KEYNOTE SPEAKERS

Title

Perceptual Quality in Online Real-Time Multimedia: An AI Approach

Abstract

With the rapid advancement of multimedia technologies, a wide array of interactive online games and real-time multimedia applications (RIMAs) has emerged. However, user-perceived quality in these applications often suffers due to network delays, resulting in sluggish or unresponsive interactions. This presentation introduces a general framework for optimizing the perceptual quality of diverse online, real-time, interactive multimedia applications. We propose a machine learning-based offline-online framework that enables practical implementation and runtime optimization. In the offline stage, the framework decomposes complex multi-metric, multi-control problems into simpler subproblems, each evaluating perceptual quality based on a single metric and control variable. During the online stage, these learned models are integrated into a composite model that identifies optimal operating points, effectively overcoming the exponential complexity of direct optimization. To validate our approach, we present two case studies: two-party and multiparty videoconferencing, and multiparty online action games. Experimental results demonstrate significant improvements in perceptual quality, highlighting the effectiveness and generality of our solution. The general approach can be applied to solve problems in psychophysics.

Biography

Benjamin W. Wah is Professor Emeritus at The Chinese University of Hong Kong (CUHK) and Franklin W. Woeltge Professor Emeritus of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign (UIUC). He previously served as Provost and Wei Lun Professor of Computer Science and Engineering at CUHK. He held joint appointments as the Franklin W. Woeltge Endowed Professor of Electrical and Computer Engineering and Professor at the Coordinated Science Laboratory at UIUC. Professor Wah received his Ph.D. in Computer Science from the University of California, Berkeley. His research spans nonlinear search and optimization, multimedia technologies, and artificial intelligence. He has received numerous prestigious awards for his contributions to research and professional service, including the IEEE Computer Society W. Wallace McDowell Award (2006), Richard E. Merwin Award (2007), Tsutomu Kanai Award (2009), the Distinguished Alumni Award in Computer Science from UC Berkeley (2011), and the Bronze Bauhinia Star from the Hong Kong SAR Government (2021). A pioneer in scholarly publishing, Professor Wah co-founded the IEEE Transactions on Knowledge and Data Engineering in 1988 and served as its Editor-in-Chief from 1993 to 1996. He is currently Co-Editor-in-Chief of Computers and Education: Artificial Intelligence and Honorary Editor-in-Chief of Knowledge and Information Systems. His leadership within the IEEE Computer Society includes serving as Vice President for Publications (1998–1999) and President (2001). Professor Wah is a Fellow of the AAAS and ACM, and a Life Fellow of the IEEE.

Title

Children, Virtual Agents, Robots, and Us: Rethinking User Acceptance of Social Technologies

Abstract

In this talk, I will present a series of experiments conducted by my research group to investigate the acceptance of interactive technologies such as virtual agents, robots, and chatbots. Our studies aim to uncover the features that foster user engagement and trust, while also highlighting differences in acceptance related to both age and gender. I will discuss results across adolescents, young adults, middle-aged adults, and older adults, before turning to our most recent findings on children—an age group that have been largely overlooked in current research. I will conclude with ethical reflections, focusing on the implications these technologies may have for users’ health and well-being, and on how design choices can support, rather than undermine, human flourishing.

