My research interests are in applications of artificial intelligence and machine learning. I apply techniques from these fields to problems in, most recently, homelessness and transportation.


Digital Homelessness Initiative

The Digital Homelessness InitiativeOpens in new window studies the use of technology to provide tele-services to residents in supportive housing. This work is supported by a grant from the National Science Foundation: SCC-IRG Track 2: Designing and testing remote services to support formerly homeless persons in permanent housingOpens in new window .

Understanding Food Waste Behavior from Social Media

The project aims to identify when actions related to food waste are reported on social media networks and to respond in ways that can change food waste behavior. The project applies text analysis methods to analyze messages and automatically generate responses. The work is supported by a grant from USDA's National Institute of Food and AgricultureOpens in new window . The grant enables a semester-long training program for students in the use of text processing techniques for sustainability applications. Participants in this program do not need prior computer programming experience.

Analyzing Social Media Communications for Correlation with Vehicular Traffic

Recent studies have identified a correlation between social media activity and traffic patterns in some urban areas. Interestingly, social media communication volume leads road traffic. This project computes correlations between the number of messages on Twitter and freeway traffic volume in southern California with an aim to improve the accuracy of traffic forecasts. This work was supported with grants from University of California Center on Economic Competitiveness in Transportation (UC CONNECT)Opens in new window .


Previous work

I was a Senior Research Associate at USC's Ming-Hsieh Department of Electrical Engineering where I jointly supervised the Big Data Analytics group with Viktor Prasanna. The group addressed the challenge of rapidly analyzing large heterogeneous data sources. The work was supported by the USC-Chevron Center for Interactive Smart Oilfield Technologies.

I was a Research Specialist at the Saban Research Institute of the Children's Hospital Los Angeles from 2004 to 2012 and a post-doctoral affiliate at NASA's Jet Propulsion Laboratory. During this time, I worked on resource optimization in embedded sensor networks (including body sensor networks).

I was a post-doctoral researcher at the Robotics Research Lab of Maja Mataric and Gaurav Sukhatme. While there, I worked on modeling human activity recorded using laser range-finders.

I worked with Prof. Adnan Darwiche at the UCLA Computer Science Department on embedding reasoning algorithms based on efficient representations of propositional logic into a Sony Aibo robot.

My Ph.D. dissertation work under Michael G. Dyer. demonstrated how agents built with a connectionist architecture could construct arbitrary physical structures in a simulated environment.