Towards Mobile Intelligence for Smart Cities
|
Speaker (s):
Zimu ZHOU
Post-Doctoral Researcher,
Computer Engineering and Networks Laboratory,
ETH Zurich
|
|
Date:
Time:
Venue:
|
|
November 19, 2018, Monday
10:00am - 11:00am
Meeting Room 5.1, Level 5
School of Information Systems
Singapore Management University
80 Stamford Road
Singapore 178902
|
|
ABSTRACT
One vision of smart cities is that mobile devices will collect information, extract knowledge and make decisions about the citizens and their living environment to provide intelligent personal and urban services. Such a vision requires high-quality data collection from mobile sensors, deep data analysis on mobile devices, and coordinated moving patterns of mobile users. In this talk, I will present three software solutions to make mobile systems for smart cities more reliable, deployable and manageable. The first solution improves the quality of environmental sensor data collection via sensor array calibration. The algorithms are validated in a 2-year mobile air pollution monitoring deployment in the city of Zurich. The second solution investigates mobile deep learning for on-device data analysis via cross-model compression. The third solution harnesses and coordinates the mobility of citizens for on-demand taxi-hailing via prediction-based task assignment, and has been integrated in a large-scale taxi-calling platform in China.
About the Speaker
Dr. Zimu Zhou is currently a post-doctoral researcher in the Computer Engineering and Networks Lab at ETH Zurich. His research interest lies broadly in sensor, mobile and ubiquitous computing systems. Prior to joining ETH Zurich, he obtained his Ph.D. from the Hong Kong University of Science and Technology in 2015 and B.E. from Tsinghua University in 2011.
