Inquiring Minds

George �鶹��Ƶ partners with DoD agency to bring closure to the families of lost U.S. service members

Shayla Brown — Mon, 28 Jul 2025 17:39:16 +0000

George �鶹��Ƶ partners with DoD agency to bring closure to the families of lost U.S. service members  Shayla Brown Mon, 07/28/2025 - 13:39

There are currently more than 80,000 unaccounted-for service members from World War II, the Korean War, the Vietnam War, the Cold War, the Persian Gulf War, and other conflicts. �鶹��Ƶ’s ongoing collaboration with the Department of Defense POW/MIA Accounting Agency (DPAA) is exploring new ways of locating the missing remains of those American service members and bringing closure to their families. 

This partnership, which began December 2020, is finding success, and deeper meaning, as it extends beyond the classroom to the grieving families of prisoners of war (POWs) and missing soldiers, and it showcases George �鶹��Ƶ’s commitment to being a veteran-serving institution.   

John C. Winters, MA History ’13, is a DPAA postdoctoral research fellow at George �鶹��Ƶ’s Roy Rosenzweig Center for History and New Media (RRCHNM) in the College of Humanities and Social Sciences (CHSS) whose research includes war, diplomacy, and the 19th and 20th centuries. 

John C. Winters. Photo provided.

“I’ve previously worked on cemetery projects, and my responsibilities were to essentially help not only map the cemetery as it stood, but to identify places where people were not cataloged properly, or were forgotten over time,” said Winters, who has been a fellow at the center since January 2025.  

Winters is also working with the Henry Jackson Foundation for the Advancement of Military Medicine with the goal of supporting and expanding a wide range of DPAA operations, from initial case development to field mission planning. 

“The advantage of conducting research at the Center for History and New Media is that the people there are experts in using intricate digital mapping tools. It's really wonderful to see that faculty, as well as graduate students, are so comfortable using these tools to make their research accessible,” said Winters. 

Digital mapping is a critical tool for the agency’s mission as it helps researchers visualize where someone was lost and supports investigation and excavation proposals.   

George �鶹��Ƶ has access to ArcGIS Pro, the mapping program that Winters is currently using to track missing or unidentified soldiers.  

“ArcGIS is a really dynamic program. There are a lot of facets to it including a base-level digital cemetery mapping, and the ability to create informational and visually engaging maps. They're accurate and concise, and they deliver all the information at a glance,” said Winters, who earned his PhD in history from the City University of New York in 2020. 

Jesse Stephen, chief of innovation at Defense POW/MIA accounting agency, said their mission has two goals: to search for, locate, recover, and identify missing-in-action personnel, and to communicate. 

Jesse Stephen. Photo provided.

“These projects are multidimensional and address active casework. They also tell the story of a conflict and of our missing individuals,” said Stephen. “That involves going back into archives and looking for information about a particular case or campaign. It's organizing, reviewing, and analyzing that information we find, and then putting all these different pieces together to build a case.”  

Over the course of the partnership, DPAA has learned more about more than 3,000 unaccounted-for losses. George �鶹��Ƶ Fellows have reviewed more than 1,000 deceased personnel files of people who served alongside the unaccounted-for. 

Throughout the process, DPAA staff, Service Casualty Offices, and family members meet and review the specifics of a loss. Documentation, including maps, is shared with family members, who can see where the last-known sighting of their loved one happened. 

The partnership also employs George �鶹��Ƶ students as interns and to date has given nine interns real-world experience in managing data, giving presentations, and project management. Beyond service to students, research partner fellows are encouraged to give presentations at museums and other venues on the mission and how unaccounted-for are found.  

“These were people who gave their lives while fighting to protect democracy, so I see the important work I’m doing at George �鶹��Ƶ as a public service and it’s relevant to a very large body of veterans in the Northern Virginia area,” said Winters. 

Currently, more than 150 Virginian service members are unaccounted for. 

