Department of Biophysical and Electronic Engineering (DIBE), University of Genoa, Italy
The Department of Biophysical and Electronic Engineering (DIBE) was established at the University of Genoa in 1984 by a group of researchers working in the fields of Electronics, Bioengineering, Systems and Circuits, Electromagnetism, and Mathematical Physics. DIBE research activities focus on Information Technology and Biophysical Engineering as well as promoting technical and scientific development through collaborations and contracts with the European Commission, national and international research agencies, private companies, technological districts and other institutions.
The SmartLab is one of the Research Laboratories at DIBE. The expertise of the SmartLab is mainly focused on methods and algorithms for advanced information processing and their implementation on electronic systems. SmartLab know-how includes state-of-the-art methods for the analysis of information, knowledge discovery and induction of models from experimental data, based on statistical, machine learning and computational intelligence techniques. The main research activities aims at combining Computational Intelligence (e.g. neural networks, machine learning methods, etc.) with Electronics and Computer Engineering for solving real-world industrial and scientific problems, which cannot be effectively solved by conventional methodologies and systems. Innovative techniques for information processing are implemented on a large spectrum of computing facilities and devices. Hardware implementations span the entire range of electronic devices from custom electronics to programmable logic devices (e.g. FPGAs), while software implementations range from Digital Signal Processors (DSPs) to conventional Personal Computers (PCs), up to Multi-core CPUs and parallel/distributed systems (e.g. computer clusters). Applications areas include, but are not limited to, industrial/scientific data mining and information classification, bioinformatics, nonlinear system identification and control, smart/adaptive information processing, real-time intelligent data processing, and intelligent sensor networks.
The SmartLab is coordinated by Prof. Davide Anguita, who has been leader of the EC RAIN project (Redundant Arrays of Inexpensive Workstations for Neurocomputing), member of the EC Networks of Excellence (NoEs) NeuroNet I and NeuroNet 2, chair of the Smart Adaptive Systems section of the EC NoE EUNITE (European Network on Intelligent Technologies for Smart Adaptive Systems) and Chair of the Focus Group "Data Technologies" of the EC Concerted Action NiSIS (Nature-inspired Smart Information Systems). Currently, he is the coordinator of the pattern recognition tasks of the EC-NMP FP7 EXCELL project. He has been project manager of several research projects between academia and national industries or scientific institutions (e.g. National Institute for Cancer Research, Ansaldo STS, Whirlpool Europe, Elsag Datamat, Electrolux‐Zanussi) including the Cooperation between DIBE and the Ferrari Formula-1 Racing Team for the application of intelligent technologies to F1.
Profile of staff members
Prof. Davide Anguita is coordinator of the SmartLab. After working as a Research Associate at the International Computer Science Institute, Berkeley, CA, on special-purpose processors for neurocomputing, he joined DIBE, where he is currently an Associate Professor of Smart Electronic Systems. He is co‐author of more than 100 publications on the theory and application of kernel methods and artificial neural networks, as well as two patents on Intelligent Technologies for pattern recognition. He has been evaluator of projects for several national and international research programmes (PRIN, POR, EC-FP7-ARTEMIS, EC FP7-FET). In 2006 he co-founded "Smartware & Data Mining", the first spin‐off of the University of Genoa.
Dr. Alessandro Ghio is postdoc researcher at the SmartLab. He works as a consultant in order to give organizational and technical support for coordinating and managing national and international funded projects. He is co-author of more than 20 publications on Computational Intelligence, kernel methods and Data Mining. He won the "Gold Leaf" (best paper award) at the IEEE Ph.D. Research in Microelectronics and Electronics (PRIME) Conference in 2007.
Five recent publications relevant to the project
 D. Anguita, A. Ghio, S. Pischiutta, S. Ridella, "A Support Vector Machine with integer parameters", Neurocomputing, Vol. 72, pp. 480-489, 2008.
 D. Anguita, L. Carlino, A. Ghio, S. Ridella, "A FPGA Core Generator for Embedded Classification Systems", Journal of Circuits, Systems and Computers, Vol. 20, pp. 263-282, 2011.
 D. Anguita, A. Ghio, S. Ridella, "Maximal Discrepancy for Support Vector Machines", Neurocomputing, Vol. 74, pp. 1436-1443, 2011.
 D. Anguita, A. Ghio, L. Oneto, S. Ridella, "The Impact of Unlabeled Patterns in Rademacher Complexity Theory for Kernel Classifiers", In: Advances in Neural Information Processing Systems, 2011.
 D. Anguita, A. Ghio, N. Greco, L. Oneto, S. Ridella, "Model Selection for Support Vector Machines: Advantages and Disadvantages of the Machine Learning Theory", Proc. of the IEEE International Joint Conference on Neural Networks (IJCNN), Barcelona, Spain, 2010.