Keynote Speaker I:

Prof. Dapeng Oliver Wu---IEEE Fellow

City University of Hong Kong, Hong Kong, China

Biography: Dapeng Oliver Wu received Ph.D. in Electrical and Computer Engineering from Carnegie Mellon University, Pittsburgh, PA, in 2003. Currently, he is Yeung Kin Man Chair Professor of Network Science, at the Department of Computer Science, City University of Hong Kong. His research interests are in the areas of artificial intelligence, FinTech, communications, image processing, computer vision, signal processing, and biomedical engineering.
He received University of Florida Term Professorship Award in 2017, University of Florida Research Foundation Professorship Award in 2009, AFOSR Young Investigator Program (YIP) Award in 2009, ONR Young Investigator Program (YIP) Award in 2008, NSF CAREER award in 2007, the IEEE Circuits and Systems for Video Technology (CSVT) Transactions Best Paper Award for Year 2001, the Best Paper Award in GLOBECOM 2011, and the Best Paper Award in QShine 2006. He has served as Editor-in-Chief of IEEE Transactions on Network Science and Engineering, and Associate Editor of IEEE Transactions on Communications, IEEE Transactions on Signal and Information Processing over Networks, and IEEE Signal Processing Magazine. He was the founding Editor-in-Chief of Journal of Advances in Multimedia between 2006 and 2008, and an Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Wireless Communications and IEEE Transactions on Vehicular Technology. He has served as Technical Program Committee (TPC) Chair for IEEE INFOCOM 2012. He was elected as a Distinguished Lecturer by IEEE Vehicular Technology Society in 2016. He is an IEEE Fellow.

Title: Explainable Question Answering

Abstract: Question answering (QA) is a computer science discipline within the fields of information retrieval and natural language processing (NLP), which is concerned with building systems that automatically answer questions posed by humans in a natural language. Most QA systems provide answers without justification; this is particularly true for deep-learning-based QA systems, which take a black-box approach. In this talk, I will present a QA system that can provide justification, in addition to an answer to a question. We focus on common-sense questions. Our approach is based on knowledge graphs.

Keynote Speaker II:

Prof. Ponnuthurai Nagaratnam Suganthan---IEEE Fellow

Nanyang Technological University, Singapore

Biography: Ponnuthurai Nagaratnam Suganthan finished schooling at Union College (Tellippalai, Jaffna) and subsequently received the B.A degree, Postgraduate Certificate and M.A degree in Electrical and Information Engineering from the University of Cambridge, UK in 1990, 1992 and 1994, respectively. He received an honorary doctorate (i.e. Doctor Honoris Causa) in 2020 from University of Maribor, Slovenia. After completing his PhD research in 1995, he served as a pre-doctoral Research Assistant in the Dept. of Electrical Engineering, University of Sydney in 1995–96 and a lecturer in the Dept. of Computer Science and Electrical Engineering, University of Queensland in 1996–99. He was an Editorial Board Member of the Evolutionary Computation Journal, MIT Press (2013-2018) and an associate editor of the IEEE Trans on Cybernetics (2012 - 2018) and IEEE Trans on Evolutionary Computation (2005 -2021). He is an associate editor of Applied Soft Computing (Elsevier, 2018- ), Neurocomputing (Elsevier, 2018- ), Information Sciences (Elsevier, 2009 - ), Pattern Recognition (Elsevier, 2001 - ), Engineering Applications of Artificial Intelligence (2022-) and IEEE Trans. on SMC: Systems (2020 - ). He is a founding co-editor-in-chief of Swarm and Evolutionary Computation (2010 - ), an SCI Indexed Elsevier Journal. His co-authored SaDE paper (published in April 2009) won the "IEEE Trans. on Evolutionary Computation outstanding paper award" in 2012. His former PhD student, Dr Jane Jing Liang, won the IEEE CIS Outstanding PhD dissertation award, in 2014. IEEE CIS Singapore Chapter won the best chapter award in Singapore in 2014 for its achievements in 2013 under his leadership. His research interests include swarm and evolutionary algorithms, pattern recognition, forecasting, randomized neural networks, deep learning and applications of swarm, evolutionary & machine learning algorithms. His publications have been well cited (Googlescholar Citations: ~56k). He was selected as one of the highly cited researchers by Thomson Reuters every year from 2015 to 2021 in computer science. He is ranked by Exaly.com. He served as the General Chair of the IEEE SSCI 2013. He is an IEEE CIS distinguished lecturer (DLP) in 2018-2021. He has been a member of the IEEE (S'91, M'92, SM'00, Fellow’15) since 1991 and an elected AdCom member of the IEEE Computational Intelligence Society (CIS) in 2014-2016.