Discover the Roy Rosenzweig Center for History and New Media

When the mosquitos bite, the Biomedical Research Lab bites back

Sarah Holland — Thu, 03 Jul 2025 19:45:51 +0000

When the mosquitos bite, the Biomedical Research Lab bites back Sarah Holland Thu, 07/03/2025 - 15:45

It’s summer, and with those longer days come backyard cookouts, outdoor activities and—ouch!—bug bites. Mosquitoes love Northern Virginia’s infamous hot and humid summers. And as the world’s deadliest animal, according to the Centers for Disease Control and Prevention, they’re more than just a nuisance at the family barbeque: They’re a health hazard.

Farhang Alem. Photo by Creative Services

But in partnership with Prince William County, �鶹��Ƶ’s Biomedical Research Laboratory (BRL) is working to prevent outbreaks of mosquito-borne diseases.

Since 2016, in response to the Zika virus outbreak, the county and the university partner each year to collect mosquito samples and test them for diseases like West Nile virus.

“West Nile is endemic in the United States, and infections can be lethal,” explained Farhang Alem, MS Biology ’15, PhD Biosciences ’19 , associate director of the BRL. Alem has led the mosquito testing program since 2019.

“Eighty percent of people will have no symptoms,” he said, “but about one in every 150 cases of West Nile is severe.” It’s a neuroinvasive disease, meaning severe cases can damage the nervous system, resulting in high mortality rates and a high likelihood of disability if survived. Even those with non-neuroinvasive West Nile virus, though most likely to make a full recovery, could experience symptoms for weeks or months.

“We want to prevent the spread as much as possible,” Alem said.

Testing season starts in late spring and runs through the fall. Each week, samples are collected at more than 60 sites across Prince William County, and the mosquitoes are sorted by species. Vector species—meaning those that carry disease—are sent to the BRL for testing. Researchers extract RNA from the mosquitos and check for the markers of West Nile virus. They then send their report to county officials. If mosquitoes are positive for West Nile virus, the county will follow their larvicide and adulticide spraying protocols to eliminate the threat at the site where the mosquitoes were trapped.

“It allows us to more precisely target areas before they become a concern for the local community,” said Eli Hosen, environmental project manager for the mosquito and forest pest management branch of Prince William County Department of Public Works. “The lab provides us with a quick turnaround so we can respond as soon as possible.”

The program has been effective, Alem said, in reducing the number of West Nile carriers in the region. "Spraying is definitely working to control the spread."

Alem is in conversation with other counties in Northern Virginia to see if there’s interest in expanding the surveillance program. The BRL is also hoping to learn best practices on mosquito trapping from Prince William County to implement in other areas of research.

George �鶹��Ƶ epidemiologist Amira Roess is looking into the possibility of a similar surveillance program in India for dengue fever, for example. And if deployed, researchers hope what they learn in India can be useful to their research here as well.

With almost 10 years’ worth of data from the ongoing testing, Alem is hoping the lab can one day look at trends in disease occurrence and correlating environmental factors.

“It's leading to new avenues of research for us,” said Alem.

Learn more about the Biomedical Research Lab

In This Story

Amira Roess, PhD, MPH

Virtual reality adds empathy to dementia care

Mary Cunningham — Fri, 06 Jun 2025 14:52:46 +0000

Virtual reality adds empathy to dementia care Mary Cunningham Fri, 06/06/2025 - 10:52

At a conference on aging two years ago, Li-Mei Chen slipped on a pair of virtual reality (VR) goggles and found herself inside the mind of a person with dementia.

The simulation cast her as an older adult in the grips of delusion: frozen in fear at the end of a hallway, watching the floor disappear beneath rising water. “There was no actual flooding,” Chen recalled, “but I could feel the panic.”

Assistant Professor Li-Mei Chen partnered with fellow social work professor Megumi Inoue to launch a pilot to train certified nursing assistants through virtual reality. Photo provided.

Chen, an assistant professor of social work in the College of Public Health at �鶹��Ƶ, specializes in aging and dementia and immediately recognized the technology’s potential for nursing home staff. She imagined caregivers seeing what she saw and walking away with a new kind of understanding and empathy for their dementia patients.

Working with Japanese company Jolly Good Inc. to adapt their VR technology, Chen launched a pilot this spring to train certified nursing assistants (CNAs) at a Northern Virginia nursing home. The three-part program combined immersive VR scenarios with online lessons and group discussions.

