Keynote Speakers

Keynote Speakers

Ryan Baker (Director of the Penn Center for Learning Analytics)
University of Pennsylvania, USa

Ryan Baker is a Professor at the University of Pennsylvania, and Director of the Penn Center for Learning Analytics. His lab conducts research on engagement and robust learning within online and blended learning, seeking to find actionable indicators that can be used today but which predict future student outcomes. Baker has developed models that can automatically detect student engagement in over a dozen online learning environments, and has led the development of an observational protocol and app for field observation of student engagement that has been used by over 150 researchers in 7 countries. Predictive analytics models he helped develop have been used to benefit over a million students, over a hundred thousand people have taken MOOCs he ran, and he has coordinated longitudinal studies that spanned over a decade. He was the founding president of the International Educational Data Mining Society, is currently serving as Editor of the journal Computer-Based Learning in Context, is Associate Editor of the Journal of Educational Data Mining, was the first technical director of the Pittsburgh Science of Learning Center DataShop, and currently serves as Co-Director of the MOOC Replication Framework (MORF). Baker has co-authored published papers with over 300 colleagues.

Title: When Might a Detector Generalize?

Abstract:Machine-learned based detectors have become an increasingly important part of contemporary online learning systems, measuring and/or predicting constructs ranging from knowledge, to disengagement, to affect, to stopout. However, often when models are developed, they are only tested to a very limited degree (usually just on held-out students from the original data set) and are then used in different situations without further evaluation. In this talk, I will discuss evidence around when detectors generalize -- and when they don't -- in terms of student identity and changes in the learning system itself, using examples from multiple studies in our research group spanning from stopout, to gaming the system, to wheel-spinning, to affect. I will offer some simple guidelines about the situations that seem to be linked to successful model generalization and propose some steps forward for better understanding this challenge.

Ljiljana Trajkovic (IEEE FELLOW)
Simon Fraser University, Canada

Ljiljana Trajkovic received the Dipl. Ing. degree from University of Pristina, Yugoslavia, the M.Sc. degrees in electrical engineering and computer engineering from Syracuse University, Syracuse, NY, and the Ph.D. degree in electrical engineering from University of California at Los Angeles. She is currently a professor in the School of Engineering Science, Simon Fraser University, Burnaby, British Columbia, Canada. Her research interests include communication networks and dynamical systems. She served as IEEE Division X Delegate/Director, President of the IEEE Systems, Man, and Cybernetics Society, and President of the IEEE Circuits and Systems Society. Dr. Trajkovic serves as Editor-in-Chief of the IEEE Transactions on Human-Machine Systems and Associate Editor-in-Chief of the IEEE Open Journal of Systems Engineering. She served as a Distinguished Lecturer of the IEEE Circuits and System Society and a Distinguished Lecturer of the IEEE Systems, Man, and Cybernetics Society. She is a Fellow of the IEEE.

Title: Machine Learning for Detecting Internet Traffic Anomalies

Abstract:Border Gateway Protocol (BGP) enables the Internet data routing. BGP anomalies may affect the Internet connectivity and cause routing disconnections, route flaps, and oscillations. Hence, detection of anomalous BGP routing dynamics is a topic of great interest in cybersecurity. Various anomaly and intrusion detection approaches based on machine learning have been employed to analyze BGP update messages collected from RIPE and Route Views collection sites. Survey of supervised and semi-supervised machine learning algorithms for detecting BGP anomalies and intrusions is presented. Deep learning, broad learning, gradient boosting decision tree, and reservoir computing algorithms are evaluated by developing models based on collected datasets that contain Internet worms, power outages, and ransomware events.

Prof. Yudong Zhang (h-index 84, Chair Professor, BCS Fellow, IEEE and ACM Senior Member)
University of Leicester, UK

Prof. Yudong Zhang worked as a postdoc from 2010 to 2012 with Columbia University, USA, and as an Assistant Research Scientist from 2012 to 2013 with the Research Foundation of Mental Hygiene (RFMH), USA. He served as a Full Professor from 2013 to 2017 with Nanjing Normal University. Now he serves as a professor at the School of Computing and Mathematical Sciences, University of Leicester, UK. His research interests include deep learning and medical image analysis. He is the Fellow of IET, Fellow of EAI, and Fellow of BCS. He is the Senior Member of IEEE, IES, and ACM. He is the Distinguished Speaker of ACM. He was included in Most Cited Chinese Researchers (Computer Science) by Elsevier from 2014 to 2018. He was the 2019 & 2021 recipient of Highly Cited Researcher by Clarivate. He won the Emerald Citation of Excellence 2017 and MDPI Top 10 Most Cited Papers 2015. He is included in Top Scientist in He has (co)authored over 400 peer-reviewed articles in the journals JAMA Psychiatry, Inf Fus, IEEE TFS, IEEE TII, IEEE TIP, IEEE TMI, IEEE IoTJ, Neural Networks, IEEE TITS, Pattern Recognition, IEEE TGRS, IEEE JBHI, IEEE TCSVT, IEEE TETCI, IEEE TCSS, IEEE JSTARS, IEEE TNSRE, IEEE Sensors J, ACM TKDD, ACM TOMM, IEEE/ACM TCBB, IEEE TCAS-II, IEEE JTEHM, ACM TMIS, etc. There are more than 50 ESI Highly Cited Papers and 5 ESI Hot Papers in his (co)authored publications.

Title: Big Data for Infectious Disease Diagnosis and Education

Abstract:COVID-19 is a pandemic disease that caused more than 6.84 million deaths until 7/Feb/2023. X-ray and CT scans are two popular chest imaging techniques used in radiology to get detailed images of the chest noninvasively for diagnostic purposes. Traditional manual analysis of X-ray or CT-based scans is tedious and error-prone. To solve the problem, our lab develops and applies novel big-data-based machine learning theories and techniques, such as advanced pooling-based networks, graph convolutional networks, attention neural networks, weakly supervised networks, etc. We also use cloud computing techniques to run our developed app on the remote server to help doctors in the suburban area. Two other chest-related infectious diseases: secondary pulmonary tuberculosis and community-acquired pneumonia, will be covered in this talk.

Your Awesome Color