Speakers

Prof. Guangjie Han, IEEE Fellow, IET/IEE Fellow, AAIA Fellow

Hohai University, China

BIO: Guangjie Han is a professor, currently serving as the Dean of the School of IoT Engineering at Hohai University. He is an IEEE Fellow, IET/IEE Fellow, and AAIA Fellow. His main research interests include smart oceans, industrial IoT, artificial intelligence, networks, and security. In recent years, he has published more than 350 high-level SCI journal papers, including over 130 papers in the IEEE/ACM Trans. series, in international journals such as IEEE JSAC, IEEE TMC, IEEE TPDS, and IEEE TCC. His publications have been cited over 17200 times on Google Scholar, with an H-index of 68. He has authored three monographs and translated one book. He has led more than 30 provincial and ministerial-level research projects, including national key R&D programs and national natural science foundation key projects. He has been granted 130 national invention patents and 6 PCT international authorized patents. He has received numerous awards, including the second prize of the China Business Federation Science and Technology Award, the third prize of the Jiangsu Provincial Science and Technology Award, the second prize of the Liaoning Provincial Science and Technology Progress Award, and the Best Paper Award of the IEEE Systems Journal in 2020. For five consecutive years (2019-2023), he has been listed as one of the top 2% of scientists globally, as well as for the Chinese Highly Cited Researchers list for four consecutive years (2020-2023). Currently, he serves as an associate editor for more than ten international journals, including IEEE TII, IEEE TVT, IEEE TCCN, and IEEE Systems. He has been awarded the "333 High-level Talents in Jiangsu Province" (second level), the "Outstanding Contribution Young and Middle-aged Experts in Jiangsu Province," the "Minjiang Scholar Lecture Professor," and the "May 1st Labor Medal" of Changzhou City.

Title: Multi-Dimensional Dynamic Trust Management Mechanism in Underwater Acoustic Sensor Networks

Abstract: The underwater acoustic sensor network (UASN) is the core module to realize the "smart ocean". At present, the UASN has not yet fully played its role in the complex water environment. The fundamental reason lies in the lack of effective methods to ensure network security and reliable data transmission. This report mainly introduces the team's research work on the trust management mechanism of UASNs. The main research contents include: 1) Intrusion detection algorithm based on energy consumption prediction model; 2) Multi-dimensional trust calculation algorithm based on fuzzy theory; 3) Trust evaluation algorithm based on cloud theory; 4) Trust cloud migration mechanism based on AUV; 5) Trust update mechanism based on reinforcement learning; 6) Anomaly-resilient trust model based on isolation forest. The research results have important theoretical value and practical significance for exploring the security technology and application of UASNs.

Prof. Zhaolong Ning, IET Fellow, EAI Fellow

Chongqing University of Posts and Telecommunications, China

BIO: Dr. Zhaolong Ning, a professor and doctoral supervisor, earned his Ph.D. through a joint program between Northeastern University in China and Kyushu University in Japan, followed by postdoctoral research at the University of Hong Kong. His primary research interests include emergency IoT, intelligent edge computing, and future communication networks. He serves as the deputy director of the Engineering Research Center of Mobile Communication, Ministry of Education, a member of the Chongqing Municipal Education Commission, and a member of the university’s academic committee. In 2023, Dr. Ning was selected as a National Top Youth Talent. Since 2020, he has been consistently recognized as a Highly Cited Scientist by Clarivate. In 2022, he was listed among the top 100 recipientsoftheMost Influential Scholar Awardfor AI 2000 in the IoT field. In 2018, he was selected for the China Association for Science and Technology’s Youth Talent Support Program (one of 285 nationwide that year). Since 2020, he has been consecutively listed as a Highly Cited Chinese Researcher by Elsevier and among the top 2% of global scientists by Stanford University. He was also selected as a Chongqing Young Top Talent in 2020 and as a Hong Kong Scholar in 2018. Dr. Ning’s contributions to his field have garnered numerous accolades, including the First Prize for Innovation in Industry-University-Research Collaboration in China (2022, as the lead contributor), Chongqing’s Top Ten Young Scientists Award (2022), Chongqing’s May Fourth Youth Medal (2022), and the Special Prize of Gansu Province’s Natural Science Award (2023, the only recipient). He has also won the First Prize for Natural Science Academic Achievement in Liaoning Province twice (2019 and 2017, both as the lead contributor), the Best Land Transportation Paper Award from the IEEE Vehicular Technology Society (2020, the only recipient worldwide), the Best Paper Award from the IEEE Systems Society (2019), one of China’s 100 Most Internationally Influential Academic Papers (2018), and five best paper award from various international conferences. 

