Welcome to the Media Center, where you can find the latest original video content from ComSoc's conferences and events. Featuring keynotes speakers, executive forums, keynote workshops, industry panels, and much more from ComSoc's events, including the IEEE Global Communications Conference (GLOBECOM) and the IEEE International Conference on Communications (ICC). These videos bring insights to you when you need it. Your ComSoc membership offers free access to many of these valuable contents simply by logging in with your IEEE account.
IEEE and Non-Members can purchase videos after logging into their IEEE Account. If you do not have an IEEE account, click 'Create Account" to create a FREE account to make a purchase.
In the past decades, we have seen a drastic evolution of the communication networks, from the conventional homogenous computer networks to the advanced heterogonous networks. As the demands on the communication systems become more stringent, the problems faced by the communication engineers also become more complex, as well as the solutions to these problems. We have seen that there are more and more solutions based on artificial intelligence, machine learning, and deep learning in the systems. This is motivated by the great success of machine learning algorithms in supporting big data analytics, parameter estimation, and complex decision-making. This talk aims to give a brief overview of the current trends of deploying machine learning algorithms in solving problems and challenges in communication systems. This talk is divided into three parts. First, a general introduction of machine learning and deep learning is given. The second part focuses on using machine learning algorithms in solving various problems in future wireless communication networks. Last but not least, the third part discusses on using deep reinforcement learning and deep federated learning to support the operation and services of internet-of-thing (IoT).
Cyber systems, including the Internet of Things (IoT), are increasingly being used ubiquitously to vastly improve operational efficiencies and reduce costs in critical areas, such as finance, transportation, defense, and healthcare. Over the past two decades, dramatic improvements in computing efficiencies and hardware costs have made most of our today’s economy increasingly ever more digitized. It is important to note that such widespread use of devices for providing various services has resulted in the generation of large amounts of rich user data which needs to be protected. Emerging trends in successful targeted cyber system breaches have shown increasing sophistication, with most of them using intelligence generated through the collection and integration of publicly available data. Such sophisticated attacks can only be thwarted by defense mechanisms that rely on specific actionable intelligence. Although it is true that more data from diverse sources are available, such data may not automatically translate to actionable intelligence. In fact, translating large quantities of such diverse datasets into actionable intelligence is a nontrivial process. It involves identifying and integrating useful pieces of information from large quantities of noisy and biased datasets. In this talk, we will discuss some useful deep learning techniques and various challenges in generating actionable pieces of intelligence utilized for thwarting such sophisticated targeted attacks.
To facilitate smart applications such as intelligent manufacturing, energy-constrained devices are inter-connected through bandwidth-constrained communication protocols to form the Internet-of-things (IoT). Unfortunately, due to such constraints, the IoT networks fail to employ conventional security protocols, which makes them vulnerable to security threats. On the one hand, the IoT devices are vulnerable to illegal access and inference of sensitive information, while on the other, their users are prone to spoofing attacks through which an attacker can feed malicious data to the user. This makes it indispensable to enhance the robustness of IoT networks, specifically those utilized for security-sensitive applications. In this talk, I will discuss two specific networks: (1) Controller Area Network (CAN) which is a representative wired IoT network connecting different electronic control units within an automobile, and (2) Bluetooth Low Energy (BLE) network which is a representative wireless IoT network connecting wearables to the user’s smartphone. For both these networks, I will describe newly discovered vulnerabilities that can exploited by an attacker to launch an attack without getting detected by the deployed security mechanisms. I will conclude the talk by discussing the adopted methodologies to mitigate the discovered threat.
