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