Wearing headsets, participants stepped into the disoriented minds of dementia patients—experiencing the confusion, fear, and memory lapses firsthand. In one scene, a woman lies in bed, panicked. She recognizes her pajamas but not the room surrounding her, and wonders aloud, “Where is my husband?”

Chen partnered with fellow social work professor Megumi Inoue to design the educational framework. The VR footage, originally produced in Japan, was updated for English-speaking users through artificial intelligence (AI)-generated voiceovers.

Support for an unsung profession

Beyond improving patient care, the project aims to support caregivers working in a field plagued by high turnover, low wages, and minimal if any formal training. In the United States, nursing homes face an estimated 53% annual turnover rate and ongoing recruitment struggles, even as demand for direct care remains high.

Though they perform some of the toughest jobs in health care, Chen said, nursing home staff are often treated as disposable. “There’s little investment in CNAs, because it’s assumed they’ll just leave—but if nursing homes invested, that would change.”

Eventually, Chen hopes to help create new VR scenes set in American care settings and filmed in English. But even with cultural differences, CNAs in the Northern Virginia pilot—many of whom spoke English as a second language—found the material relatable.

Wearing headsets, participants stepped into the disoriented minds of dementia patients—experiencing the confusion, fear, and memory lapses of dementia firsthand. Photo provided.

“They said, ‘We have seen this. We’ve experienced this scenario in here,’” said Zeynep Senturk Mannix, a George �鶹��Ƶ Master of Social Work student who helped Chen facilitate the sessions. “They didn’t even register that the actors were Japanese.”

For many of the CNAs in the program, the experience marked their first exposure to any dementia-specific training. Mannix suggested that the sessions provided a sense of validation. “Their ideas were valuable, and they were able to help shape the future of this study.”

Chen and her team are now analyzing feedback, with plans to present their findings at the American Public Health Association conference in November. They’re also working to refine the VR content and training materials, in hopes of expanding the program in the future to additional care facilities.

Chen sees VR not as a silver bullet, but one tool to support more thoughtful training. Her framework rests upon relationship-centered care, which prioritizes empathy, trust, and human connection.

“It’s about understanding the person, and building a connection that’s beyond client and provider,” she said.

Chen’s project is supported by two grants:

• George �鶹��Ƶ College of Public Health Pilot Award (2025-2026): Relationship-Centered Care for Formal and Informal Caregivers of Persons Living with Dementia: VR and Multi-modal Approaches.

• Geriatric Training and Education (GTE) Initiative at the Virginia Center of Aging (2024-2025): Immersive Training: Enhancing Relationship-Centered Care in Nursing Homes through VR

Learn about more research at George �鶹��Ƶ

In This Story

Li-Mei Chen, PhD

Megumi Inoue, PhD

George �鶹��Ƶ researchers look at low-cost solutions to increase solved cases and boost public trust in police

Katarina Benson — Thu, 05 Jun 2025 19:04:38 +0000

George �鶹��Ƶ researchers look at low-cost solutions to increase solved cases and boost public trust in police Katarina Benson Thu, 06/05/2025 - 15:04

It’s a sought-after “sweet spot,” where effective police response to combatting nonviolent crimes earns public approval and builds community goodwill—all within tight budget constraints.

Cynthia Lum. Photo by Office of University Branding

Reaching that intersection is no easy task. That’s why �鶹��Ƶ researchers Cynthia Lum and Christopher Koper are testing solutions to help local police departments balance limited resources while strengthening public trust.

Lum, director of the Center for Evidence-Based Crime Policy (CEBCP) within the Department of Criminology, Law and Society in George �鶹��Ƶ’s College of Humanities and Social Sciences, and Koper, a nationally recognized expert on firearms policy and policing and CEBCP’s Principal Fellow, are leading a new initiative supported by an $839,000 grant from Arnold Ventures. The Washington, D.C.-based nonprofit supports evidence-based policy, research, and advocacy to address systemic challenges where traditional approaches have fallen short, funding initiatives that aim to drive long-term, bipartisan reform.

