-LBS) do not assist their users with orientation. Here, we introduce Map-Enhanced GAIN-LBS which extend GAIN-LBS by an interactive map that provides extra information about the users location and the inspected touristic features. The system is evaluated with a between-subjects study.
  • The Open Digital Twin Platform (ODTP)
    Item type: Conference Poster
    Grübel, Jascha; Vivar Rios, Carlos; Zuo, Chenyu; et al. (2023)
    We use a five-component Digital Twin model for the Open Digital Twin Platform (ODTP) to capture quantities of interest from reality and represent higher order processes such as mobility in Switzerland. Digital Twins are represented in ODTP with Traces. A Trace describes how data moves through a digital twin from the data source to the last service providing output for users. Traces allow for the reproduction of a digital twin. ODTP relies on the cloud-based automation with micro-services to provide the five environments for the digital twin model. The first prototype “CH on the move” of the Swiss Mobility System uses MATSim , Eqasim and EasySynth to provide mobility simulations.
  • Semantic 3D City Inferences - multi-domain reasoning on Dynamic Geospatial Knowledge Graphs
    Item type: Working Paper
    Chadzynski, Arkadiusz; Silvennoinen, Heidi; Grisiute, Ayda; et al. (2023)
    c4e-Preprint Series
    This paper presents revised novel semantic web systems reference architecture for inferences and components that can store and operate on knowledge in the form of a fully dynamic graph to infer new statements by an intelligent autonomous agent capable of making informed choices based on long-term memories about its tasks that implement inference algorithms of all currently known classes. An Owlconverter tool was designed and developed as a new component which can produce fully dynamic knowledge graphs without information loss that otherwise occurs while attempting to store complex concept definitions in existing open-source dynamic RDF stores. An Inference Agent with extended cognitive capabilities of making informed choices based on long-term knowledge was designed and developed to act as an extended inference engine supporting all currently known classes of knowledge graphs inference algorithms. This capability is supported by the newly developed OntoInfer ontology that encodes the taxonomy of those algorithms linked to instances of the agent's tasks allowing the agent to make choices based on the knowledge stored in the knowledge graph. This extended architecture can demonstrate the implementation of tasks designed to work as independently executed threads containing examples of known inference algorithms using existing libraries and reasoning engines (Jena Jung and HermiT). Multi-domain reasoning capabilities on city object descriptions in terms of OntoCityGML, OntoZoning and OntoBuildableSpace were showcased on plot data provided by Urban Redevelopment Authority of Singapore converted into OWL 2 compliant knowledge base.
  • Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
    Item type: Conference Paper
    Eichenberger, Christian; Neun, Moritz; Martin, Henry; et al. (2022)
    Proceedings of Machine Learning Research ~ Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track
    The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bins. We thus reinterpreted the challenge of forecasting traffic conditions as a movie completion task. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. Building on the previous competitions, Traffic4cast 2021 now focuses on the question of model robustness and generalizability across time and space. Moving from one city to an entirely different city, or moving from pre-COVID times to times after COVID hit the world thus introduces a clear domain shift. We thus, for the first time, release data featuring such domain shifts. The competition now covers ten cities over 2 years, providing data compiled from over 10(12) GPS probe data. Winning solutions captured traffic dynamics sufficiently well to even cope with these complex domain shifts. Surprisingly, this seemed to require only the previous 1h traffic dynamic history and static road graph as input.
  • Controllability matters: The user experience of adaptive maps
    Item type: Journal Article
    Kiefer,Peter; Giannopoulos, Ioannis; Anagnostopoulos, Vasileios A.; et al. (2017)
    GeoInformatica
    Adaptive map interfaces have the potential of increasing usability by providing more task dependent and personalized support. It is unclear, however, how map adaptation must be designed to avoid a loss of control, transparency, and predictability. This article investigates the user experience of adaptive map interfaces in the context of gaze-based activity recognition. In a Wizard of Oz experiment we study two adaptive map interfaces differing in the degree of controllability and compare them to a non-adaptive map interface. Adaptive interfaces were found to cause higher user experience and lower perceived cognitive workload than the non-adaptive interface. Among the adaptive interfaces, users clearly preferred the condition with higher controllability. Results from structured interviews reveal that participants dislike being interrupted in their spatial cognitive processes by a sudden adaptation of the map content. Our results suggest that adaptive map interfaces should provide their users with control at what time an adaptation will be performed.
  • Evaluating the use of open data to estimate the global solar energy potential
    Item type: Conference Paper
    Veronesi, Fabio; Grassi, Stefano; Schenkel, Roland; et al. (2015)
    ICEE International Conference on Energy & Environment ~ Proceedings of the 2nd International Conference on Energy and Environment: bringing together Engineering and Economics
  • Two-Step Gaze Guidance
    Item type: Conference Paper
    Kwok, Tiffany C.K.; Kiefer,Peter; Raubal, Martin (2022)
    ICMI '22: Proceedings of the 2022 International Conference on Multimodal Interaction
    One challenge of providing guidance for search tasks consists in guiding the user's visual attention to certain objects in a potentially large search space. Previous work has tried to guide the user's attention by providing visual, audio, or haptic cues. The state-of-the-art methods either provide hints pointing towards the approximate direction of the target location for a fast but less accurate search or require the user to perform a fine-grained search from the beginning for a precise yet less efficient search. To combine the advantage of both methods, we propose an interaction concept called Two-Step Gaze Guidance. The first-step guidance focuses on quick guidance toward the approximate direction, and the second-step guidance focuses on fine-grained guidance toward the exact location of the target. A between-subject study (N = 69) with five conditions was carried out to compare the two-step gaze guidance method with the single-step gaze guidance method. Results revealed that the proposed method outperformed the single-step gaze guidance method. More precisely, the introduction of Two-Step Gaze Guidance slightly improves the searching accuracy, and the use of spatial audio as the first-step guidance significantly helps in enhancing the searching efficiency. Our results also indicated several design suggestions for designing gaze guidance methods.
  • Using eye movements to recognize activities on cartographic maps
    Item type: Conference Paper
    Kiefer,Peter; Giannopoulos, Ioannis; Raubal, Martin (2013)
    Proceedings of the 21st SIGSPATIAL International Conference on Advances in Geographic Information Systems
  • Correction to: FeaturEyeTrack: automatic matching of eye tracking data with map features on interactive maps
    Item type: Other Journal Item
    Göbel, Fabian; Kiefer,Peter; Raubal, Martin (2020)
    GeoInformatica
Publications 1 - 10 of 253