Spatio-Temporal AI Powering the Phy-gitalTM City
05:30 PM (PDT), Tuesday, November 2, 2021
08:30 AM (GMT+8), Wednesday, November 3, 2021
Abstract: Spaito-Temporal Artificial Intelligence (ST-AI) is a collection of tools, models and methods that can be used to understand the nature and dynamics of the physical world. With the technological developments of digital twins and abundant data collection tools, our cities and our physical activities are being digitized at varying spatial and temporal scales. The increasing city data aggregated from multiple data sources allows us to deploy AI tools and methods to understand the complex social and physical phenomena of cities. The presentation will address our Phy-gitalTM ST-AI platform that were deployed to handle several problems in both business and government environments. The Phy-gitalTM platform is composed of big data engine, knowledge graph engine, and ST-AI engine as well as a set of pre-trained models built from many real-world cases. We will present several promising application results, such as, city management, disaster mitigation, retail operation and real estate planning. Developing a more generic ST-AI engine is still challenging, however, ST-AI liberates a huge potential in computation, analysis and prediction of spatio-temporal problems in phy-gital cities.
Biography: Dr Tao is an entrepreneur, a researcher and an investor with vision and passion on geospatial technology and its broad applications. Tao is Founder of wayz.ai, a developer of the spatial-temporal AI technology for smart cities and businesses. As Chairman of Global Earth Ventures, Tao has invested and incubated nearly 100 companies in the tech sector. Tao held Canada Research Chair Professorship at York University, Toronto. He has authored and co-authored over 200 technical papers, and holds a number of technical patents.
Tao has many entrepreneur experiences. He founded his first company GeoTango who pioneered the first internet 3D mapping system and was acquired by Microsoft. Tao is the founding member and Director of Microsoft Virtual Earth program. He Led the development of the Microsoft’s global mapping platform serving for over 120 countries and regions. Tao is former CEO of PPTV, China’s leading online TV provider who has served over 300 million active user worldwide.
Vincent has received many international awards for his achievements both in academia and industry. Recently, he received his Honoria Doc Degree of Laws from York University rewarding his contributions to the society. Tao has also contributed to the establishment of Tao’s Engineering Scholarship at York University, and ST-AI Innovation Research Grant at Wuhan University, China.
Geospatial Technologies for Ride-Sharing and Delivery Platforms
05:30 PM (PDT), Wednesday, November 3, 2021
08:30 AM (GMT+8), Thursday, November 4, 2021
Abstract: Ride-sharing and delivery platforms such as Uber require complex geospatial inputs in order to generate their user experiences, match demand with drivers, and calculate fares. For example, route planning for meal deliveries uses predictions of the travel time between any two locations in the road network, and platform efficiency heavily depends on the accuracy of these predictions. I will describe the data-driven geospatial technologies, including those for travel time prediction, route optimization, and map error detection, that form the foundation of such multi-sided platforms. I will detail the challenges, such as data sparsity on parts of the road network, and show that highly accurate predictions need to take into account the granular dynamics of the physical system (traffic patterns in the road network). I will also illustrate machine learning architectures that incorporate this contextual information.
Biography: Dawn Woodard leads modeling and analytics for platforms including Uber Maps, which is the geospatial platform used in Uber’s user interfaces and decision systems. The team’s technologies include road map and points of interest data, map search, route optimization, travel time prediction, and navigation. Dr. Woodard earned her PhD in statistics from Duke University, after which she was a faculty member in the School of Operations Research and Information Engineering at Cornell. There she developed forecasting methods for emergency vehicle decision support systems, in collaboration with ambulance organizations. After receiving tenure at Cornell, she joined Microsoft Research for her sabbatical, where she created travel time prediction methods for use in Bing Maps. She then transitioned to Uber, leading modeling and analytics for the pricing and matching teams, eventually transitioning to her current role in Platforms.