Behnaam Aazhang

Rice University, USA

Title : Can data analytics predict and prevent the onset of seizures in epileptic patients?

Abstract :

A fundamental research objective in neuro-engineering is to understand the ways in which functionalities of the brain emerge from the organization of neurons into highly connected circuits. This goal is one of the most critical scientific challenges in medicine of our generation. It is also critical in our understanding of how these functionalities are disrupted because of trauma and diseases like depression, Alzheimer’s, or Epilepsy.

In this presentation, I will discuss how signal processing techniques and graph- and information-theoretic tools can unravel brain's circuit connection that underlie the onset of a seizure in epileptic patients. These tools can also provide features to predict the onset and possibly prevent seizures.

Bio :

Behnaam Aazhang received his B.S. (with highest honors), M.S., and Ph.D. degrees in Electrical and Computer Engineering from University of Illinois at Urbana-Champaign in 1981, 1983, and 1986, respectively. From 1981 to 1985, he was a Research Assistant in the Coordinated Science Laboratory, University of Illinois. In August 1985, he joined the faculty of Rice University, Houston, Texas, where he is now the J.S. Abercrombie Professor in the Department of Electrical and Computer Engineering Professor and Director of Rice’s Neuroengineering Initiative.

From 2006 till 2014, he held an Academy of Finland Distinguished Visiting Professorship appointment (FiDiPro) at the University of Oulu, Oulu, Finland. Dr. Aazhang is a Fellow of IEEE and AAAS, a distinguished lecturer of IEEE Communication Society. He received an Honorary Doctorate degree from the University of Oulu, Finland (the highest honor that the university can bestow) in 2017. He is also the recipient of the IEEE ComSoc CTTC Outstanding Service Award "For innovative leadership that elevated the success of the Communication Theory Workshop” in 2016 and Outstanding Technical Achievement Award “For consistent, fundamental contributions to multiuser communication theory for wireless networks” in 2017. He is a recipient of 2004 IEEE Communication Society’s Stephen O. Rice best paper award for a paper with A. Sendonaris and E. Erkip. In addition, Sendonaris, Erkip, and Aazhang received IEEE Communication Society’s 2013 Advances in Communication Award for the same paper. He has been listed in the Thomson-ISI Highly Cited Researchers and has been keynote and plenary speaker of several conferences.

His research interests are signal processing, information theory, and their applications to - engineering with focus areas in (i) understanding neuronal circuits connectivity and the impact of learning on connectivity (ii) developing minimally invasive and non-invasive real-time closed-loop stimulation of neuronal systems to mitigate disorders such as epilepsy, Parkinson, depression, and obesity, (iii) building microelectronics with data analysis techniques to develop a fine-grained recording and modulation system to remediate language disorders, (iv) developing a patient-specific multisite wireless monitoring and pacing system with temporal and spatial precision to restore the healthy function of a diseased heart.

Erol Gelenbe

Institute of Theoretical and Applied Informatics (IITIS-PAN) of the Polish Academy of Sciences and Imperial College London UK

Title : Machine Learning for Cognitive Routing in Networks to Optimize QoS, Minimise Energy Consumption and Maximise Security

Abstract :

We will focus on the design principles and experimental results regarding the use of ML to optimize composite Goal functions that include the QoS, Security and Energy Consumption in Packet Networks. Three architectures will be described, based on the one hand on Cognitive Routers, secondly on Overlays, and thirdly on Software Defined Networks. All three approaches exploit Random Neural Networks that act as smart oracles for routing decisions and that are trained using reinforcement learning (RL). Each of the three approaches will be illustrated with experimental measurement results which show the effectiveness of the approach.

Bio :

Prof. Erol Gelenbe FIEEE FACM FIET FRSS, graduated from the Middle East Technical University, Ankara, Turkey. He is currently the coordinator (PI) of the H2020 SerIoT Research and Innovation project of the European Union that is developing a secure network infrastructure for the Internet of Things, together with industry partners ATOS, DT, T-Systems, HISPASEC, TECNALIA, AustriaTech, GRUVENTA, HIT, and academic partners TU Berlin and CERTH. His other cyber- security projects are H2020 GHOST and H2020 KONFIDO.

Known for pioneering the field of modelling and performance evaluation of computer systems and networks, he invented the random neural network and the eponymous G-networks. His awards include the ACM SIGMETRICS Life-Time Achievement Award, the "in Memoriam Dennis Gabor" Award of the Hungarian Academy of Sciences, the IET UK’s Oliver Lodge Medal, the Grand Prix France Telecom of the French Academy of Sciences, and honours such as Chevalier de la Legion d'Honneur and Commandeur de l’Ordre National du Merite of France.

