Back to top

Research Projects

Current


ENEXA is a Horizon Europe project ending in 2025. Its mission is a human-centred and ethical development of digital and industrial solutions using Explainable Artificial Intelligence (AI). ENEXA aims at developing scalable, transparent and explainable machine learning algorithms for knowledge graphs, while maintaining their completeness and correctness. A supplementary innovation of ENEXA is its focus on human-centred explainability techniques based on the concept of co-construction, where human and machine enter a conversation to jointly produce human-understandable explanations. The CER team is developing scalable representation techniques for knowledge graphs.


EVENFLOW is a 3-year Horizon Europe project which aims at developing hybrid learning techniques for complex event forecasting, which combine deep learning with logic-based learning and reasoning into neuro-symbolic forecasting models. Crucial in the EVENFLOW approach is the online nature of the learning methods, handling progressively evolving data flows, the development of formal verification techniques and scalable algorithms for federated training and incremental model construction. The CER team is developing online neuro-symbolic learning and reasoning techniques, as well as methods for end-to-end forecast explainability and data augmentation via data programming.


CREXDATA is a Horizon Europe project whose vision is to develop a generic platform for real-time critical situation management including flexible action planning and agile decision making over streaming data of extreme scale and complexity, which uses federated predictive analytics and forecasting under uncertainty algorithms. In the envisioned framework, decision makers receive back extremely precise, explainable forecasted representations of future worlds reasoned about using transparent AI facilities and with reduced complexity via visual analytics and intuitive augmented reality provided on-site or remotely. The CER team is developing explainable forecasting techniques over streaming data.


ARIADNE is a 3-year H2020 project bringing together a novel high-frequency radio architecture, and an Artificial Intelligence network processing and management approach, into a new type of intelligent communications system beyond 5G. The project will employ Machine Learning (ML) and Artificial Intelligence (AI) techniques to manage the high-frequency communications and the dynamic assignment and reconfiguration of the metasurfaces, in order to allow for continuous reliable High Bandwidth connections in the Beyond 5G scenario. The CER team is developing these AI and ML techniques.


Past


INFORE was a H2020 project on extreme-scale interactive analytics and forecasting that ended in 2022. The aim of INFORE was to address the challenges posed by huge datasets and pave the way for real-time, interactive, extreme-scale analytics and forecasting. Today, at an increasing rate, industrial and scientific institutions need to deal with massive data flows, streaming-in from maritime surveillance applications, financial forecasting applications or cancel cells growth simulations as well as a multitude of other sources. The ability to forecast, as early as possible, a good approximation to the outcome of a time-consuming and resource demanding computational task allows to quickly identify undesired outcomes and save valuable amount of time, effort and computational resources. The CER team developed the forecasting and online learning technologies of INFORE.


Track&Know was a H2020 project that ended in 2021. Its mission was to research, develop and exploit a new software framework for increasing the efficiency of Big Data applications in the transport, mobility, motor insurance and health sectors. Track & Know integrated multidisciplinary research teams from Mobility Data management, Complex Event Recognition, Geospatial Modelling, Complex Network Analysis, Transportation Engineering and Visual Analytics to develop new models and applications. The Track & Know toolboxes were demonstrated in three real-world pilots using datasets from niche market scenarios to validate efficiency improvements. The CER team was responsible for the complex event recognition and forecasting technologies of Track & Know.


datACRON (Big Data Analytics for Time Critical Mobility Forecasting) was a H2020 3-year project that ended in 2019. It introduced novel methods for detecting threats and abnormal activity in very large numbers of moving entities, operating in large geographic areas. The CER team developed complex event recognition and forecasting technology, and applied it successfully to the maritime domain.


SPEEDD (Scalable ProactivE Event-Driven Decision-making) was a FP7 European project that ended in 2017. SPEEDD developed a prototype for proactive event-driven decision-making: decisions were triggered by forecasting events-whether they correspond to problems or opportunities-instead of reacting to them once they happen. The CER team coordinated the project and contributed to the development of novel techniques for real-time event recognition and forecasting under uncertainty. These techniques were successfully used for credit card fraud recognition and highway traffic management.


REVEAL (REVEALing hidden concepts in social media) was an FP7 project that ended in 2016. Further to discovering what is being said in social media, REVEAL determined how trustworthy that information is, based on predicting contributor impact and how much or to what extent this affects reputation or influence. The CER team developed techniques for social modality recognition, using heterogeneous data streams coming from various types of social media.


AMINESS (Analysis of Marine Information for Environmental Safe Shipping). A national (Greek) project that ended in 2015. The CER team developed probabilistic event recognition technology for the detection of maritime hazards, towards reducing the possibility of ship accidents.


USEFIL (Unobstrusive Smart Environments For Independent Living). An EU FP7 project that ended in 2014. The CER team developed probabilistic event recognition technology for the unobtrusive monitoring of elderly people in their smart homes.


PRONTO (Event Recognition for Intelligent Resource Managament). An EU FP7 project ended in 2012. The CER team developed event recognition technology for city transport management and emergency rescue operation management.