Parallel Computational Research Group - PCRG

Parallel Computational Research Group (PCRG), led by M-Tahar Kechadi, current research interests are primary in 1) Grid computing and software, 2) distributed data mining on Grid platforms, and 3) data mining in Digital Forensics and Cybercrime Investigations. As the data has become the central focus of most of today’s real-world applications and computing/storage platforms, these research themes share much in terms of goals, challenges and outcomes and there is also much conceptual cross-fertilisation between them.

PCRG’s current research projects’ goals are twofold: 1) design, develop and implement innovative distributed data mining techniques for real-world data intensive applications, such as digital forensics and cybercrime, telecommunication systems, banking and finance. 2) Provide these techniques with services and middleware tools in order to take advantage of the available distributed platforms such as the Grid. In other words, provide software environments for Grid infrastructure and for Grid-based data mining infrastructure, develop novel distributed data mining techniques, and apply these new concepts to real-world problems. PCRG has a range of ongoing projects including DGET (Data Grid Environment and Tools) and ADMIRE (A Distributed Data Mining Infrastructure). DGET is a Grid P2P middleware that exhibits the advantageous characteristics of both grid and peer-to-peer systems. DGET is a completely decentralised system that is highly scalable and self-configuring. DGET also provides strong transparent migration capabilities that add great value to the grid middleware. The ADMIRE system is characterised by its grid data mining engine and a knowledge map layer for distributed knowledge representation. The later is very important in distributed platforms, such as Grids. More details about these projects and other projects are given in projects’ descriptions under Research Section.