Recent Projects

The specific objectives of the project are the following:

1. Explore the use of machine learning techniques for the modelling of trajectories and estimation of hidden variables from historical air traffic data.

2. Develop new machine learning algorithms for traffic pattern classification.

3. Investigate the use of active learning metamodelling to enable a more efficient exploration of the input‑output space of complex ATM simulation models.

4. Demonstrate and evaluate the newly developed techniques in order to assess their maturity, derive recommendations on how to apply them to ATM performance assessment, and propose a roadmap for the transition of the project results to the next stages of the R&D cycle.

Objective: The objective of this PhD is to explore and present novel algorithms towards planning conflict-free trajectories at the pre-tactical phase of operations in computationally efficient ways, for large number of trajectories in airspaces comprising multiple FIRs, following a methodology combining data-driven and agent-based approaches.

Challenges:
1. Addressing conflict-free trajectory planning among multiple flights, simultaneously, while considering complex ATM phenomena and operational constraints.
2. Addressing optimization in trajectory planning taking into account multiple objectives concerning airspace use, cost indicators, preferences and constraints of stakeholders involved.
3. Follow a data-driven approach to reveal stakeholders’ preferences on trajectories followed and on resolving conflicts.
4. Addressing complex air traffic management phenomena due to traffic.
5. Addressing scalability: Coordinating between different FIRs for large number of flights.

· Definition of requirements for the input datasets needed. The requirements will consider the trajectory prediction accuracy expected.
· Study of the application of big-data techniques to trajectory related data gathering, filtering, storing, prioritization, indexing or segmentation to support the generation of reliable and homogenous input datasets.
· Study of different data-driven learning techniques to describe how a reliable trajectory prediction model will leverage them.
· Formal description of the complexity network to support correlated multiple trajectory predictions .
· Study of the application of agent-based models to the prediction of multiple correlated trajectory predictions considering complexity network.
· Description of visualization techniques to enhance trajectory data management capabilities.
· Exploration of advanced visualization processes for data-driven model algorithms formulation, tuning and validation, in the context of 4D trajectories.

The goal of the AMINESS project is to contribute in the safety, management and monitoring of the sea environment and the Aegean Sea in particular.
Reducing the possibility of ship accidents in the Aegean Sea is important to all economic, environmental, and cultural sectors of Greece. Oil spill cleanups can cost over 1 billion Euros, whereas accidents involving water soluble cargos would result in irrevocable changes to the Aegean ecosystem. Despite an increase in traffic, there are no national-level monitoring policies and ships formulate routes according to their best judgment. However, to reduce their own financial risk, shipping companies would directly benefit from a system that can reduce the possibility of an accident involving their own ship.
The project objective is the development of a web portal offering access to ship owners, policy makers and the scientific community. The portal will be used to (a) suggest vessel and environmentally optimal safe route planning (b) deliver real-time alerts for ships and (c) support policy recommendations. The portal will be based on historical and real-time maritime data, including real-time information for ship position and speed, weather and sea forecasting and land and sea location. Through this web-portal, the project aims directly to reduce the risk of a ship accident and consequently to contribute in the protection of the Aegean Sea. At the same time, the web-portal aims to bring profit to the enterprise partners of the project, mainly by proposing accident risk reducing services to ship owners. The research partners will be given a unique opportunity to advance their methodologies for handling and analysis of huge quantities of heterogeneous spatiotemporal streaming data to assess risk in real time. Any lessons learned from the analysis of the high risk ship traffic of the Aegean Sea are likely to have direct and immediate relevance to policy makers and stakeholders globally.

Traditional distinctions between the natural, the social and the artificial are becoming more and more blurred as radically new forms of Information Technology-enabled social environments are formed. These changes create the need to re-explore basic concepts of Philosophy, Humanities and Social Sciences. The aim of the European Network for Social Intelligence is twofold:

To look into those IT-enabled domains as a means for the critical examination of those basic concepts and,
To propose new approaches to understand and develop future IT-enabled social situations, by adapting and applying traditio-nal concepts.