The Sanghani Center is home to high-profile research, garnering recognition within and beyond the data analytics community.
Our talented team has been recognized with many competitive research awards and featured in major news and media outlets such as the Wall Street Journal, Newsweek, the Boston Globe and the Chronicle of Higher Education.
Mehul Sanghani, chief executive officer and founder of Octo, will deliver the keynote address at Virginia Tech’s University Commencement ceremony on Friday, May 10.
Octo is a technology firm focused on solving national security’s most complex problems. In the last decade, Sanghani built and grew the company around the foundational belief of meeting, exceeding, and advancing customer missions.
Sanghani took a leap of faith founding Octo at the age of 30 with encouragement from his family and others. Since its inception in 2006, the company has experienced exponential success under his leadership.
Octo has been repeatedly recognized, catching the attention of a number of Fortune 100 companies as an acquisition target. In January 2023, IBM announced it was acquiring the company for just under $1.3 billion.
In 2021, a gift from Mehul and his wife, Hema Sanghani, also a Virginia Tech graduate, made a historic $10 million gift to their alma mater; $1.5 million of the gift was allocated to establish The Market of Virginia Tech, a first-of-its-kind on-campus food pantry to students facing food insecurity.
The Sanghanis’ gift also endowed the Sanghani Center for Artificial Intelligence and Data Analytics. Read full story here.
Graphic is the poster “Distributionally Ambiguous Multistage Stochastic Integer and Disjunctive Programs: Applications to Sequential Two-player Interdiction Games,” presented at the INFORMS Annual Meeting 2023.
Ph.D. student Sumin Kang was drawn to the Department of Industrial Systems Engineering by its prestigious faculty with particular expertise in optimization for logistics problems with uncertainty.
“As a logistics enthusiast, I found their focus aligned very well with my own interests,” said Kang, who is advised by Manish Bansal, core faculty at the Sanghani Center. “And the interdisciplinary environment fostering a multi-faceted approach in problem solving at the Sanghani Center added to Virginia Tech’s appeal.”
Kang’s research interests lie in optimization under uncertainty, with a focus on network optimization problems and vulnerability analysis.
“Specifically I am interested in optimization problems with incomplete information about distributions of uncertain parameters,” he said. “These optimization problems find an application in the network interdiction problem. The network interdiction problem involves a game between two players, the interdictor and the network user, where the network user aims to minimize the objective value like traveling cost and security threat level, while the interdictor aims to maximize disruption of network.
“Solving this problem is valuable for identifying network vulnerabilities, particularly in cases of unexpected disruptions,” said Kang. “My proposed solution approaches consider the interdictor’s varying risk appetite towards unknown distributions.”
Kang’s interest in this research began as a master’s degree student in logistics at Korea Aerospace University, when he started to struggle with logistic optimization problems, he said, because despite the prevalence of real-world uncertainty, the literature mainly focused on deterministic cases due to their high complexity. This motivated him to address the gap and contribute to the domain of optimization with uncertainty for large-scale problems.
(From left) Chang Lu, the Fred W. Bull Professor of Chemical Engineering; Daphne Yao, professor of computer science; and Xiaoting Jia, associate professor in the Bradley Department of Electrical and Computer Engineering. Photo by Peter Means for Virginia Tech.
An estimated one in six people suffer from a brain disorder worldwide, according to the American Brain Foundation. Current research has provided some insight into cell-communication inside the brain, but there are still a lot of unknowns surrounding how this crucial organ functions. What if there was a comprehensive map that took into consideration not just the biology of the brain, but the specific location where the biology occurs?
Researchers in the College of Engineering have developed a powerful, cost-effective method to do just that.
Chang Lu, the Fred W. Bull Professor of Chemical Engineering, has been leading a research project that could be groundbreaking for brain research. The newly published article in the journal Cell Reports Methods features interdisciplinary research along with faculty in two additional departments within the College of Engineering:
Poster presentation at CV4Animals: Computer Vision for Animal Behavior Tracking and Modeling workshop during the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CPVR)
Medha Sawhney earned a bachelor’s degree from the Manipal Institute of Technology in India, where she majored in electronics and communications engineering, with a minor in data science. When considering a graduate degree in computer science, Sawhney was drawn to Virginia Tech and the Sanghani Center by a research-focused environment that offered opportunities to learn from and work with professors well known in their respective fields of research which interconnected well with her own.
“A research-focused environment makes it easy to concentrate on your work by providing interesting and challenging research projects; professors who guide you in every way; and funding opportunities via grants from organizations like the National Science Foundation,” she said. “And most professors – even if they are not your direct advisor — are extremely approachable to guide you or discuss problems.”
Sawhney entered the university as a master’s degree student but is now pursuing a Ph.D. She is advised by Anuj Karpatne.
Having worked in the domain of computer vision since her undergraduate years, Sawhney’s current research is at the intersection of computer vision and mechanobiology.
Two projects — supported by the NSF — predict the behavior and mechanics of human as well as bacteria cells. One of them involves predicting the force exerted by cells in order to be able to predict their movement using traction-force microscopy images collected in the field of mechanobiology.
“The physics knowledge that we are integrating in our machine learning methods includes phenomenological models of cell and bacteria migration and knowledge of the mechanical forces governing interactions between cells and fiber backgrounds,” she said.
