Yannis Manolopoulos
Recommending POIs in LBSNs with Deep Learning
Open University of Cyprus

More Info
Ernesto Damiani
Cloud Sustainability via ML-based Microservice Resource Management
Khalifa University

More Info
Esma Aïmeur
Privacy and Cybersecurity in the Age of IoT
University of Montreal

More Info

Invited Speaker: Yannis Manolopoulos

Yannis Manolopoulos holds a 5-years Diploma degree in Electrical Engineering (1981) and a Ph.D. degree in Computer Engineering (1986), both from the Aristotle University of Thessaloniki. He is Professor and Vice-Rector of the Open University of Cyprus as well as Professor Emeritus of the Aristotle University of Thessaloniki. He has been with the University of Toronto, the University of Maryland at College Park, the University of Cyprus, and the Hellenic Open University. He has also served as President of the Board of the University of Western Macedonia in Greece and Vice-President of the Greek Computer Society. His research interest focuses on Data Management. He has co-authored 6 monographs and 10 textbooks in Greek, as well as >350 journal and conference papers. He has received >15700 citations from >2300 distinct academic institutions from >100 countries (h-index=57). He has also received 5 best paper awards from SIGMOD, ECML/PKDD, MEDES (2), and ISSPIT conferences. He delivered keynote talks at 24 conferences in Albania, Algeria, Austria, Bulgaria, Cyprus, Czech Republic, France, Greece, Italy, Kosovo, Lebanon, Luxembourg, Montenegro, Morocco, Poland, Romania, and Russia. He served as an external member of 20 doctoral examination committees in Brazil, Denmark, France, Italy, Poland, and Spain. Evaluator for national funding agencies: Austria, Canada, Cyprus, Czech Republic, EU, Estonia, Georgia, Greece, Hong Kong, Israel, Italy, Russia, and Switzerland. Currently, he serves in the Editorial Boards of the following journals (among others): Digital (EiC), Information Systems, World Wide Web, Computer Journal, Data Science and Analytics, as well as in the Board of the Research and Innovation Foundation of Cyprus.

Title: “Recommending POIs in LBSNs with Deep Learning”

In recent years, the representation of real-life problems into k-partite graphs introduced a new era in Machine Learning. The combination of virtual and physical layers through Location-Based Social Networks (LBSNs) offered a different meaning to the constructed graphs. To this point, multiple diverse models have been introduced in the literature that aims to support users with personalized recommendations. These approaches represent the mathematical models that aim to understand users’ behavior by detecting patterns in users’ check-ins, reviews, ratings, and friendships. In this talk, we discuss state-of-the-art methods for POI recommendations based on deep learning techniques. First, we categorize these methods based on data factors or features they use, the data representation, the methodologies applied, and the recommendation types they support. By briefly representing recent key approaches, we highlight the limitations and trends. The future of the area is illustrated.

Invited Speaker: Ernesto Damiani

Ernesto Damiani is the Senior Director of Robotics and Intelligent Systems Institute at Khalifa University. He is also a Professor in the Electrical and Computer Engineering Department and Director of the Khalifa University Center for Cyber-Physical Systems (C2PS). Dr. Damiani is the Chair of the Information Security Program and a Research Professor in EBTIC. He is on extended leave from the Department of Computer Science, Università Degli Studi di Milano, Italy, where he leads the SESAR research lab. He is also the President of the Italian Consortium of Computer Science Universities (CINI). Ernesto’s research interests include secure service-oriented architectures, privacy-preserving Big Data analytics, and Cyber-Physical Systems security. Dr. Damiani holds and has held visiting positions at a number of international institutions, including George Mason University in Virginia, US; Tokyo Denki University, Japan; LaTrobe University in Melbourne, Australia; and the Institut National des Sciences Appliquées (INSA) at Lyon, France. He is a Fellow of the Japanese Society for the Progress of Science. He has been Principal Investigator in a number of large-scale research projects funded by the European Commission in the context of the Seventh Framework Program and Horizon 2020, the Italian Ministry of Research, and by private companies such as British Telecom, Cisco Systems, SAP, Telecom Italia, Siemens Networks (now Nokia Siemens) and many others. Dr. Damiani serves on the editorial board of several international journals; among others, he is the EIC of the International Journal on Big Data and of the International Journal of Knowledge and Learning. He is Associate Editor of IEEE Transactions on Service Computing and of the IEEE Transactions on Fuzzy Systems. He is also a senior member of the IEEE and served as Vice-Chair of the IEEE Technical Committee on Industrial Informatics. In 2008, Ernesto was nominated IEEE Senior Member and ACM Distinguished Scientist and received the Chester Sall Award from the IEEE Industrial Electronics Society. Ernesto Damiani’s work has more than 16,100 citations on Google Scholar and more than 6,300 citations on Scopus, with an h-index of 34. With 494 publications listed on DBLP, he is considered among the most prolific European computer scientists.