The project emphasizes practical scalable steps police departments can take, especially when it comes to serious property crime cases, such as burglaries and auto thefts, which sometimes get low priority due to lack of investigative leads, high caseloads, and limited police resources.

“We are testing whether low-cost actions will help victim satisfaction and will possibly help police solve more crimes,” said Lum, a former Baltimore police officer. “If this works, then I think many police agencies across the country, especially those who don’t have a lot of resources, but who want to try to do something, will have an accessible approach that can lead to real improvements.”

Most crimes in the United States go unsolved. Violent crimes have higher rates of clearance, with homicide cases ranking highest at 58%. Nonviolent crimes—which are much greater in number—are solved at much lower rates, frustrating many victims and eroding trust in law enforcement.

Christopher Koper. Photo by Evan Cantwell/Office of University Branding

To address that, the agencies participating in the George �鶹��Ƶ three-year pilot will send officers to personally follow-up on stalled, low-priority cases that would not normally receive extensive investigation. If this uncovers potential new leads, it may increase the likelihood of solving these cases. Further, by demonstrating continued engagement, it is hoped that the follow-ups will improve victim satisfaction with police services and boost community views of the police. Lum and Koper will be measuring both outcomes.

“At the minimum, it gets officers back into the community, visibly showing their commitment to solving crimes and positively engaging with people,” Lum said, adding that this project will provide graduate students on the research team opportunity to learn how to carry out program evaluations and field experiments.

Lum and Koper are currently partnering with two police departments, one in Northern Virginia and the other in Maryland. While setting up logistics, such as data sharing and officer training, they are both optimistic about the possibilities.

“We’re trying to move the needle with a modest, low-cost change to investigative procedures,” Koper said. “That additional follow-up by an officer could make a difference.”

Should their research prove effective, they plan to disseminate the model and findings to law enforcement agencies nationwide.

“I think of it as helping police agencies balance the realities they face,” Koper said. “They want to solve more cases and earn a higher level of public confidence and trust. But they also face limits on how intensively they can investigate all cases.”

Study Criminology, Law and Society at George �鶹��Ƶ

Trial by virtual fire: Augmented reality project tailors training for firefighters

Sarah Holland — Thu, 22 May 2025 17:18:32 +0000

Trial by virtual fire: Augmented reality project tailors training for firefighters Sarah Holland Thu, 05/22/2025 - 13:18

For firefighters, even training is a risk. According to the United States Fire Administration, 16.6% of all firefighter fatalities in 2024 took place during training exercises. �鶹��Ƶ researcher Craig Yu is hoping to change that statistic.

Yu, associate professor of computer science, has been developing augmented and virtual reality training for most of his career, and he has a particular interest in exploring how artificial intelligence (AI) and emerging technologies could help research on human development and sports science. Through National Science Foundation’s EArly-concept Grants for Exploratory Research (EAGER) program, Yu and Joel Martin, associate professor of kinesiology, are developing just that: an augmented reality program that could help train firefighters while minimizing risk.

“Firefighters have high rates of injuries and many injuries happen during training. There is a need for training technology that can replicate aspects of emergencies while minimizing the injury risk and physical burn,” said Martin. Martin has spent the past few years working with Fairfax County Fire and Rescue to determine how they can reduce physical strain to firefighters during training exercises. “I think that technology such as immersive reality training can help to meet training needs while minimizing the physical risks of performing certain drills."

A prototype of the virtual training space from their proposal. Image provided.

Augmented—or mixed—reality uses devices such as phones or a headset to overlay 3D computer-generated content onto the real world. An increasingly accessible tool, you can find augmented reality in applications like Ikea furniture previews in your house, dinosaur encounters in the Smithsonian, and catching Pokémon in your neighborhood.

As described in their project proposal, “Adapting Mixed Reality Training Programs to Real-World Scenes to Enhance Human-AI Teaming in Emergency Responses,” the new training would utilize augmented reality to create realistic training scenarios for firefighters.

Based on a 3D digital twin of the room, the program will use AI to analyze what's in the room and create a realistic outbreak of fire: where it is most likely to start and spread, and where civilians are most likely to be.

“The program understands the environment, and it will be refined with additional input from professional firefighters,” said Yu.

