Institute of Information Science, Academia Sinica



Press Ctrl+P to print from browser


Distributed AI and Edge-oriented IoT Infrastructures for Smart Cities

  • LecturerProf. Hock Beng Lim (Co-Director, Center for Smart Systems Singapore University of Technology and Design)
    Host: Ling-Jyh Chen
  • Time2018-11-30 (Fri.) 13:30 – 15:30
  • LocationAuditorium 106 at IIS new Building

Many cities in the world, including Singapore, are deploying IoT infrastructures to support smart cities applications. The key challenge is how to enable IoT infrastructures to be smart, easy to manage and scalable. To address this challenge, we have developed a virtualization-based IoT gateway to support sensor nodes with heterogeneous network protocols, and an ontology-driven IoT infrastructure to ease deployment and enhance scalability. Our IoT infrastructure is edge-oriented, with the IoT gateway being powerful enough to perform simple data processing.

We are developing distributed AI techniques which use edge nodes to run simple machine learning models for event detections and preliminary analysis. The event detection and preliminary analysis results, together with the relevant sensor data, are sent to the cloud backend for detailed processing. We are designing and implementing distributed person re-identification techniques for video surveillance as a use case to explore the development of distributed AI and edge-oriented infrastructures.


Hock Beng Lim is the Co-Director of the Center for Smart Systems (CS2) at the Singapore University of Technology and Design. He received his BS in Computer Engineering, MS in Electrical Engineering, and PhD in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign, and his MS in Management Science and Engineering from Stanford University. His research interests include sensor networks and IoT, cyber-physical systems, wireless and mobile networks, participatory and urban sensing, cloud computing, smart cyberinfrastructure, data management and analytics, and edge-oriented AI infrastructure.