Keynotes
The Indoor Positioning System: A Journey through Space and Time
Moustafa Youssef, The American University in Cairo (Keynote 1)
Abstract:
Although GPS is regarded as a ubiquitous outdoor localization technology, a comparable solution for indoor environments remains elusive. While a remarkable effort has been put in developing indoor location determination systems, they are still isolated efforts that are tailored to specific deployments. A truly ubiquitous indoor positioning system is envisioned to be deployed on a large scale worldwide, with minimum overhead, and to work with heterogeneous devices. Such a system will enable a wide set of applications including worldwide indoor navigation, enhancing emergency response systems, indoor analytics, providing a richer environment for location-aware social networking applications, among many others.
In this talk, I'll present our decades-long experience towards achieving this goal, highlighting the current state-of-the-art accomplishments and the challenges still remaining to be addressed. I end the talk by a discussion of the current trends and open research directions in this exciting field.
Bio:
Moustafa Youssef is a professor at the American University in Cairo. His research interests include mobile wireless networks, mobile and pervasive computing, location determination technologies, and quantum computing. He is an Associate Editor for ACM TSAS and the IEEE TMC, served as the Lead Guest Editor of the IEEE Computer Special Issue on Transformative Technologies and an Area Editor of ACM MC2R as well as on the organizing and technical committees of numerous prestigious conferences. He is the recipient of the 2003 University of Maryland Invention of the Year award, the 2010 TWAS-AAS-Microsoft Award for Young Scientists, the 2013 and 2015 COMESA Innovation Award, the 2013 ACM SIGSpatial GIS Conference Best Paper Award, the 2017 Egyptian State Award, multiple Google Research Awards, among many others. He is also an AAS, IEEE, and ACM Fellow.
Let's make Spatial not Special, Shall We?
Mo Sarwat, Wherobots Inc. (Keynote 2)
Abstract:
For decades, many leaders in the spatial industry have echoed bold claims like "The spatial revolution is coming," yet it has never fully materialized. Have you ever wondered why? There are definitely use cases where spatial thinking can increase revenue, mitigate risk, and reduce cost to customers. Nonetheless, many within the spatial community feel that geospatial thinking is undervalued in the enterprise world, and yet to live up to its true potential. One key reason for this is the long-held belief that "Spatial is Special." In this talk, Mo will explore this challenge, offer potential solutions, and highlight how Wherobots is driving a paradigm shift to bridge the gap between the geospatial community and the broader data and AI communities.
Bio:
Mo Sarwat is the Co-Founder and CEO of Wherobots, and the co-creator of Apache Sedona, an open-source software that has gained significant popularity in recent years for enabling scalable spatial data processing and AI pipelines. Prior to founding Wherobots, Mo served as a tenured associate professor of computer science at Arizona State University. He earned his Ph.D. in computer science from the University of Minnesota and has authored over 60 research papers in leading technical conferences and academic journals. Mo is also the recipient of the prestigious 2019 National Science Foundation CAREER Award for his work on scalable spatial data and AI infrastructure.
LLMs it (or not!): Foundational and robust approaches for modelling trajectory and spatio-temporal behaviours
Flora Salim, UNSW Sydney, Australia (Keynote 3)
Abstract:
Spatio-temporal data have been very instrumental for developing predictive models in various fields like energy, transport and mobility, retail, and public health management. The heterogeneity and dynamic nature of spatio-temporal data often require handcrafted feature transformations, making modeling more complex, and typically requires specific narrow modelling approach. Transformers offer solutions by enabling effective modeling of sequential behavior with minimal feature transformation. Further, modelling with spatiotemporal data is often hampered by the dynamic nature of the data and data sparsity.
LLM's common knowledge and semantic understanding offer new opportunities for addressing the inherent challenges from spatio-temporal data and trajectory learning tasks. We started exploring language-based modeling paradigm for modeling trajectory and spatio temporal behaviours since late 2021. To address data sparsity and lack of semantic information in common spatio-temporal data, we leverage LLMs to improve the generalizability and improve the performance, in zero-shot and fine-tuned settings. We have also introduced the first work on LLMs-based models for POI recommendation system.
But -- do we really need LLMs for many spatio-temporal and trajectory learning tasks? This talk presents the use of LLMs in to enhance generalization and few-shot learning capability in tasks like mobility forecasting, point-of-interest recommendations, and energy load forecasting. This talk also discusses some approaches to deal with missing data, sporadic time-series, distribution shift, and emerging tasks.
Bio:
Flora Salim is a Professor in the School of Computer Science and Engineering (CSE), the inaugural Cisco Chair of Digital Transport & AI, University of New South Wales (UNSW) Sydney, and the Deputy Director (Engagement) of UNSW AI Institute. Her research is on machine learning for time-series and multimodal sensor data and on trustworthy AI. She has received several prestigious fellowships including Humboldt-Bayer Fellowship, Humboldt Fellowship, Victoria Fellowship, and ARC Australian Postdoctoral (Industry) Fellowship.
She has attracted more than $20m in research and industry funding in the last 10 years, as lead or sole CI for more than half of these grants, including research funded by ARC, Microsoft Research US, Northrop Grumman Corporation US, Qatar National Priorities Research Program, Cisco, IBM Research, several city councils and many other industry and government partners/funders. She is a Chief Investigator on the ARC Centre of Excellence for Automated Decision Making and Society (ADM+S), co-leading the Machines Program and the Mobilities Focus Area. She was the recipient of the Women in AI Awards 2022 Australia and New Zealand in the Defence and Intelligence Category.
She is a member of the Australian Research Council (ARC) College of Experts. She serves as an Editor of IMWUT, Associate-Editor-in-Chief of IEEE Pervasive Computing, Associate Editor of ACM Transactions on Spatial Algorithms and Systems, a Steering Committee member of ACM UbiComp. She has served as a Senior Area Chair / Area Chair of AAAI, WWW, NeurIPS, and many other top-tier conferences in AI and ubiquitous computing.
She is an Associate of ELLIS Alicante and holds an Honorary Professor appointment at RMIT University. She was a Visiting Professor at University of Kassel, Germany, and University of Cambridge, England, in 2019.