Title: Randomization Based Deep and Shallow Learning Methods for Classification and Forecasting

Abstract: This talk will first introduce the main randomization-based feedforward learning paradigms with closed-form solutions. The popular instantiation of the feedforward neural networks is called random vector functional link neural network (RVFL). Other feedforward methods included in the tutorials are random weight neural networks (RWNN), extreme learning machines (ELM), Stochastic Configuration Networks (SCN), Broad Learning Systems (BLS), etc. We will also present deep random vector functional link implementations. Hyperparameter tuning will be addressed in detail. The talk will also present extensive benchmarking studies using classification and forecasting datasets.

Keynote Speaker III:

Prof. Shuanghua Yang

Southern University of Science and Technology, China

Biography: Shuang-Hua Yang received the B.S. degree in instrument and automation and the M.S. degree in process control from the China University of Petroleum (Huadong), Beijing, China, in 1983 and 1986, respectively, and the Ph.D. degree in intelligent systems from Zhejiang University, Hangzhou, China, in 1991. He is currently the Head of Department of Computer Science at University of Reading, UK, and the director of Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet at Southern University of Science and Technology, China. His research interests include cyber-physical systems, the Internet of Things, wireless network-based monitoring and control, and safety-critical systems. He is a senior member of IEEE and a fellow of IET and InstMC, U.K. He is also an Associate Editor of IET Cyber-Physical Systems: Theory and Applications.

Title: UAV-Enabled Wireless Communications Considering Energy Limitations

Abstract: Unmanned aerial vehicles (UAVs) have been providing promising solutions for future wireless networks. Due to their advantages of flexibility, mobility, rapid deployment and high adaptability, UAVs have been widely studied by researchers from a range of areas in both academia and industry. In general, typical examples include, but not limited to, search and rescue (SAR), wireless coverage, mobile relay, aerial base station (BS), remote sensing and monitoring, emergency response, smart agriculture and delivery of goods, etc. There have been many excellent works in this area, provided that the UAV has sufficient energy as guarantee, which is unrealistic in practice. In this talk, we will focus on UAV-enabled wireless communications considering UAV energy limitations, including UAV charging and manoeuvre energy consumptions. Furthermore, we will present the research on battery weight and UAV flight performance, and recent advance of UAV energy consumption models. We will conclude the talk by discussing potential research directions and new challenges.

Keynote Speaker IV:

Prof. Patrick Wang

Fellow of IAPR, ISIBM and WASE

Northeastern University, USA

Biography: Prof. Wang is Fellow of IAPR, ISIBM and WASE, IEEE Outstanding Achievement Awardee,Tenured Full Professor, Northeastern University, USA, iCORE (Informatics Circle of Research Excellence).,Visiting Professor, University of Calgary, Canada.,Otto- Von-Guericke Distinguished Guest Professor, Magdeburg University, Germany,Zijiang Visiting Chair, ECNU, Shanghai, China.,NSC Visiting Chair Professor, NTUST, Taipei, Taiwan,Honorary advisory professor of several key universities in China, including Sichuan University, Xiamen University, East China Normal University, Shanghai, and Guangxi Normal University, Guilin. Prof. Wang received his BSEE from National Chiao Tung University (Jiaotong University), MSEE from National Taiwan University, MSICS from Georgia Institute of Technology, and PhD, Computer Science from Oregon State University.,Published over 26 books, 160 technical papers, 3 USA/European Patents, in PR, AI, TV, Cybernetics and Imaging,Founding Editor-in-Chief of IJPRAI (International Journal of Pattern Recognition and Artificial Intelligence), and Book Series of MPAI, WSP.,Co-Chief Editor, IJPRAI and MPAI Book Series, WSP Northeastern University, Boston, MA, USA.,In addition to his technical interests, Dr. Wang also published a prose book, “Harvard Meditation Melody” and many articles and poems regarding Du Fu and Li Bai's poems, Beethoven, Brahms, Mozart and Tchaikovsky's symphonies, and Bizet, Verdi, Puccini and Rossini's operas., http://www.worldscibooks.com/series/smpai_series.shtm; http://www.isibm.org/leadership.php; http://www.dcs.warwick.ac.uk/~ctli/IJDCF.htmlUH(Based on document published on 6 April 2015).

