The National Technical University of Athens (NTUA) is the oldest and most prestigious educational institution of Greece in the field of technology, and has contributed unceasingly to the country's scientific, technical and economic development since its foundation in 1836.
The group of Process Control and Informatics belongs to the School of Chemical Engineering at NTUA. It is composed of one faculty member, one Professor Emeritus, two post-doc researchers, 2 Ph.D students and several undergraduate students working on their Diploma theses. The research interests of the laboratory focus on systems identification, optimization and control and on knowledge discovery, data mining and predictive modelling by developing and implementing statistical methods and advanced machine learning and computational intelligence algorithms, with particular emphasis on QSAR.
WP4 (Analysis and Modeling) leader. Integration of data and analysis resources. Development of user applications. Development of reporting tools.
NTUA has extensive experience in health and safety related computational research projects. In particular, through the participation in the Opentox FP7 funded project, NTUA has gained wide experience on the development and implementation of statistical and machine learning algorithms as RESTful web-services, aiming at the creation and validation of QSAR models for predicting toxicity related end-points (http://opentox.ntua.gr/). The NTUA group members have experience in developing database management tools and Java-based web services, in designing and implementing SSO-based authorization and authentication APIs, and on “web2.0” technologies such as Web Ontologies (OWL-DL) and RDF (Resource Description Framework).
Dr. Haralambos Sarimveis received a Diploma in Chemical Engineering from NTUA in 1990 and the M.Sc. and Ph.D. degrees in Chemical Engineering from Texas A&M University, in 1992 and 1995 respectively in the areas of computational intelligence and automatic control. Currently, he is an Associate Professor heading the “Unit of Process Control and Informatics” laboratory in the School of Chemical Engineering at NTUA. His research interest is in automatic control, computational intelligence, machine learning, pattern recognition, mathematical modelling and optimization, data mining, cheminformatics and bioinformatics. He has supervised 20 diploma and postgraduate theses and 5 doctoral theses. His published work includes 83 publications in scientific journals, 3 book chapters and over 80 publications and talks in conferences and workshops. His work has received over 1300 citations (excluding self-citations), h-index: 24 (Source: Scopus). He has participated in 14 national and international research projects, in 5 of which as project leader.
Dr. Pantelis Sopasakis received his Diploma in Chemical Engineering in 2007, his Master’s degree in Applied Mathematics in 2009 and his PhD. on "Modelling and Control of Biological and Physiological Systems" in 2012 from NTUA. He participated in the EU-funded project OpenTox, where he developed model training and data processing tools, a Java interface to predictive toxicology web-services and a user interface for generating QPRF reports. He has also participated in the EU-funded project CADASTER, where he developed a web application which estimates the environmental risks from chemical releases. His main research interests are machine learning, QSAR modelling, cheminformatics, Web ontologies, Semantic Web technologies and control theory with emphasis on biological and environmental systems.
|
1)
|
Alexandridis, E. Chondrodima, H. Sarimveis, “Radial Basis Function network training using a non-symmetric partition of the input space and Particle Swarm Optimization”, IEEE Transactions on Neural Networks and Learning Systems, 24(2), 219-230, 2013. |
|
2)
|
Hardy, B. et al, Collaborative Development of Predictive Toxicology Applications, Journal of Cheminformatics 2010, 2:7, 2010. |
|
3)
|
G. Melagraki, Afantitis Α., H. Sarimveis, O. Iglessi-Markopoulou, A. Alexandridis “A novel RBF neural network training methodology to predict toxicity to Vibrio fischeri”, Molecular Diversity, 10(2), 213-221, 2006. |