Big Data is undoubtedly considered one of the main enablers of the Smart cities. The public sector in the EU and worldwide is increasingly characterized by applications that rely on sensor measurements of physical phenomena such as traffic volumes, environmental pollution, filling levels of waste containers, location of municipal vehicles or detection of abnormal behaviour. In addition to sensor data from infrastructure, vast amounts of mobility and social data are generated by smartphones, C2x technology (communication among and between vehicles), and end-users with location-based services and maps.

What is beyond the smart city is the information-rich city presented with intelligent models that support planning, design and analysis of all city dimensions and thus share a vision for the future city.

In Future Cities theme, GATE research explores the following research challenges:

  • Complex reasoning over background knowledge and real-time data and streaming algorithms for automated deduction and complex event detection.
  • Knowledge-driven and probabilistic hybrid methods for reasoning over uncertain, incomplete and noisy data and the use of such data for knowledge learning and knowledge evolution in adaptive systems.
  • Data quality over multiple modalities, to optimise and transform raw data into actionable knowledge, resulting in the availability of secure, privacy‑aware and quality-aware adaptive analytical solutions.
  • Large scale image analytics, at device, edge and cloud, with semi-automatic annotation of large volumes of data, object detection/recognition and scene understanding based on deep learning and semantic ontologies.
  • Value engineering of models and methods for open data-driven services and products.
  • Advance visualisation for making decisions at scale based on intelligent models and enabling interactive approaches to tune decision processes according to predefined requirements.
  • 3D modelling and simulation, to handle a dynamic urban environment, where agents may have heterogeneous, conflicting objectives, while still allowing for distributed, cross-domain reasoning.