Virginia Tech®home

Data Analytics, Information Retrieval, Machine Learning, and Natural Language Processing

The Sanghani Center for Artificial Intelligence and Data Analytics aspires to be a leading program in the nation when it comes to executing big data projects. Using its expertise in machine learning and artificial intelligence – with a team spanning computer science, statistics, electrical and computer engineering, and mathematics – the center is working with dozens of global companies and federal agencies on projects with worldwide implications. Our work emphasizes not just the algorithmic aspects of converting data  to knowledge but also the importance of human-in-the-loop analytics to arrive at insights. 

The center performs research in many areas of artificial intelligence, machine learning, and data analytics including natural language processing, computer vision, spatial and temporal analytics, network analysis, information retrieval, visual analytics, explainability, fairness/trust, human-in-the-loop, and science-guided machine learning. The Sanghani Center has been a pioneer in harnessing information from public sources, like news and social media to predict major social events and patterns.

Student Accomplishments and Projects

Yali Bian, Ph.D. student advised by Chris North
Examine how deep learning (DL) representations, in contrast to traditional engineered features, can support semantic interaction (SI) in visual analytics. 

Debanjan Datta, Ph.D. student advised by Naren Ramakrishnan
Part of a team with research associates Brian Mayer and Nathan Self at the Sanghani Center working with Princeton University’s nonpartisan Bridging Divides Initiative (BDI) to provide more timely, reliable, and context-specific data on targeted violence events that could help leaders engage locally and better inform their policy decisions. 

Kylie Davidson, Ph.D. student advised by Chris North
Immersive Space to Think (IST) builds on prior work on "space to think" and "semantic interaction" with large 2D displays for sensemaking. 

Bill Ingram, Ph.D. in computer science, advised by Edward Fox
Aim of the project – sponsored by the U.S. Institute of Museum and Library Services -- is to bring computational access to book-length documents, specifically electronic theses and dissertations (ETDs). 

Nikhil Muralidhar, Ph.D. student advised by Naren RamakrishnanAlso a Part of the DeepOutbreak team that took first place in the COVID-19 Symptom Data Challenge and second place in the COVID-19 Grand Challenge.

Makanjuola Ogunleye, Ph.D. student advised by Ismini Lourentzou
Research is on multi-agent reinforcement learning, in particular, multi-agent emergent communication, i.e., how agents learn to communicate towards accomplishing a task by passing messages to each other.

Anika Tabassum, Ph.D. student advised by B. Aditya Prakash
Research includes developing an explainable model for actionable insights in multivariate time-series. 

Muntasir Wahed, Ph.D. student advised by Ismini Lourentzou
Research focus is on self-supervised learning, adversarial training and out-of-distribution detection. 

Research Faculty

Adjunct Professor