Andrea M. Tonello – University of Klagenfurt, Austria
Antonio F. Skarmeta – University of Murcia, Spain
Tommaso Melodia – William Lincoln Smith Professor at Northeastern University, USA
Alessandro Bassi – EurescomGmbh, Germany, and IoTItaly, Italy
Thais Batista – Universidade Federal do Rio Grande do Norte, Brazil
Adrian M. Ionescu – École Polytechnique Federalede Lausanne (EPFL), Switzerland
ANDREA M. TONELLO – UNIVERSITY OF KLAGENFURT, AUSTRIA
Generative and Discriminative AI Models for Next Generation Networked Cyber-Physical Systems
Learning the statistics of physical phenomena has been a long-time research objective. The advent of machine learning methods has offered effective tools to tackle such an objective in several data science domains. Some of those tools can be used in the domain of cyber-physical systems, the Internet of Things (IoT), smart systems, and communication networks. A distinction has to be made between data learning and signal learning. The former paradigm applies to the higher (cyber) layer, while the latter to the physical layer. Historically, stochastic models derived from the laws of physics have been exploited to describe the physical layer. From these models, transmission technology needed to provide connectivity among nodes has been developed and performance analysis carried out. Nevertheless, this approach has shown some shortcomings in complex and uncertain environments. In this talk, we will present recent generative and discriminative AI models capable of firstly learning the hidden/implicit distribution and then generating synthetic signals. The application of such methods to classic but still open problems in communications will be illustrated, including a) synthetic channel and noise modeling, b) coding/decoding design in unknown channels, and c) channel capacity estimation. Further applications of these AI learning methods to networked cyber-physical systems will also be introduced.
Andrea M. Tonello is a professor of embedded communication systems at the University of Klagenfurt, Austria. He has been an associate professor at the University of Udine, Italy, technical manager at Bell Labs-Lucent Technologies, USA, and managing director of Bell Labs Italy where he was responsible for research activities on cellular technology. He co-founded the spin-off company WiTiKee and has a part-time associate professor post at the University of Udine, Italy. Dr. Tonello received a Ph.D. in electrical and telecommunication engineering from the University of Padova, Italy (2002). He was the recipient of several awards including the Lucent Bell Labs Recognition of Excellence Award (1999), the RAENG (UK) Distinguished Visiting Fellowship (2010), the IEEE Vehicular Technology Society Distinguished Lecturer Award (2011-15), the IEEE Communications Society (ComSoc) Distinguished Lecturer Award (2018-19), the IEEE ComSoc TC-PLC Interdisciplinary and Research Award (2019), the IEEE ComSoc TC-PLC Outstanding Service Award (2019), and the Chair of Excellence from UC3M (2019-20). He was also the co-recipient of 10 best paper awards. He was/is associate editor of IEEE TVT, IEEE TCOM, IEEE ACCESS, IET Smart Grid, and Elsevier Journal of Energy and Artificial Intelligence. He was also a guest co-editor for IEEE JSAC and IEEE Communication Magazine. He was the general chair of the IEEE Smart Grid Communications Conference (2014) and IEEE Int. Symposium on Power Line Communications (2011). He has been TPC co-chair or track co-chair in several IEEE conferences. Dr. Tonello was PI in national, EU projects and industry cooperation projects. He served as a project evaluator in international funding agencies. He was the chair of the IEEE ComSoc Technical Committee on PLC (2014-18), and the director for industry outreach in the IEEE ComSoc Board of Governors (2020-21). Currently, he serves as the chair of the IEEE ComSoc Technical Committee on Smart Grid Communications. He is also the coordinator of the project NEON about creating a network of competence on IoT in Latin America.
ANTONIO F. SKARMETA, UNIVERSITY OF MURCIA, SPAIN
IoT in the Era of the Continuum Computing: Challenges and Opportunities
The advent of 5G and the IoT open new possibilities for highly distributed processing capacities from IoT-Edge-Cloud in a continuum: New services require efficient and effective management of computing and network resources which means dealing with huge amounts of data and at different levels of the future network infrastructure. this distributed context implies the orchestration of resources over the continuum but also provides new security challenges to be considered. In this talk, we will travel along several EU projects and the different challenges and solutions they introduce.
