Czech Technical University in Prague, Czech Republic
The CZECH TECHNICAL UNIVERSITY IN PRAGUE (CVUT), founded in 1707, is one of the oldest technical universities and currently the leading technical university in the Czech Republic with approx. 23 000 students enrolled in engineering courses. It offers 78 Master degree and 55 PhD programs. CVUT with over 1700 members of academic staff is also one of the largest research institutions in the Czech Republic.
The Department of Cybernetics at the Czech Technical University in Prague is a leading research body in the field of cybernetics, robotics and informatics in the Czech Republic. It employs 130+ members of academic and research staff and it was recognized as the EU Center of Excellence in 2000. It provides Master and PhD courses in technical cybernetics, artificial intelligence, computer-integrated manufacturing, computer vision, pattern recognition, medical informatics, and biomedical engineering. The department has been actively involved in scientific collaboration with international partners via various types of research programmes namely FP6 and FP7 programmes including the MC Actions (more than 20 projects).
Four research units of the Department of Cybernetics are ready to contribute to the ITFoM project:
Intelligent Systems Group (ISG) is a research group performing fundamental and applied research in the field of agent-based computing, multi-agent systems and agent technologies. ASC researchers work on various cutting edge research projects, have unique set of skills and broad international experience. The main objective of the ASC research is to contribute to: (i) applied agent research mainly in manufacturing, automotive industry, and health-care (ii) fundamental research in agent-based computing and multi-agent systems and (iii) large scale prototype and demonstration systems development.
Intelligent Data Analysis (IDA) Group of the Department of Cybernetics is one of Europe's leading laboratories for machine learning. In IDA, we are mainly concerned with learning robust yet human-interpretable models from non-trivially structured data while automatically exploiting available background knowledge such as expert rules or process models. To this end, we develop machine learning algorithms based on combinations of relational logic and statistics and apply these algorithms mainly in various areas of biomedicine. The Group is currently running two projects concerned with applying machine learning in genomics, in the respective contexts of systems biology and structural biology.
Nature Inspired Technology (NIT) Group is studying synchronized streams of data and signals gathered in diverse ways from a studied human subject with intention to gain such hidden information about his/her health condition or mood that can serve for improvement of treatment of the patient, for speeding up the diagnostic process or for estimating value of some signal that is not easy to obtain (e.g. only invasive measurement is available).
Biomedical Data and Signal Processing (BioDat) Group is Czech leading laboratory in the area of medical signal and data processing. In BioDat, we are mainly concerned with advanced methods of heterogeneous medical signal and data processing and interpretation, using non-traditional methods of feature extraction and selection combining tools for traditional signal processing (mathematical transforms, speech signal processing), machine learning methods and biologically inspired algorithms (PSO, ACO).
ISG: The former ATG Group has developed its own agent platform AGLOBE designed for testing experimental scenarios featuring agents' position and communication inaccessibility, but it can be also used without these extended functions. The platform provides functions for the residing agents, such as communication infrastructure, store, directory services, migration function, deploy service, etc. Communication in A-globe is very fast and the platform is relatively lightweight. It is suitable for real-world simulations including both static (e.g. towns, hospitals, etc.) and mobile units (e.g. vehicles, patients). In such case the platform can be started in extended version with Geographical Information System (GIS) services and Environment Simulator (ES) agent.
IDA: The Group is currently running two projects concerned with applying machine learning in genomics, in the respective contexts of systems biology and structural biology. Within the former, the Group has developed the public web-tool XGENE.ORG for integrated cross-genome analysis of gene expression data under the presence of background knowledge such as metabolic pathways and the Gene Ontology. In the latter project (joint with the Univ. of Minnesota), the team is trying to contribute to the improvement of novel gene-therapy methods by developing predictors of locus-specific DNA-binding propensity of zinc finger nucleases by machine-learning from sequential and/or spatial structures of engineered zinc fingers and other proteins.
