Location: L3 Harris Engineering Center - 450.
Abstract: Urban computing is a process of acquisition, integration, and analysis of big and heterogeneous data generated by a diversity of sources in cities to tackle urban challenges, e.g., traffic congestion, energy consumption, infrastructure, security, and air pollution. In this context, we have Connected and Autonomous Vehicles (CAVs) with several sensors producing a huge amount of continuous data stream. This data is required for the traffic congestion detection service to update and discover road segments with low speeds and high vehicle density. The use of cloud computing to support the massive amounts of traffic data received from multiple vehicles significantly increases network traffic. Additionally, this infrastructure can lead to increased response time due to the distance between cloud data centers and final devices. Therefore, we consider using edge computing to detect traffic congestion directly at the edge of the vehicular network. At the edge of the network, it is possible to leverage methods based on sampling and clustering to reduce the traffic data stream transmitted by all vehicles on the network links to the cloud. In the cloud, the framework is used as a macro-control of all vehicle’s geographic positions, acquiring traffic flow data to detect traffic congestion.
Short-Bio: Maycon Peixoto is an associate professor at the Department of Computer Science of the Federal University of Bahia (UFBA). He was a visiting researcher at the University of Waterloo - Canada for a short period while doing his postdoctoral work at the University of Campinas (UNICAMP), Brazil, in 2020. He holds a Ph.D. in Computer Science from the University of Sao Paulo (USP), Brazil, in 2012, and his Master’s Degree in Computer Science from the University of Sao Paulo, in 2008. His main research interests include urban computing, data science, smart grids, vehicular ad hoc networks, performance evaluation, cloud, edge, and fog computing.
Read More