Yu also notes that the scenario can be adapted for different experience levels. Simpler scenarios can be developed for new firefighters, which can then be adjusted for increasing sophistication and complexity as the trainees learn and improve. It also allows them to practice scenarios that would be difficult or impossible to replicate in a live burn, such as how to best evacuate and rescue civilians.

Most importantly, it prevents firefighters from being exposed to hazardous conditions while in training.

“I don’t ever see us replacing real fire training,” said Yu, “but this is a means to augment the training to improve the health and safety of the firefighters, as well as make training easier to deploy in a variety of buildings and circumstances. AI allows us to rapidly analyze human performance and then adaptively synthesize training programs to address weakness we observe.”

Martin and Yu are in the early phases of development but hope to deploy their initial training designs with Fairfax County Fire and Rescue soon. They both have hopes for further incorporation of AI and augmented reality technology in firefighting tools, such as headsets that can scan the environment and offer real-time feedback about potential dangers, exit strategies, and health metrics as firefighters enter hazardous zones.

“More and more virtual and immersive reality training is being used [in kinesiology],” said Martin. “I think this project demonstrates the importance of collaboration and interdisciplinary teams to solve challenges in the field.”

Discover how George �鶹��Ƶ is driving AI

In This Story

Lap-Fai (Craig) Yu

Engineering professors develop human-AI colorization tool for cartoonists

Shayla Brown — Mon, 03 Mar 2025 17:28:34 +0000

Engineering professors develop human-AI colorization tool for cartoonists Shayla Brown Mon, 03/03/2025 - 12:28

�鶹��Ƶ professor Sungsoo Ray Hong has always been a huge fan of cartoons, comics, and animations. By combining his passion with his research area of human-computer interaction, he has created a new tool for cartoonists, ShadowMagic.

Hong, his colleague Yotam Gingold, and their PhD students published a paper, “ShadowMagic: Designing Human-AI Collaborative Support for Comic Professionals’ Shadowing,” elucidating the need for the tool, which aims to boost product quality and designer productivity through study-informed human-AI interaction.

The team worked with professional cartoonists to find common workflow of colorization that is shared within the industry as a reference point for their research, which examines the evolution of designing technology as cartoonists transitioned from using PCs in the 1980s to artificial intelligence, said Hong, who is an assistant professor at the Department of Information Sciences and Technology.

Creating a comic book is a team effort as there are many roles throughout the process including story drafting, sketching, colorizing, editing, and sending to a production company, said Hong.

“Professional cartoonists are sometimes producing content every other day,” said Hong, who is also director of George �鶹��Ƶ’s Alignment Lab. “You cannot commit to these kinds of deadlines doing everything by yourself. That's why the colorization industry is so helpful to professional cartoonists.”

Colorization is a sequential process of line drawing, flatting, base colorization, shadows and/or lighting, background and other special effects. The tool stems from a previous project, FlatMagic, another AI-driven tool designed to improve the creative process for digital comic professionals.

“This is a fairly standardized process, especially in South Korea and growing throughout the United States as well,” he explained. “The solutions to these network visualizations should be contextualized, but we have the limited resources. We can’t build everything for everybody. That’s my motivation here.”

Gingold also specializes in human-computer interaction and “has always been interested in sketching and how computers can help us express ourselves,” said the Department of Computer Science associate professor.

Yotam Gingold (left) and Ray Hong in Research Hall, presenting their colorization tool. Photo by Cristian Torres/Office of University Branding.

“We looked at artistic challenges, usually tedious things that aren’t so fun for the artists and break down those problems, so that they can focus more on the creative parts of it,” said Gingold, who is the director of George �鶹��Ƶ’s Computational Reality, Creativity, and Graphics Lab.

There are millions of pixels in an image, and if an artist wants to move or change the color of a building for example, they point at one pixel among the millions. The artist wants the rest of the pixels to follow along naturally so the rest of the building should also change, he explained.

“The computers will do the math where we can write formulas to update all the other millions of pixels. Another example would be keeping lines parallel and corners perpendicular, and that’s where a lot of my research comes in,” said.