Biography

Anna Esposito received her “Laurea” Degree summa cum laude from Salerno University of Salerno with a thesis on Neural Networks (published on Complex System, 6(6), 507-517, 1992).  She received the PhD degree in Applied Mathematics and Computer Science from Naples University “Federico II”, with a PhD thesis developed at MIT, RLE Lab (Boston, USA) on mathematical models of speech production (published on Phonetica, 59(4), 197-231, 2002). Anna has been postdoc at the International Institute for Advanced Scientific Studies, and Assistant Professor at Dept of Physics, Salerno University, where she has taught Laboratory of Cybernetics, Neural Networks, and Speech Processing (1996-2000).  From Nov 2000 to Nov 2002 she holds a research professor position at Wright State University, Dept. of Computer Science and Engineering, OH, USA. Anna has been associate professor (from 2003 to 2019) and currently (from 2020 to date) is full professor in Artificial Intelligence, Cybernetics and Multimodal Communication at Università della Campania “L. Vanvitelli”. Her current teaching duties are on  Cognitive and Algorithmic Issues of Multimodal Communication,  Cognitive Economy, and Fundamentals of Artificial Intelligence and Neural Networks. She is the head of the Behaving Cognitive Systems laboratory (BeCogSys https://becogsys.com/becogsy). The lab participated to several H2020 (among those : a) Empathic, www.empathic-project.eu/ and b) Menhir, menhir-project.eu/ ),  Italian (among those: c) SIROBOTICS, d)  ANDROIDS, and SALICE), and Erasmus funded project (among those G-Guidance: https://g-guidance.eu/language/en/).   The currently running projects are the Italian PRIN PNRR IRRESPECTIVE and AI PATTERNS and the H2020 project CRYSTAL (https://becogsys.com/)

Anna is member of the European Science Foundations (ESF) and the EU networks EUCogntion, Chair of the IAPR Conferences & Meetings Committee, https://iapr.org/committees/conferences-and-meetings-committee, and President of SIREN (https://www.siren-neural-net.it/ ). She authored 350+ peer reviewed publications and edited/co-edited 35+ international books.

Title

Children, Virtual Agents, Robots, and Us: Rethinking User Acceptance of Social Technologies

Abstract

In this talk, I will present a series of experiments conducted by my research group to investigate the acceptance of interactive technologies such as virtual agents, robots, and chatbots. Our studies aim to uncover the features that foster user engagement and trust, while also highlighting differences in acceptance related to both age and gender. I will discuss results across adolescents, young adults, middle-aged adults, and older adults, before turning to our most recent findings on children—an age group that have been largely overlooked in current research. I will conclude with ethical reflections, focusing on the implications these technologies may have for users’ health and well-being, and on how design choices can support, rather than undermine, human flourishing.

Biography

Anna Esposito received her “Laurea” Degree summa cum laude from Salerno University of Salerno with a thesis on Neural Networks (published on Complex System, 6(6), 507-517, 1992).  She received the PhD degree in Applied Mathematics and Computer Science from Naples University “Federico II”, with a PhD thesis developed at MIT, RLE Lab (Boston, USA) on mathematical models of speech production (published on Phonetica, 59(4), 197-231, 2002). Anna has been postdoc at the International Institute for Advanced Scientific Studies, and Assistant Professor at Dept of Physics, Salerno University, where she has taught Laboratory of Cybernetics, Neural Networks, and Speech Processing (1996-2000).  From Nov 2000 to Nov 2002 she holds a research professor position at Wright State University, Dept. of Computer Science and Engineering, OH, USA. Anna has been associate professor (from 2003 to 2019) and currently (from 2020 to date) is full professor in Artificial Intelligence, Cybernetics and Multimodal Communication at Università della Campania “L. Vanvitelli”. Her current teaching duties are on  Cognitive and Algorithmic Issues of Multimodal Communication,  Cognitive Economy, and Fundamentals of Artificial Intelligence and Neural Networks. She is the head of the Behaving Cognitive Systems laboratory (BeCogSys https://becogsys.com/becogsy). The lab participated to several H2020 (among those : a) Empathic, www.empathic-project.eu/ and b) Menhir, menhir-project.eu/ ),  Italian (among those: c) SIROBOTICS, d)  ANDROIDS, and SALICE), and Erasmus funded project (among those G-Guidance: https://g-guidance.eu/language/en/).   The currently running projects are the Italian PRIN PNRR IRRESPECTIVE and AI PATTERNS and the H2020 project CRYSTAL (https://becogsys.com/)

Anna is member of the European Science Foundations (ESF) and the EU networks EUCogntion, Chair of the IAPR Conferences & Meetings Committee, https://iapr.org/committees/conferences-and-meetings-committee, and President of SIREN (https://www.siren-neural-net.it/ ). She authored 350+ peer reviewed publications and edited/co-edited 35+ international books.