Since the first commercial launch in 2019, 5G has grown to be core infrastructure for a wide range of industries. It has been used to support everything from high-quality communication, to smart factories, to vehicle-to-vehicle communication and a whole raft of other new services. Learnings from past 5G deployments and how they are dealt with within 3GPP will be discussed. While 5G is currently being commercialized, industry and academia are beginning research to shape the next generation of communication, namely 6G. In this talk, I will introduce a comprehensive overview of various aspects of 6G, including technical and societal trends, services, requirements and candidate technologies. In the 6G era, the main users will be both machine as well as human, leading to many new forms of advanced services, such as truly immersive extended reality, high-fidelity mobile holograms and digital twins. These new services will require a tremendous amount of real-time data processing, hyper fast data rates, and extremely low latency. The key candidate technologies to enable this includes THz communication and advanced duplex systems.
In the past few years, thanks to the steady advances in technologies, we have witnessed the exploding growth of mobile data rates and number of connected devices that are supported by the existing communication networks. However, the always increasing millions of mobile apps and billions of sensors connected to the Internet of Everything (IoE) are bringing the current systems to their limit. With the deployment of 5G systems around the world and the 5G Advanced definition currently underway in standards bodies, work has recently started in defining the use cases and new enabling technologies that will shape 6G, i.e., the next generation of communication networks. 6G systems will provide unmatched high-quality, low-latency, high-reliability wireless services across humans and machines anytime and anywhere. These high expectations require innovations and advanced intelligence built into the next generation networks. With the advances in big data computing technology, AI already shows promising potentials in wireless industry, and we expect it will play an even more crucial role in 6G wireless networks in tasks that cannot be presented by a mathematical equation or with high computation complexity. In this Session, industry experts and renown research leaders, with experience in leveraging AI to solve real-world wireless communication problems, are invited to share their insightful thoughts and recent works to address the challenges ahead of us and discuss AI research directions toward future 6G wireless communication systems. AI at the Edge AI-enhanced orchestration for 6G networks within the vehicular & mobility vertical Can AI make 5G and 6G Better?
3GPP has named Release-18 as the starting point of 5G-Advanced, an intermediate step between current commercial 5G networks and future 6G networks. As such, it is expected that 5G-Advanced will introduce many technologies later being part of 6G. Some examples being mentioned as potential candidate for 5G-Advanced are AI/ML-based radio access and simultaneous transmission/reception on the same frequency (“full-duplex operation”). The content of 5G-Advanced is not yet decided upon although it is expected that 3GPP will have taken some decisions by the spring of 2022, making this panel a timely and highly relevant discussion for anyone interested in the evolution of 5G technologies towards 6G.
5G rollouts have stimulated new demand that cannot be met by 5G itself. That's where 5G-Advanced comes into play, delivering enhanced capabilities. Without a doubt, 5G-Advanced will further stimulate more new demands that only 6G can address. Looking into these new demands will be crucial to defining 6G. ITU-R is leading the consortium effort to study future technology trend (FTT) and 6G vision, aiming to issue the FTT report and vision recommendation by the end of 2022 and in the middle of 2023, respectively. 6G will go far beyond communications. 6G will serve as a distributed neural network that provides communication links to fuse the physical, cyber, and biological worlds, truly ushering in an era in which everything will be sensed, connected, and intelligent. In addition to connected people and things, we predict that 6G will be the platform for connected intelligence, where the mobile network connects vast amounts of intelligent devices and connects them intelligently. This talk will first start with 5G-advanced as an introduction, then present an overall vision for 6G with drivers, use cases, KPIs, roadmap and key capabilities. Six key capabilities: (1) Extreme connectivity, (2) Native AI, (3) Networked sensing, (4) Integrated Non-terrestrial network, (5) Native trustworthiness and (6) Sustainability, will be further discussed, including potential technologies/research directions and associated challenges.
