Prof. Witold Pedrycz
University of Alberta, Edmonton, Canada
IEEE Fellow
Speech Title: A Unified Framework of Data and Knowledge Environment of Machine Learning
Abstract: Over the recent years, we have been witnessing truly remarkable progress in Machine Learning (ML) with highly visible accomplishments encountered, in particular, in natural language processing and computer vision impacting numerous areas of human endeavours. Driven inherently by the technologically advanced learning and architectural developments, ML constructs are highly impactful coming with far reaching consequences; just to mention autonomous vehicles, control, health care imaging, decision-making in critical areas, among others.
Data are central and of paramount relevance to the design methodology and algorithms of ML. While they are behind successes of ML, there are also far-reaching challenges that require urgent attention especially with the growing importance of requirements of interpretability, transparency, credibility, stability, and explainability. As a new direction, data-knowledge ML concerns a prudent and orchestrated involvement of data and domain knowledge used holistically to realize learning mechanisms and support the formation of the models.
The objective of this talk is to identify the challenges and develop a unique and comprehensive setting of data-knowledge environment in the realization of the development of ML models. We review some existing directions including concepts arising under the name of physics informed ML. We investigate the representative topologies of ML models identifying data and knowledge functional modules and interactions among them. We also elaborate on the central role of information granularity in this area.
Short Bio: Witold Pedrycz (IEEE Life Fellow) is Professor in the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada. He is also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland. Dr. Pedrycz is a foreign member of the Polish Academy of Sciences and a Fellow of the Royal Society of Canada. He is a recipient of several awards including Norbert Wiener award from the IEEE Systems, Man, and Cybernetics Society, IEEE Canada Computer Engineering Medal, a Cajastur Prize for Soft Computing from the European Centre for Soft Computing, a Killam Prize, a Fuzzy Pioneer Award from the IEEE Computational Intelligence Society, and 2019 Meritorious Service Award from the IEEE Systems Man and Cybernetics Society.
His main research directions involve Computational Intelligence, Granular Computing, and Machine Learning, among others.
Professor Pedrycz serves as an Editor-in-Chief of Information Sciences, Editor-in-Chief of WIREs Data Mining and Knowledge Discovery (Wiley), and Co-editor-in-Chief of Int. J. of Granular Computing (Springer) and J. of Data Information and Management (Springer).

Prof. Zhongfei (Mark) Zhang
Binghamton University, State University of New York, USA
IEEE Fellow, IAPR Fellow, AAIA Fellow
Speech Title: On Reliability for Deep Learning
Abstract: One significant obstacle to deploying deep neural network (DNN) models in real-world applications is that deep learning systems often break down in novel situations. Specifically, DNNs tend to yield unreliable predictive uncertainty estimates and make high-confident yet incorrect predictions when exposed to inputs drawn from unfamiliar distributions. Consequently, accurate predictive uncertainty analysis of DNNs is critical in many high-stake applications such as medical diagnosis, self-driving vehicles, and financial decision-making, where silent mistakes can lead to catastrophic consequences. In this talk, I will first introduce the reliability issue through a novel uncertainty factorization model as a theoretical foundation in general. Based on this model, I will then introduce a general and flexible framework for predictive uncertainty estimation with promising evaluation results in several out-of-distribution detection tasks on both vision and language datasets.
Short Bio: Zhongfei (Mark) Zhang is a professor at Computer Science Department, Binghamton University, State University of New York (SUNY), USA. He received a B.S. in Electronics Engineering (with Honors), an M.S. in Information Sciences, both from Zhejiang University, China, and a PhD in Computer Science from the University of Massachusetts at Amherst, USA. His research interests are in the broad areas of machine learning, data mining, computer vision, and pattern recognition, and specifically focus on multimedia/multimodal data understanding and mining. He was on the faculty of Computer Science and Engineering at the University at Buffalo, SUNY, before he joined the faculty of Computer Science at Binghamton University, SUNY. He is the author or co-author of the very first monographs on multimedia data mining and on relational data clustering, respectively. He has published over 200 papers in the premier venues in his areas. He holds more than thirty inventions, has served as members of the organization committees of several premier international conferences in his areas including general co-chair and lead program chair, and as editorial board members for several international journals. He served as a French CNRS Chair Professor of Computer Science at the University of Lille 1 in France, a JSPS Fellow and visiting professorship in Chuo University, Japan, a QiuShi Chair Professor in Zhejiang University, China, as well as visiting professorships at many universities and research labs in the world when he was on leave from Binghamton University years ago. He received many honors including SUNY Chancellor’s Award for Scholarship and Creative Activities, SUNY Chancellor’s Promising Inventor Award, and best paper awards from several premier conferences in his areas. He is a Fellow of IEEE, IAPR, and AAIA.