He is a Fellow of the National Academy of Technologies of France and of the Science Academies of Belgium, Hungary, Poland and Turkey. He has graduated some 86 PhDs in Europe and the USA.

Ismail Khalil

Institute of Telecooperation Johannes Kepler University Linz, Austria

Title : Artificial Intelligence in the Age of Big Data

Abstract :

In February 2011, Watson (IBM super computer) managed to beat two past grand champions on the TV quiz show Jeopardy!. Watson was able to answer questions that require intelligence when done by humans. This marked the first machine to pass the Turing test and started a new era of computing called cognitive computing where computers (modeled after the human brain) learn and interact naturally with people in order to augment what either humans or machines could do on their own.

Google, Amazon, Facebook, etc., using big data technologies, smart machine learning, cognitive computing, NLP and AI algorithms were able to tap into our intentions by predicting what we click, buy, like, dislike, shop, surf, etc.,. This marked the era of smart Web or data intelligence where Turing test is reversed and machines now try to figure out who we are, our information needs, our behavioral patterns, the activities we are engaged in and our goals. Together with the torrents of data we leave behind us every time we communicate with the digital eco-system, a new era of human-machine cooperation is starting that gives us millions of potential insights into user experience, marketing, personal tastes, and human behavior.

In this talk, we are going to illustrate, through motivating cases, examples, and research directions, the main characteristics of this era and how it can transform the way we interact with the Web to ultimately improve the quality of our lives and gain valuable insights into our affective, mental and physical states.

Bio :

Ismail Khalil (http://www.iiwas.org/ismail/) is the deputy head of the institute of telecooperation, Johanes Kepler University Linz, Austria, since October 2002 and Adjunct Full Professor at Faculty of Science and Technology (FST), Syarif Hidayatullah Islamic State University Jakarta, Indonesia.

He is the president of the international organization of Information Integration and Web-based Applications & Services (@WAS). He holds a PhD in computer engineering and received his habilitation degree in applied computer science on his work on agents interaction in ubiquitous Environments in May 2008. He currently teaches, consults, and conducts research in Mobile Multimedia, Cloud Computing, Agent Technologies, and Web Intelligence and is also interested in the broader business, social, and policy implications associated with the emerging information technologies.

Before joining Johannes Kepler University of Linz, he was a research fellow at the Intelligent Systems Group at Utrecht University, Netherlands from 2001-2002 and the project manager of AgenCom project at the Software Competence Center Hagenberg Austria from 2000-2001. Dr. Khalil has authored around 150 scientific publications, books, and book chapters. He serves as the Editor-in-Chief of 4 international journals and 2 books series. His work has been published and presented at various conferences and workshops.

Aria Nosratinia

Texas University at Dallas, USA

Title : Community Detection on Graphs with Side Information

Abstract :

The community detection problem involves making inferences about node labels in a graph based on observing the graph edges. Applications include recommendation systems, advertisement in social networks, and fraud detection. In practical scenarios, non-graphical information is almost always present in conjunction with graphical data. This seminar explores a new and exciting direction in community detection that investigates efficient ways to integrate grapahical and non-graphical data. We discuss the influence of non-graphical side information on community detection via analyzing the inference phase transition threshold. This threshold essentially expresses which problems are fundamentally solvable and which ones are not, thus having both theoretical significance as well as practical impact. For the two-community problem, the effect of partially revealed labels and noisy label side information is discussed. A more general side information with arbitrary alphabet consisting of k features is studied. Applications and implications of these results will be discussed.

Bio :

Aria Nosratinia is Erik Jonsson distinguished professor and associate head of the electrical engineering department at the University of Texas at Dallas. He received his Ph.D. in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign in 1996. He has held visiting appointments at Princeton University, Rice University, and UCLA.

His interests lie in information theory and signal processing, with application in wireless communications. Dr. Nosratinia is a fellow of IEEE for contributions to multimedia and wireless communications. He has served as editor and area editor for the IEEE Transactions on Wireless Communications, and as editor for the IEEE Transactions on Information Theory, IEEE Transactions on Image Processing,, IEEE Signal Processing Letters, IEEE Wireless Communications (Magazine), and Journal of Circuits, Systems, and Computers.

He has received the National Science Foundation career award, and the outstanding service award from the IEEE Signal Processing Society, Dallas Chapter. He has served in the organizing and technical program committees of a number of conferences, most recently as general co- chair of IEEE Information Theory Workshop 2018. Dr. Nosratinia was named a highly cited researcher by Clarivate Analytics (formerly Thomson Reuters).

