Anticipatory Smart Sensing System Interface Development Framework by CICT
(duration: 3.5 hours)

Professor Rodolfo A. Fiorini
Department of Electronics, Information and Bioengineering
Politecnico di Milano University, Milano, Lombardia
ITALY
E-mail: rodolfo.fiorini@polimi.it
 

Abstract: In a continuously changing operational environment, even if operational parameters cannot be closely pre-defined at system design level, we need to be able to design antifragile self-organizing, self-regulating and self-adapting system quite easily anyway. Current human made application and system can be quite fragile to unexpected perturbation because statistics can fool you, unfortunately. We need resilient and antifragile application to be ready for next generation systems. Cybernetics (i.e. advanced control theory) and complexity theory tell us that it is actually feasible to create resilient social and economic order by means of self-organization, self-regulation, and self-governance. From this point of view, current most advanced "embedded intelligent system" is a "deficient system", a fragile system, because its algorithms are based on statistical intelligence or knowledge only, and thus are lacking a fundamental evolutive system component. In fact, decision theory, based on "fixed universe" or a model of possible outcomes, ignores and minimizes the effect of events that are "outside model". Deep epistemic limitations reside in some parts of the areas covered in decision making. Unfortunately, the "probabilistic veil" can be very opaque computationally, and misplaced precision leads to confusion. To grasp a more reliable representation of reality and to get stronger physical and biological system algorithm, researchers and scientists need two intelligently articulated hands: both stochastic and combinatorial approach synergically articulated by natural coupling. In the past, many attempts to arrive to a system continuum-discrete unified mathematical approach have been proposed, all of them with big operational compromises. All these attempts use a top-down (TD) point-of-view (POV). From a computational perspective, all approaches that use a TD POV allow for starting from an exact global solution panorama of analytic solution families, which, unfortunately, offers a shallow local solution computational precision to real specific needs; in other words, overall system information from global to local POV is not conserved, as misplaced precision leads to information dissipation and confusion. On the contrary, to develop antifragile system, we need asymptotic exact global solution panoramas combined to deep local solution computational precision with information conservation. The first attempt to identify basic principles to achieve this goal for scientific application has been developing at Politecnico di Milano since the end of last century. In 2013, the basic principles on computational information conservation theory (CICT), for arbitrary- scale discrete system parameter from basic generator and relation, appeared in literature. We need anticipatory smart sensing system interfaces. To behave realistically, system interface must guarantee both Logical Aperture (to survive and grow) and Logical Closure (to learn and prosper), both fed by environmental "noise" (better� from what human beings call "noise"). We present an adaptive and learning system reference architecture for anticipatory smart sensing system interface (Interaction Interface System, IIS) development, capable to interact in real-time by design and to learn from its mistakes. IIS can be used even for advanced ISS (Inner Safety System) in advanced biomedical and advanced healthcare system development.

Short biography: Born in Ancona, Italy, Rodolfo A. Fiorini completed his high school education at Liceo Scientifico Luigi II di Savoia in 1969, Ancona, IT. In 1975, he graduated in Electronic Bioengineering at the Politecnico di Milano University, Milano, IT. In 1979, Dr. Fiorini was awarded for "Energetics Fellowship" from the Italian Ministry of Scientific Research and University and attended Bocconi University, School of Economics, and Politecnico di Milano University, specializing in Energetics. He obtained his Ph.D. degree in Energetics (100/100) from Politecnico di Milano University, in 1984. In the 80s, Dr. Fiorini was research associate to Stanford University (SU), Department of Aeronautics and Astronautics, Stanford, CA, U.S.A. and to University of California at Los Angeles (UCLA), Department of Computer Science, CA, USA. The U.S.A. DOL appointed him with the Ph.D. degree in Bioengineering in 1989. A senior member of the IEEE and the EMBC, Dr. Fiorini is currently a tenured Professor at the Department of Electronics, Information and Bioengineering (DEIB) at Politecnico di Milano University, Milano, IT, where he founded the Research Group on Computational Information Conservation Theory (CICT), and he is responsible for the main course on Wellbeing Technology Assessment. His current research interests include biomedical cybernetics, neuroscience, wellbeing, consciousness, nanoscience, computer simulation techniques, information theory, anticipatory learning systems, networked-control systems, machine learning, machine intelligence, statistical and deterministic signal processing, statistical and combinatorial optimization techniques, decision support systems, advanced management systems. Author of more than 230 national, international, scientific and technical, articles, papers, seminars, presentations and books. Since 1995 Dr. Fiorini has been a Co-Chair and Programme Committee Member for ISATA International Symposia (Virtual Reality and Supercomputing Applications; Simulation, Diagnosis and Virtual Reality Applications; Robotics, Motion and Machine Vision; Mechatronics, Efficient Computer Support for Engineering, Manufacturing, Testing & Reliability). Currently, Dr. Fiorini is associated editor of the Journal of Technology in Behavioral Science (JTiBS), sponsored by the Coalition for Technology in Behavioral Science (CTiBS) and an editorial panel member for EC Oceanography open access journal.