Data Lab News & Events

DL-TXST team participated in Media Eval 2020 FakeNews: Corona virus and 5G conspiracy benchmark. Lexical driven text analysis approach, led by Andrew Magill placed the team in 2nd place for coarse classification and 10th place for finel classification. Congratulations!
Congratulations to Data Lab 2020 Fall graduates, Lia, Andrew, Mirna, and Sebastian!
Dr. Tešić presents Computing with Words in Maritime Piracy and Attack Detections Systems at HCII 2020 Virtual Conference on Human-Computer Interaction.
Dr. Tešić advises Texas State Faculty on pivotal decision making in their career paths.
Data Lab researchers were featured in Texas State University Research Spotlight.
Dr. Jelena Tešić present at Office of Naval Research Meeting.
Dr. Jelena Tešić present at the Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, SPIE vol. 11006, Apr 2019, Baltimore, MD.
Nicholas Warren and Dr. Jelena Tešić present at the IEEE 4th International  Conference on Collaboration and Internet Computing (CIC), Pages 246-255, Oct 2018 Philadelphia, PA.

Data Lab Projects

Graph Network Science

Frustration Cloud Analysis

We expand the psychology of motivation and balance theory to analysis of social network graphs, propose frustration cloud, quantify vertex and edge with relation to the entire graph and apply the approach to social network graphs from online recommendation system, election data, surveys, and health clinical data.

Social Network Analysis at Scale

End-to-end data science pipeline for creation of diverse graphs from social network data, community discovery, topic analysis, and visualization at scale.

Fake News Classification

Fake News Classification using lexical analysis and social network analysis at scale, MediaEDval benchmark participation 2020.

Computer Vision and Deep Learning

Vehicle Activity Recognition

Robust, adaptable, intuitive implementation for automated early activity warning in maritime scenarios (piracy) or smart city setup. We expand computing with words paradigm to augment training data and identify threating activities where lack of training data prohibits the use of deep learning.

Maritime Object Localization and Identification

We expand the recent advances in deep learning to design and train algorithms to localize, identify, track, and re-identify small maritime objects under varying conditions.

Data Lab is interested in collaborating on data science projects for good.
Contact us, we would love to put our algorithms to a good use.

Data Lab Github