Why MATES?

An ever-increasing number of diverse, real-life applications, ranging from social media (e.g., Twitter) to land, sea, and air surveillance systems, produce massive amounts of streaming spatio-temporal data, whose acquisition, cleaning, representation, aggregation, processing and analysis pose new challenges for the data management community. To transform the valuable information hidden in these sources into knowledge, it is essential to provide integration mechanisms that combine data from multiple diverse sources (streaming, archival, web, and social sources) into a common representation suitable for developing the subsequent analysis tasks under unified access to the underlying data: Semantic descriptions of data offer opportunities but also create new challenges.

Having enriched data representations is expected to facilitate data analysis operations, including location or trajectory prediction and forecasting, complex event detection and forecasting, and visual analytics. Additional challenges raised in the context of the above applications include data acquisition from disparate sources including social networks, handling the streaming nature of the data, its volume, its spatio-temporal nature, the requirement for efficient and effective link discovery at scale, scalable storage and data integration, parallel data processing, and the need to perform real-time (and often exploratory) data analytics, to name a few.

A strong feature of the Mobility Analytics for Spatio-temporal and Social Data (MATES) workshop is the combination of multiple domains, including maritime, aviation and land, which all heavily rely on spatio-temporal data management. The combination of these domains brings unique data opportunities but also many research challenges, part of them leading to novel multidisciplinary research avenues. A non-exclusive list of scientific issues and applications includes transportation management and planning at large, traffic control, immigration control and security, interconnected surveillance systems, and flow management. These issues become even more important when combining social data with other datasets, thus providing enriched information that may reveal useful knowledge.

MATES is partially supported by the European Union's Horizon 2020 research and innovation programme datAcron: Big Data Analytics for Time Critical Mobility Forecasting under grant agreement No 687591