02/16/2022
By Sokny Long

The Francis College of Engineering, Department of Electrical & Computer Engineering, invites you to attend a doctoral proposal defense by Varun Garg on "Spatio-temporal Analytics Using Spurious Observations Generated by Participatory Sensing."

Ph.D. Candidate: Varun Garg
Defense Date: Thursday, March 3, 2022
Time: 3 to 5 p.m.
Location: This will be a virtual defense via Zoom. Those interested in attending should contact Varun_garg@student.uml.edu or committee advisor Thanuka_Wickramarathne@uml.edu at least 24 hours prior to the defense to request access to the meeting.

Committee Chair (Advisor): Thanuka Wickramarathne, Assistant Professor, Dept. Electrical and Computer Engineering, UMass Lowell

Committee Members:

  • Yan Lou, Professor, Dept. Electrical and Computer Engineering, UMass Lowell
  • Vinod Vokkarane, Professor, Dept. Electrical and Computer Engineering, UMass Lowell
  • Peter Bauer, Professor, Dept. Electrical Engineering, University of Notre Dame

Brief Abstract:

With the proliferation of the Internet of things, the availability of sensors has increased exponentially. Omni-present ubiquitous sensors can be utilized to participate in secondary sensing tasks. This presents opportunities to enhance the awareness of systems to understand different real-world situations. The enhanced awareness will help solve many applications in intelligent transportation systems, civil infrastructure management, and urban surveillance. The computational capability of the devices (e.g., smartphones, vehicles, roadside units) enables the development of systems for analyzing different Spatio-temporal phenomena. The developed systems can detect and predict the `targets' of interest. Our work focuses on developing data fusion and machine learning based methods for analyzing different Spatio-temporal phenomena using observations collected by ubiquitous sensors.

In particular, we develop novel methods for processing ubiquitous data streams for robust detection and prediction of the `targets' of interest, such as road conditions and other potential threats. We utilize the data from multiple sensors and systematically aggregate them to improve overall performance. The developed methods work towards circumventing the challenges posed by measurement noise, mobility of sensors, and differences among sensors.

All interested students and faculty members are invited to attend the online defense via remote access.