Mobility Information Engineering Lab at ETH Zürich
Welcome to the Mobility Information Engineering Lab (MIE) at ETH Zürich. The MIE Lab is part of the Chair of Geoinformation Engineering at the Institute of Cartography and Geoinformation (IKG).
Our research is centered around analyzing spatio-temporal aspects of human mobility and developing methods to increase its sustainability with information and communication technology (ICT).
For this, we combine competences and methods from diverse fields such as Geographic Information Science (GISc), Artificial Intelligence (AI), Data Mining, Transportation Modeling, Spatial Cognition, and Learning Analytics. Our interests span from location-based services (LBS), trajectory data analysis, agent-based models and simulation, algorithms and models for spatio-temporal information, to mobile learning visualizations and learning analytics.
In our research we also place great value on reproducibility and transparency of our work. For this purpose we publish our code on the MIE Lab Github page, and for example provide the Trackintel Python package to standardise preprocessing steps of mobility data.
Read more about our research in the following core areas:
Location-based services to support people in mobility choices, MaaS offers, sustainability assessments
Spatio-temporal machine learning, analysis, simulation & prediction of human mobility, user profiling and personalization
Vehicle-2-grid strategies, smart charging, impact of drivetrain technologies, spatio-temporal assessments of technology penetration
Our paper “GeOT: A spatially explicit framework for evaluating spatio-temporal predictions”, is now published in the International Journal of Geographical Information Science (IJGIS)! Motivation: While the GIS mantra “spatial is special” is widely acknowledged, it has not made its way into how we evaluate spatio-temporal predictions. Standard error metrics like MSE or MAE are typically …
Continue reading “New paper on evaluating spatio-temporal predictions with Optimal Transport”
Our new paper, titled “Context-Aware Knowledge Graph Framework for Traffic Speed Forecasting Using Graph Neural Networks,” has been accepted for publication in IEEE Transactions on Intelligent Transportation Systems. This paper introduces a novel context-aware knowledge graph (CKG) framework to enhance traffic speed forecasting by effectively modeling spatial and temporal contexts. Using a relation-dependent integration strategy, …
Continue reading “New paper on context-aware knowledge graph framework for traffic forecasting”
We’re exploring how people perceive cycling routes and what shapes their cycling experience. What will you do?• Watch short cycling videos.• Answer brief questionnaires about your experience. Who can join?✔ 18 years or older.✔ Moderate proficiency in English.✔ Normal eyesight (contact lenses allowed). Why participate?• Contribute to research that improves cycling experiences.• Your responses will …