Title: Research on User Association and Trajectory Optimization for IRS-Assisted UAV Communications

Abstract: Due to the flexibility, low cost, and easy deployment characteristics of UAVs, they are widely utilized in wireless communication networks and can provide temporary communication services in areas with weak or congested network coverage. However, due to the complexity of the communication environment, there might be obstructions between UAVs and users. Intelligent Reflecting Surfaces (IRS), as one of the significant new technologies in future 6G, play a role in constructing virtual Line-of-Sight (LoS) paths, bringing a new network paradigm to future communications aimed at creating an intelligently controllable wireless communication environment. To fully leverage IRS resources in IRS-assisted UAV communication networks, this talk explores the application of multiple IRS-assisted UAV communication networks in suburban and urban scenarios.

Prof. Wei Dong

Zhejiang University, China

BIO: Wei Dong is a professor at the College of Computer Science and Technology, Zhejiang University. He is currently a distinguished member of the China Computer Society (CCF). He has published over 170 papers in renowned international conferences such as ACM MobiCom, MobiSys, UbiComp, USENIX NSDI, and IEEE INFOCOM, as well as in renowned international journals such as IEEE/ACM Trans on Networking and IEEE Trans on Mobile Computing. Among these, over 70 papers have been recognized with CCF A and IEEE/ACM Trans papers. He has been awarded the Best Paper Award/Best Video Presentation Award for three times at IEEE/ACM international conferences. He has been granted over 30 national patents. He has served as a member of the organizing committee and program committee for several internationally renowned academic conferences. In recent years, he has dedicated himself to the research of IoT software and protocols for cloud-edge-end integration. His research has been widely reported by mainstream technology media such as IEEE Spectrum and ACM TechNews, and has been deeply applied in leading companies such as Alibaba Cloud, Huawei, and Hikvision, achieving good economic and social benefits.

Title: LLM-empowered IoT: Technology and Vision

Abstract: This talk explores the convergence of AI and IoT to create smart IoT systems with human-like capabilities. It categorizes smart IoT into five levels, from basic control to autonomous decision-making, and highlights key technologies at each stage, such as intelligent voice interaction and edge AI models. This talk discusses the importance of large language models in IoT, from reducing data transmission to enhancing privacy protection, and the potential for code generation and multi-agent systems. This talk also introduces "ChatIoT," leveraging LLM to create executable actions for IoT devices. 

Prof. Yanquan Liu

Southern Connecticut State University, USA

BIO: Professor and Coordinator of the Information Management and Services Undergraduate Program in the Department of Information and Library Science. Dr. Liu graduated from Peking University with a BS in Library Science, St. John's College with a Master in Liberal Arts, and the University of Wisconsin-Madison with a Ph.D. in Information Studies. The Fulbright Scholar (https://fulbrightscholars.org/grantee/yan-quan-liu). The member of Sigma Xi, The Scientific Research Honor Society.

Title: Artificial Intelligence and Smart Knowledge Technologies, A focus on recommender systems for library serves

Abstract: Smart information technologies and artificial intelligence (AI) are poised to transform libraries' services. Personalized recommender systems can transform user access to information and tailor the knowledge services given by information professionals. Using machine learning algorithms to locate hidden riches in library materials and create suggestions, knowledge discoveries emerge through user engagement, learning process, and overall library service delivery.

Senior Engineer Shiling Zhang

State Grid Chongqing Electric Power Company Chongqing Electric Power Research Institute, China

BIO: Zhang Shiling, senior engineer, doctor of engineering. He has been engaged in scientific research and production of high voltage and insulation technology and physical and chemical detection technology for a long time. The development of UHV dry-type converter transformer bushing and SF6 gas insulated through wall bushing has been applied to the construction of UHV AC and DC projects in China. Presided over and completed the GIS fault detection sensing technology and system, won the excellent innovation achievement award of the international innovation and entrepreneurship Expo, and was awarded the title of excellent scientific and technological worker by Chongqing Institute of electrical engineering.

As the first author, he has published more than110 SCI/EI search papers in domestic and foreign journals and international academic conferences, 19 Chinese Core Journals of Peking University, won 9 provincial and ministerial awards such as the first prize of Chongqing scientific and technological progress and the special first prize of China Water Conservancy and power quality management Association, authorized 1 international invention patent, 20 national invention patents and utility models, 18 software copyrights, and more than 20 reports of international and domestic conferences, As the project leader, he presided over 2 provincial and ministerial projects at the basic frontier and 3 science and technology projects at the headquarters of State Grid Corporation of China.