While a doctoral student at George �鶹��Ƶ, Chuan Yan, PhD ’24, was recruited by Gingold for this project and conducted research on sketching and painting. Yan’s area of expertise encompasses computer graphics fundamentals and sketch-related computer vision techniques, which he had learned extensively from Gingold, he explained.

The ShadowMagic tool was built as an Adobe Photoshop plug-in, and since its release, the team “has garnered significant interest from artists inquiring about updates and expressing a strong desire for a tool that could free them from the labor-intensive flatting process,” said Yan, who is currently a postdoc researcher at Stanford University.

“This response is both exciting and humbling. It confirms that our research is addressing a real need in the industry yet also highlights the remaining challenges in making [the tool] ready for widespread adoption.”

Yan believes that as more sophisticated generative AI systems continue to emerge, AI-human collaboration will become increasingly vital.

“I am excited to witness and contribute to this transformation, helping to shape a future where AI acts as a powerful tool that amplifies human creativity rather than replacing it,” he said.

Discover more Artificial Intelligence research from George �鶹��Ƶ

In This Story

Sungsoo Ray Hong

Yotam Gingold

Using AI to uncover human smuggling networks

Teresa Donnellan — Wed, 15 Jan 2025 22:39:59 +0000

Using AI to uncover human smuggling networks Teresa Donnellan Wed, 01/15/2025 - 17:39

As vulnerable members of society, migrants are subject to exploitation. Professor Carlotta Domeniconi in the Department of Computer Science at �鶹��Ƶ is using artificial intelligence (AI) to combat that abuse. She is the principal investigator (PI) on a groundbreaking project aimed at understanding and modeling human smuggling networks.

Carlotta Domeniconi

In collaboration with the Department of Homeland Security’s Criminal Investigations and Network Analysis (CINA) Center for Excellence, Domeniconi and co-PIs Guadalupe Correa-Cabrera and Sean Luke are developing advanced machine learning techniques to analyze publicly available data and uncover the intricate workings of human smuggling networks between Mexico and the United States. While Domeniconi and Luke, both computer science faculty, bring expertise in machine learning, Correa-Cabrera is a professor in George �鶹��Ƶ's Schar School of Policy and Government specializing in border studies, U.S.-Mexico relations, international security, migration studies, and illicit networks.

A significant challenge in this project is the sparsity and complexity of the data, said Domeniconi. Criminal networks are large, dynamic, and constantly evolving.

"The very nature of criminal networks—their secret nature—makes it practically impossible to gather useful data," she explained. This challenge led to the team’s innovative approach of using publicly available text data—past cases of prosecuted smugglers at both the state and federal levels in the United States as well as social media posts and news articles by and about smugglers. They are collecting data from the 1980s to 2024 to analyze the temporal dynamics of these networks.

“There are videos of smugglers actually showcasing people traveling across very difficult areas from Central America,” Domeniconi noted as an example. “You can extract a lot of information about the routes they take, where they cross the borders, and the means they use."

The team is using natural language processing (NLP) and deep learning models that are pre-trained on vast amounts of text data, enabling them to understand and extract meaningful information from the data they are collecting. Two doctoral students will support the co-PIs, one from computer science and the other from the Schar School. The team is working on automating the process of building and analyzing these criminal networks using large language models and graph mining techniques. By visualizing these networks as knowledge graphs, the team aims to mine behavioral patterns and understand how these networks adapt to changes in policy enforcement. Ultimately, this project could provide a methodology applicable to various criminal networks beyond human smuggling.

Guadalupe Correa-Cabrera

“The current project bridges the gap between machine learning and social science,” explained Correa-Cabrera. “We can replicate this same model and methodology to analyze legal cases of drug smuggling, money laundering, and arms trafficking, thereby modeling and explaining the evolution of these activities over the past few decades.”

Domeniconi's pioneering work in modeling human smuggling networks is a testament to the power of AI in addressing complex social issues. By merging domain expertise with state-of-the-art machine learning techniques, this project not only promises to unravel the clandestine operations of human smuggling but also to create a robust methodology applicable to various criminal networks. The insights gained from this research could significantly enhance national security measures, offering a strategic advantage in the fight against human smuggling and those who perpetrate this crime.