Antonio Skarmeta received an M.S. degree in Computer Science from the University of Granada and a B.S. (Hons.) and a Ph.D. degree in Computer Science from the University of Murcia Spain. Since 2009 he has been a Full Professor at the same department and University. Antonio F. Skarmeta has worked on different research projects in the national and international areas in the networking, security, IoT, and 5G area. His main interest is in integrating 5G, security services, identity, IoT, and Smart Cities, being the scientific manager of the Smart City project of Murcia City Hall (MiMurcia). He has been the head of the research group ANTS since its creation in 1995. He is also an advisor to the vice-rector of Research at the University of Murcia for International projects and head of the International Research Project Office. From 2014 until 2010, he was Spanish National Representative for the MSCA within H2020. He has published over 200 international papers and is a member of several program committees.
TOMMASO MELODIA – WILLIAM LINCOLN SMITH PROFESSOR AT NORTHEASTERN UNIVERSITY, USA
Open 6G: Toward a Reference Architecture for Secure AI-Driven NextG Open RAN Systems
This talk will present an overview of our work laying the basic architectural and algorithmic principles for new approaches to designing open, programmable, AI-driven, and secure next-generation cellular networks. We will cover in detail the challenges and opportunities associated with evolving cellular systems into cloud-native softwarized architectures enabling fine-grained control of end-to-end functionalities. We will discuss architectural aspects, automation principles, and algorithmic frameworks enabling fine-grained end-to-end control of wireless systems from low-level RAN functionalities to orchestration and management. We will also explore several challenges to secure and enable softwarized large-scale systems that create an interface between the physical and digital worlds, including components like network slicing, spectrum sharing, security, and energy efficiency, and discuss the way forward.
Tommaso Melodia is the William Lincoln Smith Professor with the Department of Electrical and Computer Engineering at Northeastern University in Boston. He is also the Founding Director of the Institute for the Wireless Internet of Things and the Director of Research for the PAWR Project Office. He received his Laurea (integrated BS and MS) from the University of Rome - La Sapienza and his Ph.D. in Electrical and Computer Engineering from the Georgia Institute of Technology in 2007. He is an IEEE Fellow and recipient of the National Science Foundation CAREER award and several best paper awards, including at IEEE Infocom 2022. Prof. Melodia, the Editor in Chief for Computer Networks, was a co-founder of the 6G Symposium, the Technical Program Committee Chair for IEEE Infocom, and General Chair for ACM MobiHoc, among others. Many US government and industry entities have funded Prof. Melodia’s research on modeling, optimization, and experimental evaluation of wireless networked systems.
ALESSANDRO BASSI – EURESCOM GMBH, GERMANY, AND IOTITALY, ITALY
IoT, a Retrospective on the Past Expectations Towards a Sustainable Roadmap
While the Internet of Things has become mainstream in the past few years, the initial concept is more than 20 years old, and the first serious scientific attempts to understand the potential of these technologies date around 15 years ago. In this talk, we will look at the roadmaps back then, and in particular, the seminal work done in Europe with the workshop “Beyond RFID - The Internet of Things” and the Expert Group for the European Commission. We will analyze the delta between what was expected and today’s reality, the challenges that have been solved and the ones still to solve, and try to understand what can happen within a 15-20 years range.
Alessandro Bassi graduated in Computer Science from the University of Milan in 1994, majoring in AI and software engineering. He worked for large corporations (Amadeus, Hitachi, Ricoh), for Universities (University of Tennessee, Ecole NormaleSuperieure), for NGOs (RIPE NCC), for SMEs and startups (THINGS, revolt Bi, Vertical Agritech), on both Research and Development / Operations side. Currently, he is a program manager for Eurescom GmbH. He is the president of IoTItaly, the Italian Association for the Internet of Things, and was an expert for ENISA, the European Network, and Information Security Agency, on possible threats from adopting IoT technologies. He was part of the group that wrote the Strategic Research Agenda on Future Internet. He has been involved in (and often coordinating) several EU research projects, including the lighthouse project regarding the Internet of Things, “Internet of Things – Architecture” (IoT-A).