Title: “Cloud Sustainability via ML-based Microservice Resource Management”

The growing adoption of MicroService Architectures (MSA) has led to a number of research efforts to improve their performance, reliability, and robustness via demand-driven scaling, ensuring Quality-of-Service and the enforcement of Service-Level agreements (SLAs). However, less attention has been devoted to efficient cloud resource allocation and optimal power management, which are crucial for the sustainability of data-driven, computation-intensive applications. In this talk, we survey some microservice frameworks, highlighting the problems of controlling resource utilization and power consumption. We discuss the assumptions behind the growing use of Machine Learning as an alternative to, or in association with, traditional optimization techniques for optimizing workload-driven resource sharing within microservice meshes.

Invited Speaker: Esma Aïmeur

Esma Aïmeur is Professor at the Department of Computer Science at University of Montréal. She is the Director of the Artificial Intelligence and Cybersecurity laboratory. She obtained her Ph.D. in computer science (Artificial Intelligence) from the University of Paris 6 (France). She works on privacy and security, applying artificial intelligence techniques to manage personal data in e-Learning, Finance, and Medicine. Her most recent research focuses on online deception, the ethics of artificial intelligence, social networks, security awareness, recommender systems, and privacy-preserving. She was the director for 10 years of a Master in Electronic Commerce, a joint program between HEC Montréal, the Faculty of Law, and the Department of Computer Science. She was appointed a member of the Data Protection Advisory Committee of the University of Montreal. Her responsibilities include helping to improve policies and decision-making in cyber education by providing best practices to protect personal data. She was program chair for the 24 workshops of the 2016 World Web Conference, one of which was co-hosted by Sir Tim Berners-Lee, the inventor of the Web. In 2017, she co-chaired the 7th MCETECH international conference on electronic technologies. In 2019, she was the representative of the Natural Sciences and Engineering Research Council of Canada (CRSNG) on the panel of the panel "Canada-UK Artificial Intelligence Initiative: building competitive and resilient economies and societies through responsible AI". This year, she is the chair of the "1st IJCAI workshop on Adverse Impacts and Collateral Effects of Artificial Intelligence Technologies” (AIofAI), Montréal, Canada, 2021. She is also the PC co-chair of FPS, "The 14th International Symposium on Foundations & Practice of Security", Paris, France, 2021, and Guest editor of the special issue "Understanding and Mitigating Online Deception", Frontiers in Artificial Intelligence, 'AI for Human Learning and Behavior Change' 2021. She is currently co-editor of the International Journal of Privacy and Health Information Management, associate editor for IEEE Transactions on Big Data, and for Artificial Intelligence for Human Learning and Behavior Change.

Title: “Privacy and Cybersecurity in the Age of IoT”

Fast-paced technological developments have created a proliferating web of interconnected smart devices that exchange a large volume of data on a daily basis. In today’s world, an average person is estimated to have four IoT devices including smartwatches, phones, personal assistants, etc. Users have grown accustomed to the services offered by such devices that they often overlook how much of their private information is known to other companies and third parties. This data includes medical details captured by insulin pumps and pacemakers as well as virtual assistants that know a person’s schedule, activities, sleeping habits, intimate relationships, and so much more. The benefits of IoT devices are well recognized but users can be remiss about the potential harm this technology can pose. The lack of awareness amongst the general public is usually demonstrated in the way they handle their devices such as constantly leaving their location tracker on. In this talk, I will highlight the urgent need for privacy-preserving measures on three fronts: the technical, regulatory, and human sides. First, the devices themselves need to have secure communication protocols and deploy adequate risk management assessments and interventions. Second, tighter restrictions have to be considered: The current lack of specific regulations leaves a backdoor open for suspicious activities that can escalate to highly unethical practices like harvesting data belonging to minors. Third, the user should be aware of what information they are sharing, with whom, and for how long would that data be retained.