Keynote Speaker V:

Assoc. Prof. Yiwen Wang

Hong Kong University of Science and Technology, Hong Kong, China

Biography: Yiwen Wang received B.S. and M.S. degrees from University of Science and Technology of China (USTC), Hefei, Anhui, China in 2001 and 2004 respectively. She received a Ph.D. degree from University of Florida, Gainesville, FL, USA in 2008. She then joined the Department of Electronics and Computer Engineering as a Research Associate at the Hong Kong University of Science and Technology, Kowloon, Hong Kong. In 2010, she joined as an Associate Professor at Zhejiang University, Hangzhou, China. In 2017, she joined the faculty at the Department of Electronic and Computer Engineering, Department of Chemical and Biological Engineering, the Hong Kong University of Science and Technology. In 2022, she was promoted to Associate Professor with substantiation.
Her research interests are in neural decoding of brain-machine interfaces, adaptive signal processing, computational neuroscience, neuromorphic engineering. She serves as the chair of IEEE BRAIN publication subcommittee, the Chair in the IEEE EMBS Neural Engineering Tech Committee, the Board Member of Brain Computer Interfaces Society. She is the Editor-in-Chief of IEEE Brain Newsletter, she serves in the editorial board of the Journal of Neural Engineering, and is the associate editor of Frontiers in Human Neuroscience (Brain-Computer Interfaces), an associate editor of the IEEE Transactions on Cognitive and Developmental Engineering. She was an associate editor of the IEEE Transactions on Neural Systems and Rehabilitation Engineering. She was recognized as IEEE EMBS distinguished lecturer in 2022. She holds one US patent and has authored more than 100 peer-reviewed publications.

Title: Autonomous task learning for Motor Brain Machine Interfaces

Abstract: A fundamental aspect of biological behavior is the ability to learn and to adapt to the environment. The brain has developed remarkable mechanisms to achieve this ability. As part of the overall effort to permit the brain to control neuroprosthetic devices via brain-machine interfaces (BMI), it is critical to model and or recreate such adaptive mechanisms. Previous experiments have demonstrated the feasibility of brain control on neuroprosthesis without actual limb action, where subjects need to adjust brain activity to learn the operation on a BMI system based on visual feedback. However, current systems are still far from being ready for routine clinical use due to the limits of the actions, extensive training, frequent recalibration, and no generalization over new tasks. The ideal BMI is supposed to accomplish complex movement tasks with fast training, high accuracy, and stability over time. More importantly, we expected BMIs to have the smart learning ability to adapt and develop new movements autonomously.
We develop a series of kernel reinforcement learning (KRL) methods implemented in Reproducing Kernel Hilbert Space (RKHS) to enable continuous adaptation and autonomous learning for motor BMI. RL based decoders enable the user to learn the prosthesis control through interactions without actual limb movement, and better represents the subject's goal to complete the task. KRL enables mBMI to use knowledge learned previously on tasks performed in MC mode (e.g., normal control where the subject’s limb moves during reaching) to adapt efficiently to changes in neural activity, when the subject switches mode (e.g., pure brain control where the limb is anesthetized or paralyzed). We further extend KRL from merely providing BMIs with robust adaptation overtime on known tasks, to enabling them to learn new tasks, by using medial prefrontal cortex (mPFC) activity as an internal critic.
Our study sheds light on the essence of neuroplasticity and learning for neuroscience. It also opens the door to the design of an autonomous decoder that adapts to and executes high-level goals provided by subjects. The translational impact is to empower clinical BMI devices with learning, where the subject starts with simple training at the lab and learns how to execute complex movements through daily interactions.