Role:Principal Investigator.

As an adjunct researcher at Athena IMSI.

EVENFLOW will develop hybrid learning techniques for complex event forecasting, which combine deep learning with logic-based learning and reasoning into neurosymbolic forecasting models. The envisioned methods will combine (i) neural representation learning techniques, capable of constructing event-based features from streams of perception-level data with (ii) powerful symbolic learning and reasoning tools, that utilize such features to synthesize high-level, interpretable patterns of critical situations to be forecast.

(EU Project, 2022-25)

Role: Main Investigator for Technical University of Crete.

CREXDATA's vision is to develop a generic, real-time platform for critical and emergency situation management. To this end the platform focuses on flexible action planning and flexible decision making on continuous streams of relevant data of large scale and complexity. To achieve its vision, CREXDATA will develop a next-generation Prediction-as-a-Service (PaaS) system where critical decision makers will easily register their data sources and obtain computing resources from private or public clouds in order to perform predictive data analysis workflows. These workflows will be designed graphically, easily and quickly and will include the whole process of (i) collecting data streams in real time, (ii) simulating critical scenarios and situations, (iii) distributed machine learning to extract patterns that lead to emergency/critical situations and (iv) multi-temporal forecasting. Decision makers will get back highly accurate predictions through visual analytics and augmented reality techniques, reasoned about using transparent AI techniques.

(EU Project, 2023-26)

Role:co-Coordinator (Coordinator: Antonios Deligiannakis).

As an adjunct researcher at Athena IMSI.

At an increasing rate, industrial and scientific institutions need to deal with massive data flows streaming in from a multitude of sources. For instance, maritime surveillance applications combine high-velocity data streams, including vessel position signals emitted from hundreds of thousands of vessels across the world and acoustic signals of autonomous, unmanned vessels; in the financial domain, stock price forecasting and portfolio management rely on stock tick data combined with real-time information sources on various pricing indicators; at the fight against cancer, complex simulations of multi-cellular systems are used, producing extreme-scale data streams in an effort to predict the effects of drug synergies on cancer cells. In these applications, the data volumes are expected to dramatically grow in the future. Processing this data often requires not only using an HPC infrastructure, but also having data scientists, who are typically not expert programmers, program complex workflows, with a vast number of parameters to tune through time-consuming repeated programming and testing. INFORE addressed these challenges and paved the way for real-time, interactive extreme-scale analytics and forecasting. The ability to forecast, as early as possible, a good approximation to the outcome of a time-consuming and resource-demanding computational task allowed to quickly identify undesired outcomes and save valuable amount of time, effort and computational resources, which would otherwise be spent in vain. INFORE also designed and developed a flexible, pluggable, distributed software architecture that is programmable and set up by graphical data processing workflows. The INFORE prototype was tested on massive real-world data from the life sciences, financial and maritime domains.

(EU Project, 2019-22)

Role: Main Investigator for Technical University of Crete.

As a research collaborator at the SoftNet Lab.

The goal of the FERARI project is to pave the way for efficient and timely processing of Big Data. We intend to exploit the structured nature of M2M data while retaining the flexibility required for handling unstructured data elements. Taking into account the structured nature of the data will enable business users to express complex tasks, such as efficiently identifying sequences of events over distributed sources with complex relations, or learning and monitoring sophisticated abstract models of the data. These tasks will be expressed in a high-level declarative language (as opposed to programming them manually as is the case in current streaming systems). The system will be able to perform these tasks in an efficient and timely manner.

(EU Project, 2014-17)

Role: co-Principal Investigator for Technical University of Crete.

As a research collaborator at the SoftNet Lab.

The EIPAS project is related to the improvement of patient safety in the healthcare systems, in terms of technology necessary to provide rapid and accurate information for adverse events. The modern approach of Medical Devices Vigilance system is not only based on official user reports but also includes the introduction of additional means for data mining, standardization and codification of the information from different sources worldwide.

("THALIS" - Operational Programme "Education & Lifelong Learning", 2012-15)

Role: Main Investigator for Technical University of Crete.

As a postgraduate collaborator at the SoftNet Lab.

The goal of LIFT is to enable the local detection of global phenomena and the efficient and effective detection of phase changes in very large data streams, where it is impossible or ineffective to accumulate all data into a single place. In addition, this will give rise to new methods for analyzing privacy-sensitive data, where it is not desirable to move data away from the point where it is collected. This will be facilitated by developing a theory based on the novel Safe-Zone-Approach and related methodologies.

(EU Project, 2010-13)