Plenary Talk 1: Fakhreddine Karray, Univ. of Waterloo, Canada
Plenary Talk 2: Manuel Roveri, Politecnico di Milano, Italy
Plenary Talk 3: Farouk Chérif, Univ. Sousse, Tunisia
Plenary Talk 4: Abderazek Ben Abdallah, Univ. of Aizu, Japan
Plenary Talk 5: Robert John, Univ. of Nottingham, United Kingdom

Plenary Talk 1

Fakhreddine Karray
Univ. of Waterloo, Canada

Title: Multi Entity Bayesian Networks for Situation Assessment in Connected Vehicular Network
Abstract: Inattentiveness of drivers has been shown to be the main cause in road accidents making it a major factor in road safety for next generation connected car systems. In this work, we propose a comprehensive framework to address the problem of road safety by tackling it from a high-level information fusion standpoint, considering the Vehicular Ad- hoc Networks (VANET) as the deployment platform. The proposed framework relies on the Multi-Entity Bayesian Networks (MEBN), which exploits the expressiveness of first- order logic for semantic relations, and the strength of the Bayesian networks in handling uncertainty. To demonstrate the capabilities of the proposed framework, we have developed a collision warning system simulator, which evaluates the likelihood of a vehicle being in a near-collision situation using a wide variety of local and global information sources available in VANET environment. Our experimental results for two driving scenarios simulating near-collision situations demonstrate the capability of the proposed framework to achieve situation assessment on the road.
Biography: Fakhreddine Karray is the Univ. Research Chair Professor in Electrical and Computer Engineering and co- Director of the Center for Pattern Analysis and Machine Intelligence Center at the Univ. of Waterloo, Canada. He received the Ing. Dip (EE), degree from ENIT, Tunisia and the PhD degree from the Univ. of Illinois, Urbana Champaign, USA in the area of systems and control. Dr. Karray’s research interests are in the areas of intelligent systems, soft computing, sensor fusion, and context aware machines with applications to intelligent transportation systems, cognitive robotics and natural man- machine interaction. He has (co)authored over 350 technical articles, a textbook on soft computing and intelligent systems, five edited textbooks and 13 textbook chapters. He holds 15 US patents. He has chaired/co-chaired 14 international conferences in his area of expertise and has served as keynote/plenary speaker on numerous occasions. He has also served as the associate editor/guest editor for more than 12 journals, including the IEEE Transactions on Cybernetics, the IEEE Transactions on Neural Networks and Learning, the IEEE Transactions on Mechatronics, the IEEE Computational Intelligence Magazine. He is the Chair of the IEEE Computational Intelligence Society Chapter in Kitchener- Waterloo, Canada.
Dr. Karray is the co-founder of Intelligent Mechatronic Systems Inc. and Voice Enabling Systems Technology Inc. (Vestec Inc.), two spinoff companies of the Univ. of Waterloo, employing collectively more than 230 scientists and engineers. He currently serves as the Chairman of the Board of Vestec Inc, with branches in Japan, Tunisia and USA. He is also a founding member and past Vice President of the Arab Science and Technology Foundation (ASTF).

