Events Calendar

ECE Seminar: Understanding Real-World Diffusion Processes: From Epidemics to Violence

Speaker: Dr. Ajitesh Srivastava, Senior Research Associate, Ming Hsieh Department of Computer and Electrical Engineering

Talk Title: Understanding Real-World Diffusion Processes: From Epidemics to Violence

Abstract: The recent outbreak of COVID-19 has encouraged researchers all around the world to identify how their skillsets can be best utilized to contribute to the efforts to deal with the epidemic. Containing the epidemic, providing informed predictions and identifying strategies to restart the economy are essential for the global population to resume their day-to-day life. This may not be the last pandemic we will face, and therefore the research does not end with COVID-19. In fact, the extensive data-collection and monitoring during this epidemic sets the stage for more impactful research in preparedness for future epidemics. Diseases are not the only contagions that fit the above described framework. Violence and drug-abuse are also known to spread through interactions. These issues severely affect the homeless and impede their attempts to safely and successfully exit homelessness and lead a long productive life. California Governor has signed an Executive order this year to assign state resources to reduce homelessness. Modeling how violence and drug-abuse spread among homeless is the key to designing peer-based intervention studies which can assist with these long-term goals.

In this talk, I will discuss utilizing the full potential of Algorithms, Network Science and Data Mining in issues of societal importance, with epidemics and homelessness as examples, and the challenges and opportunities that come with it. By focusing on proper abstractions, we can capture many complexities of the process, and yet come up with a simple model, less prone to overfitting. Doing so can lead to fast and accurate forecasts. For instance, we can train and produce case and death forecasts for more than 3000 counties in under 30 seconds, while still being more accurate than the state-of-the-art methods. Useful modeling informed by sensible assumptions and coupled with optimization approaches can lead to impactful results. For instance, in a Pilot Study at a homeless youth center, we were able to achieve 40% reduction in violence.


Biography: Dr. Ajitesh Srivastava is a Senior Research Associate at Ming Hsieh Department of Computer and Electrical Engineering. He is a member of the Data Science Lab led by Prof. Viktor K. Prasanna. He received his PhD in 2018 from University of Southern California, titled "Computing Cascades: How to Spread Rumors, Win Campaigns, Stop Violence and Predict Epidemics". His research interests include Data Mining, Algorithms, and Network Science applied to epidemics, social good, social networks, architecture, and smart grids. During the COVID-19 pandemic he has been producing weekly forecasts of COVID-19 cases and deaths for the CDC.

Host: Dr. Richard Leahy, leahy@sipi.usc.edu

Webcast: https://usc.zoom.us/j/96802468309?pwd=LzBiWVJCMXI5aUEwM05oTzJXZGQ2QT09

WebCast Link: https://usc.zoom.us/j/96802468309?pwd=LzBiWVJCMXI5aUEwM05oTzJXZGQ2QT09

Audiences: Everyone Is Invited

Contact: Mayumi Thrasher