Prof. Yang Yue
Xi'an Jiaotong University, China
SPIE Fellow, IEEE Senior Member and Optica Senior Member
Speech Title: Image Fusion and Object Detection with Pose and Surface Material Recognition Using a Time-of-Flight Camera
Abstract: In this work, a comprehensive framework for pose estimation, and surface material recognition using a time-of-flight (ToF) camera is presented. Our innovative approach combines depth and active infrared intensity images through a slide window weight fusion (SWWF) method, which fuses two modalities to localize targets. By constructing a joint feature space from the depth and intensity information, we employ four machine learning methods to achieve robust object recognition. We further leverage diffuse reflection principles and data fusion to focus on surface information, deriving factors that influence diffuse reflection on objects. The corresponding method processes the combined depth and active infrared intensity data using feature extraction and lightweight machine-learning techniques, introducing an optimization method to enhance the fitting of intensity. To validate our approach, experiments are performed on an in-house dataset containing 1066 images categorized into six different surface materials. Our method demonstrates strong localization performance with a 0.778 intersection over union (IoU) and achieves a 98.01% total accuracy in classification using K-Nearest Neighbor (KNN). Additionally, the proposed framework is less affected by varying illumination conditions and achieves a recognition accuracy of 94.8% or higher for the vast majority of sample data, effectively detecting the positions and surface materials of targets with different sizes and spatial locations.
Short Bio: Yang Yue received the B.S. and M.S. degrees in electrical engineering and optics from Nankai University, China, in 2004 and 2007, respectively. He received the Ph.D. degree in electrical engineering from the University of Southern California, USA, in 2012. He is a Professor with the School of Information and Communications Engineering, Xi'an Jiaotong University, China. Dr. Yue’s current research interest is intelligent photonics, including optical communications, optical perception, and optical chip. He has published ~300 journal papers (including Science) and conference proceedings with >12,000 citations, one book, seven edited books, two book chapters, >60 issued or pending patents, >200 invited presentations (including 1 tutorial, >30 plenary and >80 keynote talks). Dr. Yue is a Fellow of SPIE, a Senior Member of IEEE and Optica. He is an Associate Editor for IEEE Access and Frontiers in Physics, Editor Board Member for four other scientific journals, Guest Editor for >10 journal special issues. He also served as Chair or Committee Member for >100 international conferences, Reviewer for >70 prestigious journals.

Prof. Yen-Wei Chen
Ritsumeikan University, Japan
Speech Title: Deep learning in diagnosis of focal liver lesions using multi-phase CT images
Abstract: Liver cancer is the second most common cause of cancer-related deaths worldwide among men, and the sixth among women. Radiological examinations, such as computed tomography (CT) images and magnetic resonance images (MRI) are the primary methods of detecting focal liver lesions. Artificial intelligence-based diagnosis systems play an important role in the early and accurate detection and classification of focal liver lesions. Recently, deep learning (DL), which learns data-driven, highly representative, hierarchical image features, have proven to be superior to conventional machine learning using hand-crafted low-level features and mid-level features. In this talk, I will introduce several our proposed deep-learning-aided detection and classification of focal liver lesions, and prediction of early recurrence of liver cancers.
Short Bio: Yen-Wei Chen received the B.E. degree in 1985 from Kobe Univ., Kobe, Japan, the M.E. degree in 1987, and the D.E. degree in 1990, both from Osaka Univ., Osaka, Japan. He was a research fellow with the Institute for Laser Technology, Osaka, from 1991 to 1994. From Oct. 1994 to Mar. 2004, he was an associate Professor and a professor with the Department of Electrical and Electronic Engineering, Univ. of the Ryukyus, Okinawa, Japan. He is currently a professor with the college of Information Science and Engineering, Ritsumeikan University, Japan. He is the founder and the first director of Center of Advanced ICT for Medicine and Healthcare, Ritsumeikan University.
His research interests include medical image analysis, computer vision and computational intelligence. He has published more than 300 research papers in a number of leading journals and leading conferences including IEEE Trans. Image Processing, IEEE Trans. Medical Imaging, Pattern Recognition. He has received many distinguished awards including ICPR2012 Best Scientific Paper Award, 2014 JAMIT Best Paper Award. He is/was a leader of numerous national and industrial research projects.