Sitting at the intersection of wireless communication and ML, the talk will focus on two important aspects of wireless edge AI. First, we will discuss and demonstrate the application of ML in wireless communication for understanding, orchestrating, securing and maximizing the use of spectrum resources through learning. ML techniques can provide significant leaps in performance and efficiency of key L1 functions surrounding channel sensing, channel modeling, modulation and receiver design, and spatial re-use, as well as improving access and coordination schemes. We will explore how some of these ideas are advancing the 5G RAN today and how they can evolve to enable 6G.Second, we describe the role of Distributed Edge AI in the wireless environment. Owing to the distributed nature of data arising from sensors, base stations, and so forth, the goal in edge AI is to train privacy-preserving machine learning models under resource constraints. We provide an overview of recent techniques such as federated learning, distillation and split learning. We will also explore how to harness over-the-air computing and analog communication to provide scalable and privacy-preserving over-the-air model training. The talk will conclude by shedding light onto the next frontier of edge AI sitting at the confluence of semantic communication and ML.
This session will discuss the evolution of radio access network to open and virtualized cloud native RAN. It will focus on the RAN networks today for 5G, current ecosystem landscape, emerging trends in this space for 5G and beyond. It will also talk about the opportunities and challenges as well as how our network will become scalable specifically in the context of virtualization. The session with discussion some of evolving trends towards 6G and how cloud native technologies and ubiquitous computing will play a crucial role going forward. Why is this topic important: Analysts are getting more bullish on ORAN/vRAN – Dell ORO recently increased the ORAN/vRAN adoption from 10 to 14% by 2025. There are lot of innovations and investments being done in both hardware and software associated with ORAN/VRAN. Multiple partnerships/consortiums are being formed across the RAN ecosystem. The usage will also extend from Macro network to enterprise & IOT networks as well. What industry challenges are you addressing / solving? This will address dynamic scalability of a network and availability of multiple ecosystem options that will deliver TCO benefits for the end customer.
The use of MIMO and Massive MIMO is considered one the most disruptive and effective technologies introduced in recent years. For beyond 5G networks, the use of cell-free MIMO is being considered, which essentially means distributing the access points (AP) and doing the processing either locally or centrally. While many studies have considered spectral efficiency gains of various central or local processing methods, few publications consider the impact of the 5G architecture, and the NG-RAN, on the cell-free networking opportunities and challenges. The O-RAN alliance, initiated by some large operators and players in the telecom domain, aims to transform the radio access networks towards truly virtualized, distributed, and most importantly open systems. In an ideal world, multiple distributed O-RAN entities cooperate seamlessly to bring the best possible connectivity to each UE, cooperating through the O-RAN APIs. The key challenge that remains is how to merge cell-free networking, and distributed processing, with those existing network architectures. To exploit those distributed O-RAN entities optimally, and meet diverse requirements of future communication systems, beyond 5G intelligent networks will provide enhanced flexibility through the dynamic scheduling of the available resources. Given the densification of networks, and the introduction of cell-free architectures, the availability of radio access resources is unseen, and is only limited by the potential of the resource allocation methods. A major challenge is how to achieve this within standard and open architectures, such as for instance the O-RAN ALLIANCE. We will give a brief overview of the main academic trends in cell-free communication and radio resource management. We then describe how they will be mapped to NG-RAN and O-RAN terminology and architectures, giving a clear insight in the remaining challenges and innovation needs.
3GPP is finalizing Release 17 and starting to work on the second phase of 5G, which is officially named as 5G Advanced. The goal of 5G Advanced is to extend the 5G framework to support more scenarios and use cases, in particular for IoTs and vertical applications. Communications for automation and intelligence in vertical domains come with demanding and diverse requirements with respect to latency, data rates, availability, reliability, and in some cases, high-accuracy positioning. The vertical industries that will reap the benefits of this new level of automation will range from railways, buildings, manufacturing, healthcare, smart cities, electrical power supply and special events. Integrated with AI, Big Data, IoT, and other key technologies, 5G Advanced will empower traditional industries one step further than 5G. The talk will demonstrate the latest status of 5G empowered vertical applications and provide insight on how 5G Advanced will digitalize and modernize traditional industries to raise the efficiency. AI, industrial IoT, ubiquitous networks, blockchains, edge computing and network slicing are the key technologies which will be elaborated in this talk. In the conclusion of this talk, evolving trends of 5G Advanced to better boost a smart society and better support verticals will also be outlined.
