Professor Yong Yue
BEng, PhD, CEng, FIET, FIMechE, FHEA
Professor at the Department of Computing, Director of the Virtual Engineering Centre (VEC), Xi'an Jiaotong-Liverpool University (XJTLU), China

Areas of Expertise: Virtual Reality, Computer Vision, Robot Applications, Operations Research

Speech Title: Intelligent Real-Time Path Planning for Unmanned Surface Vehicle

Abstract: Unmanned Surface Vehicles (USVs) play a key role in water environment monitoring. The backbone of USVs is intelligent path planning which is crucial for ensuring the safety, reliability and success of USVs amid challenges such as fluctuating currents and tides while detecting and avoiding obstacles. This talk will briefly introduce the USV, reviews contemporary techniques for path planning and present ongoing work on intelligent real-time path planning for the USV for water environment monitoring. The work covers a novel path-keeping algorithm based on artificial potential field (PK-APF), enhancing the USV ability to maintain its pre-set path under variable wind conditions; a novel riverbank following planner (RBFP) with point cloud data to realise autonomous navigation along riverbanks for surveying water environments; a self-supervised framework for autonomous USV docking without the need for traditional human labelling and camera calibration, leading to highly precise USV docking manoeuvres.

Brief Introduction: Yong Yue (BEng Northeastern China, PhD Heriot-Watt UK, CEng, FIET, FIMechE, FHEA) is currently a Professor and Director of the Virtual Engineering Centre (VEC). He was Head of Department of Computer Science and Software Engineering (2013-2019). Prior to joining XJTLU, he had held various positions in industry and academia in China and the UK, including Engineer, Project Manager, Professor, Director of Research and Head of Department.
Professor Yue has experience in learning and teaching, research and enterprise as well as management. He has led a variety of research and professional projects supported by major funding bodies and industry. He has also lead curriculum development at both undergraduate and postgraduate levels. His Research interests include computer vision, robotics, virtual reality and operations research. He has over 250 peer-reviewed publications and supervised 27 PhD students to successful completion.

Professor Zhiquan Liu
College of Cyber Security, Jinan University, Guangzhou, China

Areas of Expertise: Internet of Vehicles security, web security, data security, trust modeling, privacy computing, blockchain, artificial intelligence, etc.

Speech Title: Security, Trust, and Privacy in Vehicular Networks

Abstract: Vehicular networks, as an important application of Internet of things in the automotive industry, and as the core component of intelligent transportation system, can realize all-round network connection and efficient information interaction between vehicles and other nearby vehicles, road infrastructures, pedestrians, and network, etc., so as to provide various information services, improve driving safety and efficiency, and promote energy saving and emission reduction. Vehicular networks are regarded as a global innovation hotspot and an important commanding point of economic development, with huge industrial development potential and application market space. However, due to the large, open, highly dynamic, delay sensitive, and other characteristics, the security, trust, and privacy in vehicular networks face huge challenges. Thus, this talk will focus on highlighting the recent advances, challenges, and approaches for the security, trust, and privacy in vehicular networks.

Brief Introduction: Zhiquan Liu is a full professor with the College of Cyber Security, Jinan University. In recent years, Prof. Liu has published more than 80 SCI/EI papers on authoritative journals and conferences, such as IEEE JSAC, IEEE TIFS, IEEE TDSC, IEEE TMC, IEEE TKDE, IEEE TPAMI, IEEE TITS, IEEE IOTJ, IEEE TVT, IEEE TII, IEEE TCC, IEEE Network, Science China Information Sciences, Information Fusion, Information Sciences, IEEE ICWS, IEEE WCNC, ACISP, and Chinese Computer Journal (including more than 40 papers on CCF-A/JCR-1/TOP journals, 4 best papers on international conferences, and 2 most popular papers on international journals), and has applied for/been authorized more than 100 invention patents and PCT patents. Besides, Prof. Liu has served as the Chair, Program Committee Chair, Publication Chair, Publicity Chair, Finance Chair, Workshop Chair, or Program Committee Member for more than 20 international conferences. Meanwhile, Prof. Liu has served as the editor-in-chief of Advances in Transportation and Logistics, the associate editor of IEEE IOTJ, the academic editor of PLOS ONE, and the guest editors of two international journals, Security and Communication Networks and Electronics, and has served as the reviewers of more than 40 authoritative journals and conferences. His homepage is https://www.zqliu.com/.

Associate Professor Lei Chen
Shandong University, China

Areas of Expertise: Image processing, Computer vision, Deep learning, Artificial intelligence

Speech Title: Deep Learning for Spatio-temporal Action Localization

Abstract: With the increasing popularity of surveillance devices, there is a growing demand for intelligent action recognition. Spatio-temporal action localization has gradually become an important application of deep learning in computer vision. Compared with the usual sense of action recognition, spatio-temporal action localization task can anchor all kinds of behaviours and individuals from time and space. Traditional spatio-temporal action location algorithms have the problem of insufficient fusion ability for spatio-temporal feature extraction and incomplete application of information at various levels. How to extract spatio-temporal action features more efficiently for detection under the condition of ensuring real-time inference speed, the solution of these problems will greatly promote the development and application of spatio-temporal behavioural localization algorithms. To address the problem, we design a multidimensional path aggregation network for spatio-temporal action location, which aggregates the features of multiple paths and fuses the corresponding hierarchical features to obtain spatio-temporal behavioural features. The experimental results demonstrate better performance compared with other algorithms.

