Descripción del proyecto
Intelligent Content and Semantics
Not just a single reasoning engine, but a generic platform and an open architecture
LarKC will develop the Large Knowledge Collider, an open-source pluggable distributed infrastructure for real-time incomplete reasoning and search, exploiting techniques and heuristics from areas as diverse as databases, machine learning, cognitive science and Semantic Web. The platform will fulfil needs in sectors that are dependent on massive heterogeneous information sources such as telecommunication services, bio-medical research, and drug-discovery. LarKC is designed to harness the efforts of various research communities so as to deliver the paradigm shift required for reasoning at Web scale.
Current Semantic Web reasoning systems do not scale to the requirements of their hottestapplications, such as analyzing data from millions of mobile devices, dealing with terabytes ofscientific data, and content management in enterprises with thousands of knowledge workers.We will build the Large Knowledge Collider (LarKC, for short, pronounced "lark"), a platformfor massive distributed incomplete reasoning that will remove these scalability barriers. Thiswill be achieved by:- Enriching the current logic-based Semantic Web reasoning methods with methodsfrom information retrieval, machine learning, information theory, databases andprobabilistic reasoning,- Employing cognitively inspired approaches and techniques such as spreading activation,focus of attention, reinforcement, habituation, relevance reasoning, and boundedrationality.- Building a distributed reasoning platform and realising it both on a high-performancecomputing cluster and via "computing at home".The consortium is an interdisciplinary team of engineers and researchers in Computing Science,Web Science and Cognitive Science, well qualified to realize this ambitious vision. The LargeKnowledge Collider will be an open architecture. Researchers and practitioners from outside theconsortium will be encouraged to develop and plug in their own components to drive parts of thesystem. This will make the Large Knowledge Collider a generic platform, and not just a singlereasoning engine.The success of the Large Knowledge Collider will be demonstrated in three end-user casestudies. The first case study is from the telecom sector. It aims at real-time aggregation andanalysis of location data obtained from mobile phones carried by the population of a city, in orderto regulate city infrastructure functions such as public transport and to provide context-sensitivenavigation information. The other two case studies are in the life-sciences domain, relatedrespectively to dr
Ámbito científico
- natural sciencesphysical sciencestheoretical physicsparticle physicsparticle accelerator
- natural sciencescomputer and information sciencesdatabases
- engineering and technologyelectrical engineering, electronic engineering, information engineeringinformation engineeringtelecommunicationsmobile phones
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
- natural sciencescomputer and information sciencesinternetsemantic web
Convocatoria de propuestas
FP7-ICT-2007-1
Consulte otros proyectos de esta convocatoria
Régimen de financiación
CP - Collaborative project (generic)Coordinador
6020 Innsbruck
Austria
Ver en el mapa
Participantes (19)
1220 Wien
Ver en el mapa
La participación finalizó
1784 SOFIA
Ver en el mapa
1784 Sofia
Ver en el mapa
100124 BEIJING
Ver en el mapa
80333 Munchen
Ver en el mapa
70174 Stuttgart
Ver en el mapa
80539 Munchen
Ver en el mapa
69007 Lyon 7eme
Ver en el mapa
20126 Milano
Ver en el mapa
135-848 SEOUL
Ver en el mapa
1081 HV Amsterdam
Ver en el mapa
405300 GHERLA
Ver en el mapa
400114 Cluj Napoca
Ver en el mapa
151 85 Sodertaelje
Ver en el mapa
1000 LJUBLJANA
Ver en el mapa
S10 2TN Sheffield
Ver en el mapa
1060 WIEN
Ver en el mapa
20133 Milano
Ver en el mapa
TX 78731 Austin
Ver en el mapa