Lifted by the network automation mega-trend, a third wave of autonomous computing and networking technologies development rises across the ICT industry. Multiple initiatives from Standards Development Organizations (SDOs), large open source projects, preeminent industry actors and renowned academic research teams have been launched in recent years and continue to emerge. This phenomenon deserves careful consideration if one wants to avoid facing the same disillusion as previous attempts at making autonomous networks a reality. While the theoretical and applied research corpus has been extensively contributed, the real world and large-scale adoption of autonomous networks has been, in contrast, relatively limited and disappointing. Since autonomous networks continue to fascinate research and engineers as a technological area full of potential and promise, the goal of this panel is to make a reality check on where we stand on the level of maturity of autonomous networks technologies and what challenges should the industry collectively address to ensure that the promises are met.
Edge computing as an evolution of cloud computing brings application hosting from centralized data centers down to the network edge, closer to consumers and the data generated by applications. It is acknowledged as one of the key pillars for meeting the demanding 5G Key Performance Indicators, especially as far as low latency and bandwidth efficiency are concerned. Moreover edge computing also plays an essential role in the transformation of the telecommunications business, where telecommunications networks are turning into versatile service platforms for industry and other specific customer segments. ETSI ISG MEC is the home of technical standards for edge computing. The group has already published a set of specifications and reports to offer fully standardized solutions to support IoT applications in distributed cloud. The emphasis of this talk is the MEC features in support of IoT use cases and requirements, as well as the MEC integration with 5G system and the MEC expansion to edge federation.
Today's mobile phones are far from mere communication devices they were just fifteen years ago. Equipped with sophisticated sensors and advanced computing hardware, phones can be used to infer users' location, activity, social setting and more. As devices become increasingly intelligent, their capabilities evolve beyond inferring context to predicting it, and then reasoning and acting upon the predicted context. Information about users’ behaviour can also be gathered by means of wearables and IoT devices as well as by sensors embedded in the fabric of our cities. Inference is not only limited to physical context and activities, but in the recent years mobile phones have been increasingly used to infer users' emotional states. The applications of these techniques are several, from positive behavioural intervention to more natural and effective human-mobile device interaction. In this talk, I will discuss the work of my lab in the area of mobile sensing for modelling and predicting human behaviour for social good. I will also discuss our research directions in the broader area of modelling human behaviour and social systems, outlining the open challenges and opportunities.
Federated Learning (FL) and Multi-agent Reinforcement Learning (MARL) are two emerging machine learning paradigms for future intelligent wireless IoT and networked systems. FL is a data-driven supervised machine learning setting where the centralized location trains a learning model by using remote devices (e.g., sensors, user devices). On the other hand, the decentralized MARL schemes, which are based on interactions of the learning agents with the environment, present suitable frameworks to solve decision and control problems considering the heterogeneity of IoT systems. In this talk, I shall discuss example applications and also the challenges of employing FL and MARL methods in resource-constrained and unreliable wireless IoT systems and networks. I shall present an FL algorithm that is suitable for a resource-constrained wireless access network and also a MARL method for a practical wireless edge computing environment. To this end, I shall discuss several of the key open research issues.
The new generation of Internet of Things involves Internet of Mobile Things (IoMT) which lets increasingly moving objects make better operational decisions through pooling data and resources from other connected vehicles and devices. Due to the enormous research and commercial potential, a lot of companies and researchers are attracted to this area. This workshop aims to bring researchers working on Future IoMTs under one roof to discuss the implementation, applications, and possible standardization efforts. We expect that the authors can together bring about significant impacts within this domain and share their knowledge and experiences with members of the research community, commercial sector and wider audiences.