NIT: The group has participated in several recent projects, e.g. STREP IST 045 282 OLDES: Older Peoples e/Services at Home (2007-10) or MAS: Nanoelectronics for Mobile Ambient Assisted Living (AAL) Systems (2010-2012), that provided us with rich experience in design, development and testing web-based e-health solutions intended to ensure individualized care to patients in their home environment through remote supervision using multi parameter biosensors and secure communication networks.
BioDat: The team has developed several larger decision support systems that have been applied to medical tasks (e.g. automated evaluation of long-term EEG recordings, intracardial signal complexity evaluation). Recently the team has developed several tools for medical signals processing and visualization (EEG, ECG, cardiotocography, intracardial signals). In the K4CARE project (Knowledge-Based Homecare eServices for an Ageing Europe - EU FP6 -STREP, 2006-2009) we were responsiblie for the design and development of the database system architecture, security and mobile devices applications. We have participated in further EU projects: MAS: Nanoelectronics for Mobile Ambient Assisted Living (AAL) Systems (EU ENIAC Project, 2010-2012); NETCARITY: A NETworked multi-sensor system for elderly people: health CARe, safety and securITY in home environment (EU FP6 - Integrated project, 2007-2011); DfA@eInclusion: Design for ALL for eInclusion (EU FP6 - Coordination Action, 2007-2009).
Profile of staff members
Prof. Vladimír Mařík was appointed a professor of Control Engineering at the Czech Technical University, Prague, Czech Republic in 1990. Later, he founded the Department of Cybernetics, which has been recognized as an EU Center of Excellence (in 2000). He acts as the Head of this Department with 130 members of staff. This Department has a long-term contracted cooperation with such companies like Toyota, Volkswagen, Medtronic, Google, Honeywell and others. Besides this, V. Marik helped to found the Rockwell Automation Research Center Prague as a part of the Rockwell Automation Advanced Technology organization and he acted as its Managing Director in the period 1993-2009. His main fields of interests include artificial intelligence, agent-based, multi-agent and holonic systems, planning and scheduling, and knowledge representation and management. He is an author or a co-author of 7 books and more than 140 scientific papers.
Dr. Lenka Lhotská (PhD in Technical Cybernetics, CVUT, 1989) is associate professor and head of the BioDat research group; co-author of more than 70 publications in knowledge-based and multi-agent systems, machine learning, and advanced biomedical signal processing. Her main research interests are distributed AI, machine learning, knowledge-based systems, and applications to medical area. She has been project leader of a number of local and international R&D projects (e.g. 5FP, 6FP).
Five recent publications relevant to the project
1) Vrba, P. - Mařík, V.: Capabilities of Dynamic Reconfiguration of Multiagent-Based Industrial Control Systems. IEEE Transactions on Systems, Man, and Cybernetics - part A: Systems and Humans. 2010, vol. 40, no. 2, p. 213-223. ISSN 1083-4427.
2) Chudáček, V. - Georgoulas, G. - Lhotská, L. - Stylios, C. - Petrík, M. - et al.: Examining Cross-Database Global Training to Evaluate Five Different Methods for Ventricular Beat Classification. Physiological Measurement. 2009, vol. 30, no. 7, p. 661-677. ISSN 0967-3334.
3) Gerla, V. - Paul, K. - Lhotská, L. - Krajča, V.: Multivariate Analysis of Full-Term Neonatal Polysomnographic Data. IEEE Transactions on Information Technology in Biomedicine. 2009, vol. 13, no. 1, p. 104-110. ISSN 1089-7771.
4) Kléma, J. - Železný, F. - Trajkovski, I. - Karel, F. - Cremilleux, B. - et al.: Gene Expression Mining Guided by Background Knowledge. In Data Mining and Medical Knowledge Management: Cases and Applications. Hershey: IGI Publishing, 2009, p. 268-292. ISBN 978-1-60566-218-3.
5) Burša, M. - Lhotská, L.: Ant Colonies and Data Mining. In Handbook of Research on Artificial Immune Systems and Natural Computing: Applying Complex Adaptive Technologies. Hershey: Information science Reference, 2009, p. 405-421. ISBN 978-1-60566-310-4.