News

Virginia Tech’s virtual university commencement will livestream tonight, Friday, May 14, at 6:15 p.m., and degrees will be conferred at this time.

“We are extremely proud of our graduates who achieved their goals despite more than a year of a pandemic that upended much of their lives,” said Naren Ramakrishnan, the Thomas L. Phillips Professor of Engineering in the Department of Computer Science at Virginia Tech and director of the Sanghani Center for Artificial Intelligence and Data Analytics. “When everything went virtual, they continued to attend classes, meet with their advisors, conduct research, present papers at conferences, and work at internships — all testament to their perseverance and a good barometer of their future success .”

Following is a list of Sanghani Center graduates:

Ph.D.

Prashant Chandrasekar, advised by  Edward Fox, is receiving a Ph.D. in computer science. His research interest lies in digital libraries. The title of his dissertation is “Continuously Extensible Information Systems: Extending the 5S Framework by Integrating UX and Workflows.” Chandrasekar will join the University of Mary Washington as an assistant professor in computer science.

Kaiqun Fu, advised by Chang-Tien Lu, is receiving a Ph.D. in computer science. His research interests lie in spatial data mining, machine learning, and graph neural networks, with a focus on social media analysis in intelligent transportation systems and smart cities. The title of his dissertation is “Spatiotemporal Event Forecasting and Analysis with Ubiquitous Urban Sensors.” Fu will join South Dakota State University as assistant professor in August 2021.

Yen-Cheng Lu, advised by Chang-Tien Lu, is receiving a Ph.D. in computer science. His research interests lie in anomaly detection and probabilistic modeling. The title of his dissertation is “Relational Anomaly Detection: Techniques and Applications.” Lu will be continuing his career as a software engineer at Amazon Alexa AI.

Sneha Mehta, advised by Naren Ramakrishnan, is receiving a Ph.D. in computer science. Her research interests are data mining and deep learning, especially for natural language processing applications. The title of  her dissertation is “New Methods for Event Detection and Extraction from News Articles.” Mehta will join Twitter as a machine learning researcher in July.

Sathappan Muthiah, advised by Naren Ramakrishnan, is receiving a Ph.D. in computer science. His areas of interest include forecasting, machine learning, information retrieval, and topic detection and tracking (TDT). The title of his dissertation is “Design and Maintenance of Event Forecasting Systems”.  Muthiah has joined eBay as an applied researcher.

Reza Sepasdar, advised by Anuj Karpatne, is receiving a simultaneous master’s degree in computer science and Ph.D. in civil engineering. (His master’s co-advisor is Maryam Shakiba). His research interests lie in the intersection of AI and computational mechanics. Sepasdar’s master’s thesis is entitled “A Deep Learning Approach to Predict Full-Field Stress Distribution in Composite Materials.” He will defend his Ph.D. dissertation, “Micro-mechanical Behavior of Fiber-reinforced Composites using Finite Element Simulation and Deep Learning,” this summer.

Sirui Yao, advised by Bert Huang, is receiving a Ph.D. in computer science. Her research interests include machine learning, recommender systems, and fairness. The title of her dissertation is “Evaluating, Understanding, and Mitigating Unfairness in Recommender Systems.” Yao will join Google in June 2021 as a machine learning engineer.

Master’s degree

John Aromando, advised by Edward Fox, is receiving a (coursework only) master’s degree in computer science. His research interests include natural language processing and information retrieval, particularly analyzing design specs written in natural language and synthesizing a machine-understood language via relevant descriptions.

Mohi Beyki, advised by Edward Fox, is receiving a master’s degree in computer science. His research interests are in deep learning, health care, and software engineering. The title of his thesis is “Synthetic Electronic Medical Record Generation using Generative Adversarial Networks.”  Beyki will be joining Google as a software engineer this summer.

Yi-Chun Chang, advised by Chang-Tien Lu, is receiving a master’s degree in computer science. His research interest is in using social media analytics to detect threats. The title of his thesis is “RISECURE: Metro Incidents And Disruptions Detection Using Social Media And Graph Convolution.”  He will join Walmart Global Tech as a software engineer in July.

Po-Han Chen, advised by Chang-Tien Lu, is receiving a master’s degree in computer science. His research focuses on using data from social media to help solve real-world problems. The title of his dissertation is “Metro Security Incidents And Threat Detection Using Social Media.” He will be joining Bloomberg as a software engineer this summer.

Yi Huang, advised by Jia-Bin Huang, is receiving a masters of engineering degree. His research interests lie in computer vision and machine learning. The title of his master’s project is “Cross-Domain Context-aware 3D Hand Pose Estimation.” Huang will join Qualcomm as a computer vision research engineer.

Kulendra Kumar Kaushal, advised by  Naren Ramakrishnan, is receiving a master’s degree in computer science. His research interests lie in the field of natural language processing and information extraction. The title of his thesis is “Information Extraction of Technical Details From Scholarly Articles.” Kaushal will be joining Bloomberg as a software developer.

Prathamesh Kalyan Mandke, advised by Anuj Karpatne, is receiving a masters of engineering degree. His research interests lie in machine learning and computer vision. The title of his master’s project is “Fluorescent Image Reconstruction in Shape Controlled Cell Migration using Deep Learning.”  Mandke will join Qualcomm AI Research as a machine learning software engineer in July.

Ashkan Nazari, advised by Lenwood Heath, is receiving a master’s degree in computer science. His research interests lie in artificial intelligence, deep learning, and cloud-based intelligence systems analysis. Nazari has also worked toward a Ph.D. in mechanical engineering. He will join the Silicon Valley-based luxury electric vehicle start-up Lucid Motors as a senior data scientist, working on developing intelligent battery initiatives.