Title

Optimizing Continental-Scale Logistics: Network Design at Amazon

Abstract

We will talk about the outbound network of logistics operations of Amazon. Moving millions of customer orders and thousands of trucks weekly around the European continent, the Amazon European Middle-Mile Network is a very complicated infrastructure that relies on precise planning of resources to be able to offer to Amazon’s customer a high quality of service. Focusing on network design, we will first introduce two important optimization problems that are used to determine how the network is connected and how it can be optimized for timely deliveries to customers. These two problems need to be solved jointly, they have very large size, and represent a real technical challenge with a significant business impact. We will present the principles of our Amazon custom decision software, built by our research & technology team, which is used to address this complexity. During this discussion, we will focus on findings that were for me unexpected when I joined the company 6.5 years ago. We will also discuss how Generative Artificial Intelligence is used in this software.

Biography

Since Sep’22, Dr. Georgios Paschos holds the position of Director of Science at Amazon.com in Luxembourg, leading the Science & Technology team of EU Operations that focuses on improving the transportation and network planning. Dr. Paschos  joined Amazon in 2019 as a Snr Manager of Science, and built a research lab that comprises today 150 individuals, among which 60 scientists and 3 professors acting as research Scholars. At Amazon, Dr. Paschos has built with his team the truck scheduler, the network design decision software, and the capacity and forecasting software used today worldwide to optimally serve packages to customers. For the period Nov’14 – Jun ’19, he worked as a principal researcher at Huawei Technologies, Paris, France, leading the Network Control and Resource Allocation team and working on projects for Energy-efficient Artificial Intelligence, Software-Defined Networking, and Network Slicing. Previously, he worked two years at LIDS, MIT while before he held positions at CERTH– ITI, Greece ’08-’12 (researcher), University of Thessaly, Dept. ECE ’09-’11 (adjunct lecturer) and VTT, Finland, ‘07-‘08 (ERCIM Postdoc Fellow). He received his diploma in Electrical and Computer Engineering ’02 from Aristotle University of Thessaloniki, and his PhD degree in Wireless Networks ’06 from ECE dept. University of Patras, both in Greece. Two of his papers won the best paper award, in GLOBECOM 07’ and IFIP Wireless Days 09’ respectively. He has served as an associate editor for IEEE/ACM Trans. on Networking (’15-’19), IEEE Networking Letters (’18-’19), as a TPC member of INFOCOM, WiOPT, and Netsoft (’12-now). He has organized several international workshops on the topics of caching, network slicing and machine learning techniques for communication systems, while he was the co-organizer and editor of the IEEE JSAC Special Issue on Caching for Communication Systems and Networks

Title

Artificial Intelligence for Smarter Energy Management in Buildings and Cities

Abstract

The keynote will explore how Artificial Intelligence can transform energy systems by enabling smarter decision-making, greater efficiency, and deeper integration of renewables. It will highlight general insights, emerging applications, and broader societal impacts of AI in the energy and building sectors, offering perspectives that go beyond technical solutions to address challenges of sustainability and resilience. Selected case studies from the City of Athens and the Island of Crete will be highlighted.

Biography

Dr. Vangelis Marinakis is an Assistant Professor at the School of Electrical and Computer Engineering of the National Technical University of Athens (NTUA). His research focuses on the design and development of methodologies and decision support systems using leading-edge ICT technologies (Internet of Things, Artificial Intelligence, Big Data) for intelligent energy management at multiple levels (Smart Homes/Buildings, Smart Cities, Smart Districts). He also serves as President of DAEM, the IT and digital innovation company of the City of Athens.