A. Murat Tekalp

Koc University, Turkey

Title : Optimization of Video Services by Multi-Access Edge Computing

Abstract :

We are recently experiencing two major industry trends in transitioning from centralized to edge computing aided by SDN and NFV technologies. The first trend is cloud service providers are moving cloud computing out of central datacenters towards the network edge to provide their customers lower latency and higher bandwidth. The second trend is network service providers are upgrading their access network technologies to transition from closed and proprietary hardware to disaggregated and virtualized software running on white-box servers, switches, and access devices. This talk will address how current over-the-top (unmanaged) and emerging managed video services can benefit from these two trends. In particular, we will discuss new models for high-bandwidth streaming video services and low-delay real-time communication services as edge-managed value-added services from the network service provider perspective.

Bio :

Murat Tekalp received BS degrees in Electrical Engineering and Mathematics from Bogazici University in 1980 with high honors, and the M.S. and Ph.D. degrees in Electrical, Computer, and Systems Engineering from Rensselaer Polytechnic Institute (RPI), Troy, New York, in 1982 and 1984, respectively. He has been with Eastman Kodak Company, Rochester, New York, from December 1984 to June 1987, and with the University of Rochester, Rochester, New York, from July 1987 to June 2005, where he was promoted to Distinguished University Professor. Since June 2001, he is a Professor at Koc University, Istanbul, Turkey. He has been the Dean of Engineering at Koç University between 2010-2013. His research interests are in the area of digital image and video processing, including video compression and streaming, motion-compensated filtering, super-resolution, video segmentation, object tracking, content-based video analysis and summarization, 3D video processing, deep learning for image and video processing, video streaming and real-time video communications services, and software-defined networking.

Prof. Tekalp is a Fellow of IEEE and a member of Turkish Academy of Sciences and Academia Europaea. He was named as Distinguished Lecturer by IEEE Signal Processing Society in 1998. He received the TUBITAK Science Award in 2004 and Lifetime Achievement Award from IEEE Turkey Section in 2019.

He has chaired the IEEE Signal Processing Society Technical Committee on Image and Multidimensional Signal Processing (Jan. 1996 - Dec. 1997). He served as the Editor-in-Chief of Elsevier journal Signal Processing: Image Communication (2000-2010). He was an Associate Editor for the IEEE Trans. on Signal Processing (1990-1992), IEEE Trans. on Image Processing (1994-1996), and the Kluwer Journal Multidimensional Systems and Signal Processing (1994-2002). He was an area editor for the Academic Press Journal Graphical Models and Image Processing (1995-1998). He was also on the editorial board of the Academic Press Journal Visual Communication and Image Representation (1995-2002) and IEEE Signal Processing Magazine (2007-2010). He is currently in the IEEE Press Board (2018- ) and the Editorial Board of the Proceedings of the IEEE (2014-).

He is the founder and first Chairman of the Rochester Chapter of the IEEE Signal Processing Society. He was elected as the Chair of the Rochester Section of IEEE in 1994-1995. He was appointed as the Technical Program Chair for the 1991 IEEE Signal Processing Society Workshop on Image and Multidimensional Signal Processing, the Special Sessions Chair for the 1995 IEEE International Conference on Image Processing, the Technical Program Co-Chair for IEEE ICASSP 2000 in Istanbul, Turkey, the General Chair of IEEE International Conference on Image Processing (ICIP) at Rochester, NY in 2002, and Technical Program Co-Chair of EUSIPCO 2005 in Antalya, Turkey.

The new edition of his Prentice Hall book Digital Video Processing (1995) is published in June 2015. Dr. Tekalp participates in several European Framework projects, and he has served as a project evaluator for the European Commission and panel member for European Research Council.

Peter J. Tonellato

Director of the Center for Biomedical Informatics, Professor of Bioinformatics, School of Medicine, University of Missouri, Columbia MO, USA

Title : Artificial Intelligence in Precision Medicine

Abstract :

The era of Big Data is upon us. To address the biomedical and omic data onslaught, over the past 3 decades, the scientific and compuational community have progressively enhanced the use of sophisticated mathematical and statistical modeling, computer technology and computational analysis to seek ever more insightful information from the tsunami of data. However, the rapid development of ever more accurate digital probes and interrogation of life – at the clinical, laboratory, sample, and molecular levels has overwhelmed our ability to develop phenomenological much less physical principled based models of the mechanisms that produce the digitized signals. We have swept through three era’s of approaches to this problem: 80s-90’s – Mathematical modeling-data fitting-statistical analysis; 2000-10’s computational analysis performed on statistical and physical principled models; and post 2010’s-current data exploration and massive computational discovery.