Ioannis Papakis, co-advised by Anuj Karpatne and Abhijit Sarkar, is receiving a master’s degree in computer science. His research interests lie in machine learning, computer vision, robotics, and signal processing. The title of his thesis is “A Graph Convolutional Neural Network Based Approach for Object Tracking Using Augmented Detections With Optical Flow.”  Papakis also won first place in the 2021 Paul E. Torgersen Graduate Student Research Excellence Awards MS poster presentation category. Starting in July, he will be employed by Bertrandt US, Inc., working at Audi in Santa Clara, California, as an advanced driver-assistance systems engineer.

Arya Shahdi, co-advised by Anuj Karpatne and Bahareh Nojabaei, is receiving a master’s degree in computer science. His research interests lie in forecasting and geospatial modeling and analysis. The title of his thesis is “Physics-guided Machine Learning Approaches for Applications in Geothermal Energy Prediction.” Shahdi is a supply chain data scientist at Lowe’s Companies, Inc. 

Aarohi Sumant, advised by Edward Fox, is receiving a master’s degree in computer science. Her research focuses on deep learning and machine learning application, specifically in natural language processing. The title of her thesis is “Improving Deposition Summarization using Enhanced Generation and Extraction of Entities and Keywords.” Sumant will join Amazon as a software development engineer in July.

Omer Zulfiqar, advised by Chang-Tien Lu, is receiving a master’s degree in computer science. His research interests lie in social media event detection and natural language processing. The title of his thesis is “Detecting Public Transit Service Disruptions Using Social Media Mining and Graph Convolution.” He will join Walmart Labs as a software engineer in June.

About the series: Every complex problem has many multidisciplinary angles. Leveraging expertise and energy, Virginia Tech faculty and students serve humanity by addressing the world’s most difficult problems.

With risk of political and targeted violence on the rise across the United States, national and local leaders are asking Princeton University’s nonpartisan Bridging Divides Initiative (BDI) to provide them with more timely, reliable, and context-specific data on targeted violence events that could help them engage locally and better inform their policy decisions. 

As part of their response to this plea, BDI’s team of Princeton social scientists collaborated with data scientists at the Sanghani Center for Artificial Intelligence and Data Analytics to identify targeted violence events. These often include hate crimes and other incidents that target individuals because of their race, religion, sexual orientation, or other perceived characteristics. Click here to read more about this research.

Protests are an increasingly common occurrence, but only a small percentage of them turn violent. In a collaborative study led by the Discovery Analytics Center with the University of California, San Diego, and George Mason University, a team of researchers set out to uncover triggers that foretell violence by crowds.

Gathering data from thousands of online news sources in five Latin American countries — Argentina, Brazil, Colombia, Paraguay, and Venezuela — the researchers used the characteristics of past events to develop new methods that forecast the occurrence of violent crowd behavior in advance.

“Crowd violence is not generally initiated by one factor but, often, is a culmination of outrage over a stream of preceding unresolved public issues or events,” said Yue Ning, lead author of the study, who was a Ph.D. graduate in computer science from the Discovery Analytics Center at the time of the study and now an assistant professor at Stevens Institute of Technology. “Our study showed that before a violent protest in any of these countries, other protests and strike events, even if peaceful, occurred during the prior week.”

“The fact that violent protest can be modeled before it happens is an important finding of the study,” said David Mares, Institute of the Americas Chair for Inter-American Affairs and professor of political science at the University of California, San Diego. “The link between the act of protesting and violent behavior in a protest has been difficult to understand because so many factors are operating at the same time. Our model gives us confidence that it will be possible to develop a better understanding of the factors that transform peaceful protest into violent confrontations.”

The study was designed to give governments, law enforcement, and community organizations insights that can help them support the right to peaceful gatherings, mitigate the level of frustration and anger that people who have been in many recent protests experience, and reduce the risk of violence.

“Being able to forecast violent events can help policymakers make better decisions about how to deal with protests,” said Naren Ramakrishnan, the Thomas L. Phillips Professor of Engineering in the Department of Computer Science and director of the Discovery Analytics Center. “And understanding triggers is important because any effort to decrease the probability of a violent gathering without understanding the dynamics that differentiate violent from non-violent events can lead to measures that have the opposite effect.”

For example, he said, a significant show of force with police or the military at the first sign of protest can intimidate and frustrate protesters rather than make them feel protected. If such intimidation and frustration build into anger, the likelihood of violence increases during the next such gathering.

Huzefa Rangwala, professor of computer science at George Mason University, said the study also showed that events can be influenced by what is happening in different locations. “One might have thought that people would be most affected by what happens locally, but our data suggests that those protesters prone to violence reflect upon national and not just local experiences when voicing grievances and increasing frustrations that lead to violence.”

In addition to Ning, Mares, Ramakrishnan, and Rangwala, the research team included Sathappan Muthiah, a Ph.D. student in the Discovery Analytics Center majoring in computer science.

Read the full study, “When do Crowds turn Violent? Uncovering Triggers from Media.”

 

 

 

DAC and director, Naren Ramakrishnan, are featured as this month’s Virginia Tech​ Inventors of the Month by the Office of Research and Innovation for work in Early Model Based Event Recognition using Surrogates (EMBERS) software project.

EMBERS is a fully automated system for forecasting significant societal events, such as influenza-like illness case counts, rare disease outbreaks, civil unrest, domestic political crises, and elections, from open source surrogates. To read more about EMBERS click here.

Congratulations to DAC/CS PhD Student Sathappan Muthiah on receiving Deployed Application Award at IAAI (Conference on Innovative Applications of Artificial Intelligence) 2015 for his paper “Planned Protest Modeling in News and Social Media“. The CS department also recognized his work with a Pratt fellowship for Spring 2015 – Congratulations twice!