Meeting ID: 988 2129 5100; Passcode: 188976
Welcome Words!
Huber Flores,University of Tartu, Estonia
Watch the Keynote Talk Recording here
Sasu Tarkoma
University of Helsinki, Finland
Abstract: This talk gives an overview of the MegaSense research program that is a collaboration between Computer Science, Atmospheric Sciences and Geosciences at the University of Helsinki. The research program designs and deploys an environmental monitoring system for realizing low-cost, near real-time and high resolution spatio-temporal air pollution maps of urban areas. MegaSense involves a novel hierarchy of distributed air quality sensors, in which more accurate sensors calibrate lower cost sensors. Current low-cost air quality sensors suffer from measurement drift and they have low accuracy. We address this significant open problem for dense urban areas by developing a calibration scheme based on machine learning that detects and automatically corrects drift. MegaSense integrates with the 5G cellular network and leverages mobile edge computing for sensor management and distributed pollution map creation. We pave the way for mega-city and planet-scale sensing systems with 6G and beyond.
Speaker bio: Sasu Tarkoma is a full Professor and the dean of the Faculty of Science at University of Helsinki, Finland. He also leads the Megasense group at the University of Helsinki. His expertise includes the Internet of Things, Artificial Intelligence, Edge Computing, and Big data. Megasense focuses on extending state-of-the-art machine learning solutions for air pollution modelling and prediction and integrating them into a scalable data processing and AI platform for air pollution analysis.
Farooq Ayoub Dar,
University of Tartu, Estonia
Agustin Zuniga,
University of Helsinki, Finland
Zhigang Yin,
University of Tartu, Estonia
Abdul-Rasheed Ottun,
University of Tartu, Estonia
Watch the Keynote Talk Recording here
Petteri Nurmi
University of Helsinki, Finland
Abstract: This talk gives an overview of the research activities related to underwater pervasive data science. The research develops new ways to monitor aquatic environments (oceans, lakes, rivers etc.) using drones, technology carried by divers, and fixedly deployed sensors (e.g., buoys and ships), as well as investigates ways to facilitate the work of marine scientists. Developing computing support for underwater environments is highly challenging as different water conditions (turbidity, turbulence, etc.) make robust modeling difficult and as the difficulty of operating computing or communication underwater makes access to computing resources scarce. We address these challenges through development of new sensing modalities and underwater computing systems.
Speaker bio: Petteri Nurmi is an Associate Professor at the University of Helsinki where he also leads the Pervasive Data Science Group. His research expertise includes Internet of Things, Pervasive Computing, Sensors and Sensing, and their applications in Data Science.
Martha Arbayani Zaidan,
University of Helsinki, Finland
Naser Hossein Motlagh,
University of Helsinki, Finland
Alberto Defendi,
University of Helsinki, Finland
Xiaoli Liu,
University of Helsinki, Finland