Brief Introduction: Lei Chen received the B.Sc. and M.Sc. degrees in electrical engineering from Shandong University, Jinan, China, and the Ph.D. degree in electrical and computer engineering from University of Ottawa, Ontario, Canada. He is currently an Associate Professor with the School of Information Science and Engineering, Shandong University, China. His research interests include image processing and computer vision, visual quality assessment and pattern recognition, machine learning and artificial intelligence. He was the principal investigator of projects granted from the National Natural Science Foundation of China, National Natural Science Foundation of Shandong Province, China Postdoctoral Science Foundation, etc. He has published more than 40 papers on top international journals and conferences in recent years including IEEE TIP, Signal Process., ICME, etc. He was awarded the Future Plan for Young Scholars of Shandong University. He served for many international conferences including the ICIGP 2021, CSAI2022, MLCCIM2022, and ICIVC 2023 as Program Chair, Technical Chair or Publicity Chair.

Professor Rajanikanth Aluvalu
SMIEEE | Member-ACM | Member -Mirlabs | Life member ISTE | Member EAI
Department of IT, Chaitanya Bharathi Institute of Technology, India

Areas of Expertise: High Performance Computing, Bigdata and AI

Speech Title: Private AI opportunities and Challenges

Abstract: Private AI helps organizations realize value from their generative AI/AI initiatives faster while maintaining the privacy and control organizations expect for their sensitive data, whether it resides in a data center, public cloud, or at the edge. Data privacy is a strong consideration in all technology decisions—we can’t lose sight of that fact in the rush to gain productivity benefits from AI. Organizations still need to follow compliance regulations. Artificial Intelligence (AI), the privacy risks are many. AI can improve our lives, but may leak or misuse our private data. private AI can help to build trust and confidence in AI systems, users can have greater transparency and accountability in how their data is used and processed.

Prof. Yousef FARHAOUI
Moulay Ismail University, Faculty of sciences and Techniques, Morocco

Areas of Expertise: Artificial intelligence, Design and analysis of algorithms, High-Performance Computing, Human-Computer Interaction…

Brief Introduction: Chair of IDMS Team, Director of STI laboratory. Local Publishing and Research Coordinator, Cambridge International Academics in United Kingdom. He obtained his Ph.D. degree in Computer Security from Ibn Zohr University of Science. His research interests include learning, e-learning, computer security, big data analytics, and business intelligence. Farhaoui has three books in computer science. He is a coordinator and member of the organizing committee and also a member of the scientific committee of several international congresses, and is a member of various international associations. He has authored 6 Book and many Book Chapters with Reputed Publishers such as Springer and IGI. He is served as a Reviewer for IEEE, IET, Springer, Inderscience and Elsevier Journals. He is also the Guest Editor of many Journals with Wiley, Springer, Inderscience, etc. He has been the General Chair, Session Chair, and Panelist in Several Conferences. He is Senior Member of IEEE, IET, ACM and EAI Research Group.

Dr. Binqiang Wang
Inspur (Beijing) Electronic Information Industry Co. Ltd

Areas of Expertise: Spiking neural network; Emotion Recognition/Analysis

Speech Title: Innovative Pathways in Affective Computing: Multimodal Sentiment Analysis and Beyond

Abstract: Leveraging the advancements in artificial intelligence, the integration of emotion recognition paves the way for intelligent systems capable of empathy and nuanced interaction. Affective computing aims to equip computers with the skills to not only perceive and comprehend emotions but also to express them in a meaningful manner. In this presentation, we delve into the realm of multimodal sentiment analysis, examining the synergistic relationship between various modalities to amplify the efficacy and reliability of emotion recognition systems. We introduce a novel non-uniform attention mechanism that harnesses the collective power of multimodal features, ensuring a more refined and context-aware fusion of information. This mechanism is designed to recognize and weigh the contributions of different modalities, thereby enhancing the overall performance of emotion recognition tasks. Expanding beyond the spatiotemporal analysis, we present an innovative approach to emotion recognition through the frequency domain. By incorporating Fourier transform, our method fortifies traditional neural networks, facilitating a more nuanced understanding of emotional cues and consequently, improved recognition accuracy. Acknowledging the diversity and complexity of multimodal data, we introduce a new dataset specifically tailored for multimodal emotion recognition. This dataset, which captures emotional expressions through gestures, provides a more homogeneous perspective on the emotional tendencies exhibited in everyday life. Drawing inspiration from the fundamental human experience of emotion, we advocate for an emulation of brain structures to infer emotional states. With the high degree of biological fidelity offered by brain-inspired computing, we assert that a deeper simulation of brain processes is essential for unraveling the complexities of human emotions. Our research points towards a future where the intersection of artificial intelligence and affective computing leads to the development of systems with a deeper understanding of human emotions, fostering more empathetic and sophisticated interactions.

Brief Introduction: Dr. Binqiang Wang is a distinguished researcher with a Ph.D. in Signal and Information Processing from the University of Chinese Academy of Sciences. His academic journey began at Northwestern Polytechnical University, where he earned a Bachelor of Science in Computer Science and Technology. He has honed his expertise in deep learning, multi-modal information processing, and affective computing through extensive academic and industrial experiences. His research interests are at the forefront of technological innovation, with a particular emphasis on affective computing, emotion recognition and analysis, brain-inspired computing, and spiking neural networks. He currently holds the position of researcher with the title of Senior Engineer at Inspur (Beijing) Electronic Information Industry Co., Ltd. His academic prowess is reflected in his numerous accolades, including the Excellent Paper of Inspur Group in 2022, funding from the Shandong Provincial Natural Science in 2021, and the LiYuehua Zhu Scholarship in 2020. He leads a research group focused on information fusion algorithms for multi-modal emotion recognition in affective computing and brain-inspired computing. He has published 12 academic papers in renowned domestic and international journals, with 6 of them indexed by SCI and another 6 by EI. His work has garnered over 700 citations on Google Scholar, attesting to its influence and relevance. Additionally, He has applied for 9 patents, out of which 5 have been authorized as invention patents, highlighting his innovative and impactful research contributions.