We will focus attention on the current era, the production of the massive digitized data in a more-is-better manner; computational resources and infrastructure to manage and compute with; and the emerging approaches and methods to computationally interrogate and explore the data with the desire to discover results. Examples will be drawn from Electronic Medical Records; Next Generation Sequencing of ‘Omes; and applications to diseases such as breast cancer. We will assay the use of Artificial Intelligence, neural networks and deep learning to explore and discover. We present examples of the application of such approaches in precision medicine. We will also demonstrate the use of such approaches in liquid bioassays in breast cancer and in comprehensive cancer genetic tests recently approved by the FDA. We argue that these and parallel approaches will catalyze the value of the massive data sets, and the subsequent results will facilitate adoption and widespread implementation of precision medicine resulting in dramatically improved patient outcomes.

Bio :

Peter J. Tonellato, PhD is Founding Director, Center for Biomedical and Informatics Research, and Professor of Bioinformatics, School of Medicine, University of Missouri. He seeks to apply mathematic, statistic and bioinformatic methods to create platforms to translate, test and predict the value of actionable healthcare data and information - particularly genetic data, information and knowledge - in “Best Practice” Precision Medicine. Dr.Tonellato’s work includes the use of “Clinical Avatars”, digital representations of patients, in the modeling, simulation and prediction of genetic data’s impact on individual and characteristic patient outcome metrics. Professor Tonellato is constructing the Center for Biomedical Informatics to support self-sustaining, multidisciplinary collaborative research in cancer; cardiovascular and neuro-behavioral diseases.

Dr. Tonellato earned his PhD in applied mathematics from the University of Arizona following study at both the University of Oxford and Hiroshima University. Past positions include joint appointments with Harvard Medical School (Director, Laboratory for Personalized Medicine) in the Department of Biomedical Informatics and Professor of Bioinformatics the Zilber School of Public Health, University of Wisconsin, Milwaukee and Medical College of Wisconsin (founding Director, Bioinformatics Research Center). Dr. Tonellato was Founder and CEO, of Pointone Systems, LLC, the first personalized medicine software company that provided genetic enabled ‘best practice’ clinical decision support systems to hospitals and health care facilities. Previous work includes the creation of the Rat Genome Database (rgd.mcw.edu), the first disease-centric repository of phenotype and genetic data and the Program in Genomic Applications (pga.mcw.edu) a model organism of human disease phenotype-genotype platform designed to aid the animal model research community to create hypotheses through data mining a massive heterogeneous collection of phenotypes, genetic, and microarray expression data from the largest collection of rat and other model organism specialty bred species.

Jitendra K. Tugnait

Auburn University, USA

Title : Secure Communication under Active Eavesdropping/ Pilot Contamination Attack

Abstract :

In a time-division duplex multiple antenna system such as massive MIMO, the channel state information can be estimated using reverse training. A pilot contamination attack (also called active eavesdropping) occurs when during the training phase in the uplink, an adversary also sends synchronized, identical training (pilot) signal as that of the legitimate receiver. This contaminates channel estimation and alters the legitimate beamforming/precoder design at the base station, facilitating eavesdropping in the downlink.

In this talk I will discuss recent progress on issues related to secure communication under such attacks, including their impact on achievable secrecy rates, and approaches to detection and mitigation of such attacks.

Bio :

Jitendra K. Tugnait received the B.Sc.(Hons.) degree in electronics and electrical communication engineering from the Punjab Engineering College, Chandigarh, India in 1971, the M.S. and the E.E. degrees from Syracuse University, Syracuse, NY and the Ph.D. degree from the University of Illinois, Urbana-Champaign in 1973, 1974, and 1978, respectively, all in electrical engineering.

From 1978 to 1982 he was an Assistant Professor at the University of Iowa, Iowa City, IA, and was with the Long Range Research Division of the Exxon Production Research Company, Houston, TX, from June 1982 to Sept. 1989. He joined the Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, in September 1989 as a Professor, where he is now James B. Davis Professor. His current research interests are in statistical signal processing and wireless physical and secure communications.

He is a fellow of IEEE (class of 1994). He has served as Associate Editor of the IEEE Transactions on Automatic Control and IEEE Signal Processing letters, Editor of IEEE Transactions on Wireless Communications, Associate Editor and Senior Area Editor of the IEEE Transactions on Signal Processing, and Senior Editor of IEEE Wireless Communications letters.