Keynote Speaker Ⅰ
Professor Witold Pedrycz
IEEE Life Fellow, Editor-in-Chief of Information Sciences
Editor-in-Chief of WIREs Data Mining and Knowledge Discovery
Professor and Canada Research Chair in Computational Intelligence
Co-editor-in-Chief of Int. J. of Granular Computing (Springer) and J. of Data Information and Management (Springer)
The University of Alberta, Canada
Speech Title: New Frontiers of Machine Learning: Federated Learning
Abstract: With the rapid progress encountered in system modeling and simulation, especially in complex and human-centric systems, we have been witnessing important challenges. The visible requirements are inherently associated with the data and the way they are addressed in system modeling. We identify three ongoing challenges with far-reaching methodological implications, namely (i)modeling in the presence of strict constraints of privacy and security, (ii) efficient model building with limited data of varying quality, and (iii) knowledge distillation. We advocate that to conveniently address these challenges, it becomes beneficial to engage the fundamental framework of Granular Computing to enhance the existing approaches (such as e.g., federated learning in case of (i) and transfer knowledge in (ii)) or establish new directions to the problems. It is demonstrated that various ways of conceptualization of information granules as fuzzy sets, sets, rough sets, and others may lead to efficient solutions. To establish a sound conceptual modeling framework, we include a brief discussion of concepts of information granules and Granular Computing. In the sequel, a concise information granules-oriented design of rule-based architectures is discussed. A way of forming the rules through unsupervised federated learning is investigated along with algorithmic developments. A granular characterization of the model formed by the server vis-a-vis data located at individual clients is presented. It is demonstrated that the quality of the rules at the client’s end is described in terms of granular parameters and subsequently the global model becomes represented as a granular model with parameters in the form of information granules of type-2. The roles of granular augmentations of models in the setting of logic-oriented knowledge distillation are discussed.
A brief introduction to Professor Witold Pedrycz:
Witold Pedrycz (IEEE Life Fellow) is a Professor and Canada Research Chair (CRC) in Computational Intelligence 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 the 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, knowledge discovery, data science, and knowledge-based neural networks among others. Dr. Pedrycz is involved in editorial activities. He is 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).
Keynote Speaker Ⅱ
Professor Zhu Han
ECE Department and CS Department, University of Houston
Speech Title: Federated Learning and Analysis with Multi-access Edge Computing
Abstract: In recent years, mobile devices are equipped with increasingly advanced computing capabilities, which opens up countless possibilities for meaningful applications. Traditional cloud-based Machine Learning (ML) approaches require the data to be centralized in a cloud server or data center. However, this results in critical issues related to unacceptable latency and communication inefficiency. To this end, multi-access edge computing (MEC) has been proposed to bring intelligence closer to the edge, where data is originally generated. However, conventional edge ML technologies still require personal data to be shared with edge servers. Recently, in light of increasing privacy concerns, the concept of Federated Learning (FL) has been introduced. In FL, end devices use their local data to train a local ML model required by the server. The end devices then send the local model updates instead of raw data to the server for aggregation. FL can serve as enabling technology in MEC since it enables the collaborative training of an ML model and also enables ML for mobile edge network optimization. However, in a large-scale and complex mobile edge network, FL still faces implementation challenges with regard to communication costs and resource allocation. In this talk, we begin with an introduction to the background and fundamentals of FL. Then, we discuss several potential challenges for FL implementation. In addition, we study the extension to Federated Analysis (FA) with potential applications.
A brief introduction to Professor Zhu Han:
Zhu Han received the B.S. degree in electronic engineering from Tsinghua University, in 1997, and the M.S. and Ph.D. degrees in electrical engineering from the University of Maryland, College Park, in 1999 and 2003, respectively. From 2000 to 2002, he was an R&D Engineer of JDSU, Germantown, Maryland. From 2003 to 2006, he was a Research Associate at the University of Maryland. From 2006 to 2008, he was an assistant professor in Boise State University, Idaho. Currently, he is a John and Rebecca Moores Professor in Electrical and Computer Engineering Department as well as Computer Science Department at University of Houston, Texas. His research interests include security, wireless resource allocation and management, wireless communication and networking, game theory, and wireless multimedia. Dr. Han is an NSF CAREER award recipient of 2010. Dr. Han has several IEEE conference best paper awards, and winner of 2011 IEEE Fred W. Ellersick Prize, 2015 EURASIP Best Paper Award for the Journal on Advances in Signal Processing and 2016 IEEE Leonard G. Abraham Prize in the field of Communication Systems (Best Paper Award for IEEE Journal on Selected Areas on Communications). Dr. Han is the winner 2021 IEEE Kiyo Tomiyasu Award. He has been an IEEE fellow since 2014, AAAS fellow since 2020 and IEEE Distinguished Lecturer from 2015 to 2018. Dr. Han is a 1% highly cited researcher according to Web of Science since 2017.
Invited Speaker Ⅰ
Dr. Lalit Garg
Faculty of Information and Communication Technology, University of Malta, Malta, Europe
Speech title: Application of machine learning and signal processing techniques to real time detection and prediction of epileptic seizures
Abstract: Epilepsy is a neurological disease, which affects around 50 million people of the world’s population. With the increased development of effective prevention treatments, early diagnosis of epileptic seizures is becoming necessary because the patient can undergo treatments, which can delay or prevent the disease progression. A number of studies have been carried out in the past to explore the feasibility of a practical real-time epilepsy seizure detector. However, still there is a need for improved methods of data acquisition, feature extraction and feature space creation for epilepsy seizure detection. Also, there is no known technique available for accurately predict a seizure onset well ahead. An accurate prediction even few minutes before the seizure onset might help prepare the patient, his/her caregiver. Therefore, we developed energy efficient real-time seizure detection algorithms which can be implemented in wearable, non-invasive EEG devices which would ensure prompt and effective management of seizures. The research focus also includes development of accurate seizure detection and prediction algorithms to prevent or minimize harmful effects of seizure onsets. Our methods differ from previous studies mainly on two things; the first is providing a simple yet very effective training set acquisition for epileptic seizure detection and prediction, and the second is testing these novel approaches using a high number of seizure instances, precisely a total of 192 seizures from total 22 pediatric patients.
Biography: Lalit Garg is a Lecturer in Computer Information Systems at the University of Malta, Malta. He is also an honorary lecturer at the University of Liverpool, UK. He has also worked as a researcher at the Nanyang Technological University, Singapore and at the University of Ulster, UK. He received his first degree in electronics and communication engineering from the Barkatullah University, Bhopal, India, in 1999, and his postgraduate in information technology from the ABV-Indian Institute of Information Technology and Management (IIITM), Gwalior, India in 2001. He received his Ph.D. degree from the University of Ulster, Coleraine, U.K., in 2010. His research interests are missing data handling, machine learning, data mining, mathematical and stochastic modelling, and operational research, and their applications especially in the healthcare domain. He has published over 80 technical papers in refered high impact journals, conferences and books and has more than 550 citation count to his publications.
More notable speakers is to be updated...