Assoc. Prof. Yik-Chung Wu
The University of Hong Kong (HKU), China
IEEE Senior Member
Speech Title: Parameter tuning-free matrix completion: A Bayesian approach
Abstract: Matrix completion is an important data analytic tool in many applications, such as recommendation systems and image completion. Traditionally, matrix completion is approached from optimization perspective. While proven to be effective, optimization-based matrix completion usually involve hyperparameters tuning, with one of the major hyperparameters being the matrix rank. However, when the number of hyperparameters is more than 3 or 4, tuning them becomes computationally expensive. This talk approaches the problem from the Bayesian perspective and shows how hyperparameter tuning can be eliminated while providing comparable or even better performance than corresponding optimization-based algorithms.
Short Bio: Yik-Chung Wu received the B.Eng. (EEE) degree in 1998 and the M.Phil. degree in 2001 from the University of Hong Kong (HKU). He received the Croucher Foundation scholarship in 2002 to study Ph.D. degree at Texas A&M University, College Station, and graduated in 2005. From August 2005 to August 2006, he was with the Thomson Corporate Research, Princeton, NJ, as a Member of Technical Staff. Since September 2006, he has been with HKU, currently as an Associate Professor. He was a visiting scholar at Princeton University, in summers of 2015 and 2017. His research interests are in general areas of signal processing and communication systems , and in particular Bayesian inference, distributed algorithms, and large-scale optimization. Dr. Wu served as an Editor for IEEE Communications Letters, and IEEE Transactions on Communications. He is currently a Senior Area Editor for IEEE Transactions on Signal Processing, an Associate Editor for IEEE Wireless Communications Letters, and an Editor for Journal of Communications and Networks. He was a TPC member for over 100 IEEE major conferences. He received four best paper awards in international conferences, with the most recent one from IEEE International Conference on Communications (ICC) 2020. He is a senior member of the IEEE.

Assoc. Prof. Shijian Lu
Nanyang Technological University, Singapore
Speech Title: Sustainable Artificial Intelligence via Data Generation and Knowledge Transfer
Abstract: Artificial intelligence (AI) has achieved great progress with the advance of deep learning technology in the past few years. This trend recently even accelerates thanks to the development of foundation models in different research areas such as computer vision, natural language processing, etc. On the other hand, training deep network models especially large-scale foundation models usually requires a huge amount of training data and computational resources, where sustainability has become one big concern due to the high costs in data collection and deep network training. This talk will share our recent work that aims to tackle the sustainability of AI and deep learning from two complementary perspectives. The first is data synthesis, aims to generate realistic and high-fidelity data that can be directly and effectively applied for deep network training. We have explored various approaches such as image composition, image style transfer, image editing, etc., and obtained very promising outcomes. The second is knowledge transfer, aiming to leverage previously learnt knowledge or annotated data to facilitate the handling of new tasks with minimal data collection and network training. For this perspective, we have designed a series of techniques on unsupervised domain adaptation, unsupervised model adaptation, domain generalization, etc.
Short Bio: Prof Lu is an Associate Professor in the College of Computing and Data Science, Nanyang Technological University. He received his PhD in electrical and computer engineering from the National University of Singapore. His research interests include computer vision and deep learning. He has published more than 100 internationally refereed journal and conference papers and co-authored over 10 patents in these research areas. Before joining in NTU, he took several leadership roles in the Institute for Infocomm Research (I2R), the Agency for Science, Technology, and Research (A*SATR) in Singapore, including Head of Visual Attention Lab, Deputy Head of Satellite Department, etc. Dr Lu is currently an Associate Editor for the journals of Pattern Recognition (PR) and Neurocomputing. He has also served in the program committee of several international conferences such as the Area Chair of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Senior Program Committee of the International Joint Conferences on Artificial Intelligence (IJCAI) and AAAI Conference on Artificial Intelligence (AAAI), the General Chair of the IAPR International Workshop on Document Analysis System (DAS) in 2020, etc.