Title: Research on digital twin model of outgoing-line device area of UHV converter transformer based on computer-aided 3D configuration and electro-thermal sensing technology

Abstract: Valve side bushing of the ultra-high voltage converter transformer operates in the multi-field coupling environment of electric field, temperature field, and mechanical stress field. There is uneven distribution of temperature and electric field inside the capacitor core. It is urgent to introduce nonlinear characteristics of insulation medium into electric thermal coupling mechanism of the valve side bushing and carry out optimization design. This article simulates complex electric field and temperature distribution of the valve side bushing under the excitation of DC and multiple harmonic components, establishes a heating model of valve side bushing capacitor core, and proposes valve  bushing electric-thermal coupling model considers nonlinear characteristics of capacitor core insulation material. Research has shown during normal operation, the bushing on the side of the ultra-high voltage valve bears harmonic components and DC components in addition to 50Hz power frequency component. After frequency component reaches 2500Hz, its waveform amplitude approaches zero. As temperature increases in range of [20,110]℃ and the frequency decreases in range of [10-1,106] Hz, the tangent value parameter of loss angle increases and there are multiple peaks and valleys. There is clear nonlinear relationship between the dielectric constant of the material and temperature and frequency. Nonlinear model of valve side bushing electric thermal coupling proposed in article forms an improved equal margin design method for the electric thermal coupling, achieving the maximum radial field strength of 5.85kV/mm, the axial field of 0.41kV/mm, and the partial discharge margin value of 1.29 for the casing core. The comparison between calculation and design shows that the axial field strength between the core plates of valve side sleeve is distributed, which verifies the rationality of the nonlinear model of the valve side sleeve electric thermal coupling. Simulated data in this article can provide theoretical support for the design and manufacturing of the ultra-high voltage valve side bushings, and has certain guiding value for ensuring the safe and reliable operation of ultra-high voltage direct current transmission projects.

Assistant Professor Fiseha B. Tesema

University of Nottingham Ningbo China, China

BIO: Fiseha B. Tesema, Ph.D, is an experienced lecturer, Machine/Deep learning, and computer vision engineer andresearcher passionate about solving real-world problems and developing novel algorithms and systems that enablemachines to see and understand the world around them. Proven ability to take complex problems and break theminto manageable parts, leading to rapid prototyping and successful product launches. He published several works ireputable journals and conferences. Furthermore, he is a licensed professional teacher with more than seven yearsof teaching experience in universities.

Title: Addressee Detection in Mixed Human–Human and Human–Robot Settings Using Facial and Audio Features: A Deep Learning Framework

Abstract: The goal of addressee detection (AD) is to answer the question, "Are you addressing me?" For robots to participate effectively in multiparty conversations, they must determine whether a user is addressing the robot or another human. As robots transition from factory floors to populated spaces, the need for human-like interactive skills becomes crucial. AD enables robots to interact smoothly with humans by accurately identifying when they are being addressed. Despite its significance, AD has not been extensively explored. Existing studies focus primarily on human-to-human or human-to-robot interactions within confined meeting room settings, relying on gaze and utterance data through statistical and rule-based approaches. These methods are often limited by specific settings and fail to fully exploit the rich audio-visual information available, nor do they effectively integrate short-term and long-term conversational cues. Moreover, there is a lack of comprehensive audiovisual spatiotemporal annotated datasets capturing mixed human-to-human and human-to-robot interactions to support the development of advanced AD approaches. In this work, we introduce a novel AD dataset, Extended MuMMER (E-MuMMER), recorded in mixed human-to-human and human-to-robot settings. E-MuMMER extends the existing MuMMER dataset by incorporating spatiotemporal annotations of spoken activity. Additionally, we propose a two-stream-based deep learning framework called ADNet, designed to predict the addressee using both long-term and short-term audiovisual features. ADNet includes audio and video stream encoders, an audiovisual cross-attention (CA) mechanism for intermodality interaction, bilinear fusion (BLF) to combine audio and visual modalities, and a self-attention (SA) approach to capture long-term speech activity. This framework pioneers the use of both facial and audio features through deep learning for AD. Our study not only introduces a new paradigm for AD research but also positions E-MuMMER as the first dataset to facilitate advanced AD studies, paving the way for more interactive and responsive robotic systems.

Prof. Richard Everson

University of Exeter, UK

BIO: Richard Everson is a Professor of Machine Learning at the University of Exeter, UK and a fellow of the Alan Turing Institute  His research interests are in machine learning and optimisation and the interaction between them: machine learning for optimisation and optimisation for machine learning.  His work finds applications in engineering design, healthcare and he is academic principal investigator for Project Bluebird, investigating the feasibility of using AI for air traffic control. 

Title: Project Bluebird: AI for Air Traffic Control

Abstract: Project Bluebird is an investigation into the feasibility of air traffic control (ATC) using AI agents. It has the potential to provide safe management of the increasing air traffic over UK and worldwide skies. In addition to ensuring safety, AI agents may be able to direct aircraft along more fuel-efficient routes, helping to reduce the environmental impact of air traffic. This talk will describe progress made towards these goals: the construction of a probabilistic digital twin of UK airspace; the development of agents capable of safe routing of aircraft in a sector of airspace; and methods needed to promote successful human-AI cooperation to ensure safe, explainable and trustworthy use of AI in safety-critical ATC systems. The talk will concentrate on an agent based on optimisation of safety and efficiency goals and will show some initial simulations of controlling real traffic.