Talk by Prof. Ai-Chun Pang on Edge Intelligence for Connected Cars
We are very pleased to announce the following talk by Prof. Ai-Chun Pang on Edge Intelligence for Connected Cars, as per the following details:
Edge Intelligence for Connected Cars: Performance, Privacy and Robustness
With advances in wireless communications and sensing technologies, autonomous and connected cars are becoming a reality. Emerging vehicular applications will require significant computing power to process data generated by vehicle sensors (e.g., cameras) for an intelligent and near-real-time response.
Edge computing is considered a promising solution in vehicular networks to fulfill the requirement. Vehicles constitute a collaborative computing platform and can jointly conduct AI learning tasks to optimize performance.However, due to privacy issues, drivers may not allow their vehicles to share raw sensor data with other vehicles.
To tackle this problem, Google has advocated a new kind of privacy-preserving edge learning as Federated Learning (FL). In this lecture, we will give a usage scenario to elaborate on how edge intelligence is adopted for connected vehicles and present the development of our edge-based mobile video platform, named "OmniEyes," to support timely video analytics for cars. The platform collects live street videos and converts them, using AI technologies, to various location-based information for real-time task executions and long-term statistical analytics via connected mobile cameras.
We will present how FL aids OmniEyes in preserving user privacy while maintaining AI model accuracy. Specifically, we are interested in the effects of limited labeled data and Non-IID (Non-Identically Independently Distributed) data in FL.
We will also discuss the vulnerability of the FL framework and some defense methods against privacy leakage and security threats.
Prof. Ai-Chun Pang
Department of Computer Science and Information Engineering
Graduate Institute of Networking and Multimedia
National Taiwan University
Ai-Chun Pang received B.S., M.S., and Ph.D. degrees in Computer Science and Information Engineering from National Chiao Tung University, Taiwan, in 1996, 1998, and 2002, respectively. Dr. Pang joined the Department of Computer Science and Information Engineering, National Taiwan University (NTU), Taiwan, in 2002 and is now a Distinguished Professor. She was the Associate Dean of the College of Electrical Engineering and Computer Science from 2018 to 2022. She is also the co-founder of OmniEyes Inc. (a startup company focusing on edge-AI technology for mobile video platform). Her research interests include wireless and mobile networking, edge computing, and IoT.
Dr. Pang is currently the editor of IEEE Transactions on Mobile Computing, IEEE Transactions on Vehicular Technology, IEEE Transactions on Network and Service Management, IEEE Transactions on Emerging Topics in Computing, and ACM Transactions on Cyber-Physical Systems. She co-authored the book "Wireless and Mobile All-IP Networks" published by John Wiley. She was a recipient of Outstanding Research Award (a prestigious award in Taiwan) of the Ministry of Science and Technology (MOST) in 2019 and 2022. She is an IEEE Vehicular Technology Society (VTS) Distinguished Lecturer in 2018-22 and an IEEE Communications Society Distinguished Lecturer in 2022-2023. She received VTS Women's Distinguished Career Award in 2020. She is a Fellow of the IEEE.
13:30- / Tuesday, November 8th, 2022
If you would like to join, please contact by email.
Email : kei [at]nii.ac.jp
The person in charge will send you the zoom url of this event.
Yusheng Ji Laboratory