Dr. Jelena Tesic
Associate Professor - Department of Computer Science
Research Areas:
Dr. Tešić's research project spans topics in machine learning and data science for large unstructured imagery, social, health, and sensor data sources. More details on the current projects can be found on https://DataLab12.github.io page.
Background
Jelena Tešić is an Associate Professor in the Department of Computer Science and a founding member and a research lead in the Center for Analytics and Data Science at the Texas State Unviersity in San Marcos, Texas, USA. From 2009 to 2017 Dr. Tešić was a senior research scientist @ Mayachitra Inc. in California. From 2004 to 2009, Dr. Tešić was a Research Staff Member at IBM Watson Research Center in New York. Dr. Tešić received her Ph.D. (2004), M.Sc. (1999) in Electrical and Computer Engineering from University of California Santa Barbara, CA, USA, and Dipl. Ing. (1998) in Electrical Engineering from University of Belgrade, Serbia. Dr. Tešić's research is to develop novel AI methods and scalable algorithms for analyzing large, unstructured multi-modal multi-source data at scale. She holds seven U.S. patents: 12,093,970; 9,710,760; 8,738,695; 8,032,539; 7,958,068; 7,818,329; and 7,707,162. Her research has been sponsored by DoD, DoE, NSF, TxDoT, and the industry. Dr. Tešić is a co-organizer of the 2027 ACM ICMR, and she is an IEEE and NAI senior member. Her articles and patents were cited over 3370 times with h-index of 24 and i10-index of 38, per Google Scholar.
About Faculty Fellows Projects
This research used data science and machine learning to understand short and long-term resilience in Texas public schools during the COVID-19 pandemic. The study included an interactive data dashboard that featured distinct data storylines for each school district, highlighting the most prominent resilience predictors to improve learning recovery. Findings from this research can inform data-driven decision making and strategic planning to assist policymakers in identifying interventions that will improve learning resilience.
Research Impact Highlights
Users can view indicator data at the county and district levels to understand the most impactful factors on learning loss in Texas school districts as a result of the COVID-19 pandemic. These data provide insight into avenues for learning recovery in Texas schools.
Data Science Insights
Using machine learning to better understand resilience trends and outcomes.
Local Data Access
Explore indicator data at county and district levels for informed decisions.
Impactful Metrics
Identify the factors that matter most through accessible data tools.
Featured Media
Learning Loss Recovery After COVID-19 Pandemic in Texas Public Schools.