THAIS BATISTA – UNIVERSIDADE FEDERAL DO RIO GRANDE DO NORTE, BRAZIL
Challenges and Directions to Break Silos in Smart Cities Applications Development
The Smart City idea has emerged as a response to the challenges that cities have faced with the huge population growth and rapid urbanization. It relies on Information and Communication Technologies (ICTs) to provide systems that improve city services to deliver citizens a better quality of life. However, smart city initiatives are commonly designed and implemented as isolated strategies, forming information silos that are unaware of each other. The lack of integration reduces the potential of achieving the purpose of smart cities, which demands synergic cooperation among multiple systems. This talk initially discusses challenges to breaking silos in smart cities applications development. Following, it gives an overview of how a smart city application development platform can provide effective ways to foster cross-silos interaction and seamless integration. Finally, it provides insights into future directions for researchers in this field.
Thais Batista is a full professor at the Federal University of Rio Grande do Norte, Natal, Brazil. She holds MSc (1994) and Ph.D. (2000) degrees in Computer Science from the Catholic University of Rio de Janeiro, Brazil. She was also a visiting researcher (2003-2004) and a senior fellow (2013-2014) at Lancaster University, United Kingdom. She is currently a Level 1C research fellow of the Brazilian National Council for Scientific and Technological Development. She has also served on the Program Committees of several Brazilian and international conferences and workshops on software architecture, computer networks, distributed systems, and software engineering-related topics. She published three books and more than 200 papers, besides being the supervisor of 35 MSc students and 15 Ph.D. theses. Her main research interests are distributed systems and software engineering, specifically the Internet of Things, Cloud Computing, middleware, smart cities, and software architecture.
ADRIAN M. IONESCU – ÉCOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL), SWITZERLAND
Towards an Energy Efficient Spiking Internet of Things
Edge Artificial Intelligence (AI) and Internet of Things (IoT) deployment imposes high expectations for energy-efficient sensing and computing in autonomous systems with various form factors. To satisfy the requirements of many emerging applications at the Edge, various electronic devices based on new physical principles and novel architectures are considered, aiming to improve information processing performance and go beyond traditional principles and system architectures. Inspired by nature, future task- or event-driven IoT nodes could feature end-to-end all spiking architectures, benefiting from new materials, devices, and spiking neural networks (SNNs).
In the first part of the talk, we will report on recent advances in stochastic memristive devices based on reversible metal-insulator-transition (MIT) materials such as vanadium dioxide. We will report multi-modal low-power spiking sensing devices capable of serving as power detectors from GHz to THz and as super-sensitive optical and temperature sensors. Finally, such spiking sensors can be designed and implemented on advanced CMOS platforms, with the spiking MIT devices 3D integrated into the BEOL or on top of standard chips.
In the second part of the talk, we will propose a platform that enables the co-integration of logic and neuromorphic units, as a promising approach. In this context, enhanced functionalities of field effect devices by material innovations are key to creating a multi-functional hardware platform. Due to the excellent electrostatic control and free dangling bond properties, two-dimensional (2D) material could be used to fabricate versatile heterostructure and scaled devices with reconfigurable circuit elements. 2D/2D material system offers the potential to demonstrate tunneling field-effect transistor (TFET)s with alternative carrier-injection mechanism for achieving a sub-60 mV/dec subthreshold slope (SS) and reducing power consumption. Negative capacitance (NC) of ferroelectric (FE) materials can effectively boost the performance of FET and tunnel FET transistors by offering a step-up voltage transformer. Moreover, the strong proximal coupling of FE materials with 2D materials allows the realization of 2D material-basedFeFETs for constructing synaptic devices with low power consumption, fast operation, and good data retention. We will explore the benefits and the performance of such designs, exploiting the co-integrated von Neumann 2D steep slope switches and neuromorphic synaptic devices. Moreover, we will show that the proposed ferroelectric material system can co-integrate supercapacitors for on-chip energy storage on the same technological ferroelectric/2D platform.
Adrian M. Ionescu is a Full Professor at Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland. He is the director of the Nanoelectronic Devices Laboratory of EPFL, Switzerland. His group pioneered steep slope devices, phage change devices, sensors, and MEMS resonators for energy-efficient Edge AI applications. He published more than 600 articles in scientific journals and conferences. He is the recipient of the IEEE Cledo Brunetti Award 2024, IBM Faculty Award 2013, and André Blondel Medal 2009. In 2015 he was elected a member of the Swiss Academy of Technical Sciences. He received an ERC Advanced Grant in 2016 and the EDL IEEE George Smith Award in 2017. He is an IEEE Fellow, served as Editor of IEEE TED, and is a member of the PUB committee of EDS. He is currently a member of the Editorial Board of Proceedings of IEEE.