The second project involves tracking the movement of bacteria cells to predict and also study the characteristics of their motion such as their velocity, their stickiness, and other such measures. This study is directed towards cancer research.
“The resolution of microscopy and the dense fibrous environment the bacteria is in makes it challenging to differentiate the bacteria in an image by just looking at it since the bacteria sometimes merges with the 3D media or goes inside,” she said. “We use artificially-generated motion and temporal features of the microscopic bacteria images as input to the machine learning model to be able to identify and track them.”
Sawhney gave a poster presentation of her work, “Detecting and Tracking Hard-to-Detect Bacteria in Dense Porous Backgrounds,” at a CV4Animals: Computer Vision for Animal Behavior Tracking and Modeling workshop during the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CPVR) last fall.
This was preliminary work for the paper, “MEMTrack: A deep learning-based approach to microrobot tracking in dense and low-contrast environments,” which will be published in an upcoming volume of the Advanced Intelligent Systems journal.
Sawhney will also be presenting her work on bacteria tracking at the first Workshop on Imageomics during the Association for the Advancement of Artificial Intelligence (AAAI 24) conference next week.
She is also serving on the program committee for the workshop.
Projected to graduate in 2026, her ideal job would be one that offers challenges and in which her work would have an impact on society.
The Cloud-based Distributed Radio Frequency Machine Learning project team members at work. Photo by Isabella Rossi for Virginia Tech.
A student-led research team is working with Amazon to advance use cases for machine learning within the cloud for wireless communication applications.
The Virginia Tech National Security Institute is collaborating with Amazon Web Services (AWS) to give 11 undergraduate students and a graduate research assistant experience deploying state-of-the-art machine learning algorithms in the cloud for distributed radio frequency spectrum sensing through the Emerging Technology Research Fellowship. The fellowship aims to improve the performance of radio frequency spectrum sensing algorithms by leveraging multiple sensors collaborating through the cloud.
Graphic is from the paper “Comparative analysis of alternative powertrain technologies in freight trains: A numerical examination towards sustainable rail transport”
Ahmed Aredah’s graduate school experience is not a typical one as he is simultaneously pursuing two graduate degrees in different majors. He is a master’s degree student in the Department of Computer Science advised by Hoda Eldardiry, assistant professor and core faculty at the Sanghani Center, and is also a Ph.D. student in the Bradley Department of Electrical and Computer Engineering, advised by Hesham Rakha with Eldardiry serving on his dissertation committee.
“The multidisciplinary approach at the Sanghani Center aligns perfectly with my dual-degree aspirations, allowing me to bridge the gap between civil engineering and computer science,” Aredah said. “Advanced research facilities and extensive networking opportunities have further enriched my academic experience.”
His research area is centered on energy optimization in transportation. He is part of a team at the Virginia Tech Transportation Institute that developed NeTrainSim, a network train simulator that explores ways to make train operations more energy efficient.
“A significant contribution from our work has been the study and proposal of different powertrain technologies to enhance train infrastructure in the United States. Thanks to the robust methodology we have employed, our findings can be expanded to other regions/countries,” Aredah said.
His interest in energy optimization for railway systems was sparked by a combination of factors. “The real-world impact of creating more efficient, sustainable transport solutions resonated with my desire for meaningful work,” Aredah said. “And the interdisciplinary nature of the field offers a unique technical challenge that appealed to my problem-solving instincts.”
Aredah earned a bachelor’s degree and a master’s degree in civil engineering from German University in Cairo, Egypt, and nanodegrees in data science and machine learning from Udacity.
After graduating with his Ph.D. (currently projected for 2025), Aredah said that he is open to exploring any opportunity that allows him to leverage his skills.
“At my core, I am a problem solver, passionate about applying my knowledge to real-world challenges. Whether that means continuing research to push the boundaries of what’s possible or working in an industrial setting to implement practical solutions, I am eager to find a role where I can make a meaningful impact,” he said.
(From left) Chang-Tien “C.T.” Lu, Naren Ramakrishnan, and Dimitrios Nikolopoulos. Photo illustration by Peter Means for Virginia Tech.
Chang-Tien “C.T.” Lu, Dimitrios Nikolopoulos, and Naren Ramakrishnan, all faculty in the Department of Computer Science, have been elected to the 2024 class of fellows in the Institute of Electrical and Electronics Engineers (IEEE).
To be named a fellow, IEEE members must demonstrate significant contributions to their field, show evidence of technical accomplishments and realization of significant impact to society, and a record of service to professional engineering societies, among other criteria.
Fewer than 0.1 percent of voting members in the institute are selected annually for this career milestone, according to IEEE.
A recent project from the Virginia Tech Transportation Institute provides new insights to the impact of freight trains using alternative fuel sources. Virginia Tech photo
Researchers at the Virginia Tech Transportation Institute recently created the nationwide multi-train simulation software, NeTrainSim, to show the impacts of a countrywide shift away from diesel.
A U.S. map shows counties where residents could (blue) or could not (pink) receive local-specific information about environmental justice issues. Photo courtesy of Junghwan Kim.
Virginia Tech researchers have discovered limitations in ChatGPT’s capacity to provide location-specific information about environmental justice issues. Their findings, published in the journal Telematics and Informatics, suggest the potential for geographic biases existing in current generative artificial intelligence (AI) models.