Plenary Talk 2


Manuel Roveri
Politecnico di Milano, Italy

Title: Intelligence for Embedded Systems

Abstract: The emergence of nontrivial embedded units mounting a rich sensor platform, sensor networks, the Internet of Things, pervasive and cyber-physical systems has made possible the design of sophisticated applications where large amounts of real-time data are collected and analyzed. The talk will present some fundamental mechanisms behind intelligence and learning strategies and show how they represent the key ingredients needed to design the current and future generation of intelligent embedded systems and derived applications.
In particular, aspects related to the study and design of intelligent embedded systems (i.e., embedded systems inheriting intelligent mechanisms proper of human cognition), the investigation and design of adaptive computational-intelligence techniques (i.e., learning in non stationary environments) and the deployment of credible networked intelligent embedded systems able to operate in harsh environments will be introduced. We will see how these methodologies, techniques and solutions for adaptive and intelligent information processing systems allow the design of intelligent embedded systems able to interact proactively with the environment and react and adapt to evolving time-variant situations.
Biography: Manuel Roveri, received the Dr. Eng. degree in Computer Science Engineering from the Politecnico di Milano (Milano, Italy) in June 2003, the MS in Computer Science from the Univ. of Illinois at Chicago (Chicago, Illinois, U.S.A.) in December 2003 and the Ph.D. degree in Computer Engineering from Politecnico di Milano (Milano, Italy) in May 2007. Currently, he is an assistant professor at the Department of Electronics and Information of the Politecnico di Milano. 
He has been visiting researcher at Imperial College London (UK).
Manuel Roveri is an Associate Editor of the IEEE Transactions on Neural Networks and Learning Systems and served as chair and member in many IEEE subcommittees. He is the co-organizer of the IEEE Symposium on Intelligent Embedded Systems in 2014 and organizer and co-organizer of workshops and special sessions at IEEE-sponsored conferences. Current research activity addresses adaptation and learning in non-stationary environments and intelligence for embedded systems and cognitive fault diagnosis.
Manuel Roveri has published about 70 papers in international journals and conference proceedings.

Plenary Talk 3


Farouk Chérif
Univ. Sousse, Tunisia

Title: Stability and Oscillations of Recurrent neural networks (RNNs)

Abstract: Many scientific studies have proven that an animal continuously senses its environment via different perceptual means and integrates the sensory information to adapt its behavior. The temporal aspect of this integration is fundamental for the sensory perception. A population of neurons makes a success of this dynamic integration by an intricate combination of synchronization of potential of action and recurring connections.
Inspired by this biological mechanism, recurrent neural networks (RNNs) are believed to be a powerful sequence processing method. Recurrent interactions among large populations of neurons are expected to yield collective phenomena adapted for dealing with temporal behavior.
The stability of dynamical systems in presence of time-delay is a problem of big interest since the presence of a time-delay may induce instabilities, and complex behaviors for the corresponding schemes. In particular, the problem becomes even more difficult in the case when the delays are distributed or mixed.
This talk is concerned with the stability and oscillations to some delayed recurrent neural networks with periodic (resp. almost periodic, resp. pseudo almost periodic) environments.
Biography: Farouk Chérif received the B.S. degree from the Univ. of Monastir, Tunisia, the M.S. degree from the Univ. of Paris 7, France, and the Ph.D. degree from the Univ. of Paris 1 Panthéon-Sorbonne, Paris, France, all in mathematics/applied mathematics, in 1989, 1992 and 1995 respectively.
He was with CERMCEM, Univ. of Paris 1 Panthéon-Sorbonne from 1992 to 1996. In 1996, he joined the Department of Mathematics and Computer Science, Military Academy, Sousse, Tunisia.
He is currently an Associate Professor with the Department of Computer science, the higher institute of applied sciences and technology of Sousse, Univ. of Sousse.
Farouk is the author or co-author of more than 25 journal papers and book chapters. His research was first nonlinear analysis and especially the qualitative study of Hamiltonian systems. In particular, he defined and studied an index to characterize the existence of almost periodic solutions and chaotic behavior of Hamiltonian systems via Lyapunov exponents. Later, he studied the nonlinear dynamics and the delayed differential equations and different applications in various fields such as artificial neural networks (RNNs, CNNs, SICNNs). Hence, the existence of almost periodic solutions and/or almost auto-morphicof such models are established. Recently, Dr. Farouk has built a new and original space: Quadratic-mean pseudo almost periodic functions. This new concept has allowed to solve the stochastic differential equations and in particular the stochastic delayed recurrent neural networks.
Dr. Farouk, currently, serves as a reviewer of several international journals and a Program Committee for various international conferences and workshops.

