The aim of this talk is to present research results of the Complex Event Recognition lab (http://cer.iit.demokritos.gr/) of NCSR Demokritos (Athens, Greece), focusing on maritime applications. Maritime monitoring systems support safe shipping, through real-time detection of dangerous, suspicious and illegal vessel activities. We have been developing a complex event recognition system for maritime monitoring in the Event Calculus, allowing both for verification and real-time performance. The basic system is being developed through collaboration with domain experts, constructing effective patterns of maritime activity. In order to refine these patterns, we have developed online, relational learning techniques and applied them on AIS data streams. More recently, we have also been developing complex event forecasting techniques, allowing for predictive maritime analytics. In the talk, we will show results of our techniques on real AIS streams, covering large geographical areas.
George Paliouras is a senior researcher and head of the Intelligent Information Systems division of the Institute of Informatics and Telecommunications at NCSR "Demokritos", Greece. He holds a PhD in Machine Learning and has performed basic and applied research in Artificial Intelligence for the last 20 years. He is interested in the development of novel methods for addressing challenging big and small data analysis problems, such as learning complex models from structured relational data, learning from noisy and sparse data, learning from multiple heterogeneous data streams, discovering patterns in hypergraphs. He is motivated by research that addresses real-world problems and has contributed in a variety of such problems, ranging from spam filtering and Web personalization to complex event recognition and biomedical information retrieval. He has co-founded the spin-off company i-sieve technologies that provides online reputation monitoring services. He has served as board member in national and international scientific societies; in the editorial board of international journals and has chaired international conferences. He is involved in several research projects and has the role of scientific coordinator (PI or co-PI) in some of them. In particular, he was PI of the SPEEDD project, that was funded by the European Commission το develop a proactive decision-making system, based on scalable even recognition technology. He is also co-PI of the projects datAcron and ‘Track and Know’, involving complex event recognition and forecasting in various domains, among which maritime monitoring. These projects are implemented by the Complex Event Recognition group of NCSR “Demokritos”.
Hosts: Stan Matwin (firstname.lastname@example.org) and Evangelos Milios (email@example.com)