Plenary Talk 4

Abderazek Ben Abdallah
Univ. of Aizu, Japan
Title: On-Chip Optical Interconnects for Future Computing Systems: Prospects and Challenges

Abstract: Interconnects will play a leading role in overall system performance and energy consumption of future computing systems. As new applications continuously require more communication bandwidth, electrical links in future many-core computing systems will not scale to the desired performance/power levels required to ensure efficient systems. This is due to the high power consumption, limited bandwidth, and signal integrity problems of the electrical links.
Optical interconnects is a novel and promising concept enabling low-power and high bandwidth especially when combined with wavelength division multiplexing to concurrently transfer multiple parallel optical stream of data through a single waveguide. This talk will discuss the prospects and challenges of this emerging paradigm and present our findings in the area. The talk will conclude by describing future prospects on photonic-electronic chips and their impacts on future computing systems.
Biography: Abderazek Ben Abdallah is a Full Professor of Computer Science and Engineering and Head of the Division of Computer Engineering, The Univ. of Aizu, Japan. He is also directing the Adaptive Systems Laboratory at the School of Computer Science and Engineering, the Univ. of Aizu, Japan. Prior to joining the Univ. of Aizu, he was a faculty member at the Graduate School of Information Systems, The Univ. of Electro-Communications at Tokyo from 2002-2007.
He received his B.S. degree in Electrical Engineering, and his M.S. degree in Computer Engineering from Huazhong Univ. of Science and Technology in 1994, and 1997, respectively. He received his PhD degree in Computer Engineering from the Univ. of Electro-Communications at Tokyo in 2002.
Dr. Ben Abdallah's research interests are in adaptive computing systems, and energy-efficient system design and many core SoC design. He is also active in the areas of network-on-chip and high-performance computing architectures.
He has published more than 200 publications in international journals and conferences, three books, received numerous research grants, and supervised more than 30 graduate and undergraduate students. He was awarded the 2010 Presidential Prize for scientific research and technology, and several best paper awards. He has delivered several keynotes at conferences as well as invited lectures/courses at well-known universities including, Hong Kong Univ. of Science and Technology and Huazhong Univ. of Science and Technology. In addition, he has frequently consulted for international governmental and industrial bodies.
Dr. Ben Abdallah served on the chair, editorial, and review boards of several journals and conferences including, founding and steering chair of the IEEE MC SoC Symposium Series. He has been also involved in organizing many symposia, and conferences sponsored by professional organizations as well as guest editor of special issues in journals, such as IEEE Transactions on Emerging Topics in Computing. He is a senior member of IEEE, and a member of ACM and IEICE.

Plenary Talk 5

Robert John
Univ. of Nottingham, United Kingdom

Title: Type-2 Fuzzy Logic in Decision Support

Abstract: This talk will provide an overview of Bob's research in type-2 fuzzy logic and its application in Decision Support.
Type-2 fuzzy sets are fuzzy-fuzzy sets - that is, where the fuzzy set has membership grades that are themselves fuzzy sets, rather than numbers in [0,1]. Fuzzy sets (type-1) have had significant success in control applications but by their very definition are not particularly 'fuzzy' and struggle in applications that attempt to mimic human reasoning in decision support systems. Introduced in 1975, type-2 fuzzy logic really started to grow in the late '90s led by Bob and Jerry Mendel. In the intervening period the number of type-2 papers and researchers has grown considerably. This talk will introduce the audience to type-2 fuzzy logic and provide a brief history.
Bob will describe practical application of his work in decision support, such as the aggregation of uncertain information, supply chain modelling and medical diagnosis.
Biography: Bob John has a BSc in Mathematics, a MSc in Statistics and a PhD in Fuzzy Logic. He worked in industry for 10 years as a mathematician and knowledge engineer developing knowledge based systems for British Gas and the financial services industry. Bob spent 24 years at De Montfort Univ. in various roles including Head of Department, Head of School and Deputy Dean. He led the Centre for Computational Intelligence research group from 2001 until 2012. Bob joined Nottingham this year where he leads on the LANCS initiative and Heads up the research group ASAP in the School of Computer Science. The LANCS Initiative is built on a collaboration between four U.K. Universities: Lancaster, Nottingham, Cardiff and Southampton. The U.K.'s Engineering and Physical Sciences Research Council granted £5.4 million to support the development of research at the edge of Computer Science and Operational Research. The Automated Scheduling, Optimization and Planning (ASAP) research group carries out multi-disciplinary research into mathematical models and algorithms for a variety of real world optimization problems. It has 8 academic staff, 9 researchers and over 30 PhD students.