Start your George �鶹��Ƶ journey

In This Story

Carlotta Domeniconi

Sean Luke

Guadalupe Correa-Cabrera

Advancing sensor tech for foggy situations

Nathan Kahl — Mon, 13 Jan 2025 13:15:50 +0000

Advancing sensor tech for foggy situations Nathan Kahl Mon, 01/13/2025 - 08:15

Devices that rely on sensors to accurately navigate and perceive the world around them are more and more commonplace, from drones to autonomous vehicles to ground robots on rescue missions. Parth Pathak, an associate professor in the Department of Computer Science at �鶹��Ƶ, is working to ensure the sensors have 20/20 vision.

From left, Rezoan Ahmed Nazib, Parth Pathak, and Ahmad Kamari with a rescue robot that can "see" through smoke and fog. Photo provided

Pathak received $660K in funding from the Army Research Office (ARO) for this work, some of which is done in collaboration with colleagues at the University of California, Davis, where he did his post-doc.

“Conventional sensors rely on cameras or LiDAR (light detection and ranging) to pursue objects around them, but they don't work very well when there's smoke, fog, or generally a visually degraded environment,” said Pathak. “But the mmwave wireless radar sensors that we are working on don't get affected by that. If there is dirt on the sensor, well, that's okay. They can see through things and see around things."

Imagine a rescue robot going into a building filled with smoke, trying to navigate with little to no visibility, Pathak said. "These wireless sensors can enable them to perceive the environment and even self-localize without cameras, LiDARs, or other positioning systems.”

Another positive aspect of the devices is that while they can sense…they don’t sense too much, which is important for privacy concerns. The disadvantage, of course, is that when a sensor depicts an object such as a car, the resolution is not particularly good, and the images are “noisy.” Pathak is not just improving navigation and perception, but using multiple robots, for example, cooperatively. In a rescue mission, a swarm of robots can share their data, allowing them to collectively “see” a better picture.

Photo provided

“They can self-localize based on what they see, like how our brains work. But the robots only have wireless sensors to rely on, so part of the work is developing very good signatures of what they see from these very low resolution and noisy images,” said Pathak. “We can build 3D models of a room by scanning it through the wireless sensors and using machine learning to capture and recreate every minute detail. This is something that these sensors were never designed for. We are developing custom-tailored deep learning models of wireless sensing, essentially pushing the limits of what they can perceive using wireless signals.”

In addition to the research, ARO’s funding also supports testbed-to-prototype development and solution evaluation.

Pathak and colleagues published this research at the Association for Computing Machinery’s ACM Mobicom conference and have submitted it to other conferences for potential publication. Two PhD students from his team, Ahmed Kamari and Rezoan Ahmed Nazib, are working actively on the project, along with three high school students who participated in prototyping over the summer as part of George �鶹��Ƶ's Aspiring Scientists Summer Internship Program.

Connect with Computer Science at �鶹��Ƶ

In This Story

Parth Pathak

George �鶹��Ƶ scientist identifies 1,000-year-old seedling linked to biblical myrrh

Katarina Benson — Wed, 08 Jan 2025 19:50:37 +0000

George �鶹��Ƶ scientist identifies 1,000-year-old seedling linked to biblical myrrh Katarina Benson Wed, 01/08/2025 - 14:50

�鶹��Ƶ researcher Andrea Weeks played a key role in identifying an ancient seedling linked to the biblical myrrh. The seed, a yellow and fragrant resin from the Commiphora tree, was discovered in the Judean desert and revived by a team of researchers.

The ancient seedling. Photo provided.

Weeks was invited to join the project, led by Hadassah University Medical Center in Jerusalem, because of her expertise in the evolutionary biology of Commiphora. Her extensive DNA sequence database played an instrumental role in analyzing the genetic makeup of the ancient specimen. Morgan Gostel, Weeks’ former PhD student and current research botanist at the Botanical Research Institute of Texas, also played a critical role in this research.

While the team confirmed the seedling’s genus, they have yet to pinpoint its precise species. “Its exact species remains unclear, highlighting the need for further biodiversity research. No lab has yet tested every species of Commiphora,” said Weeks, who is an associate professor in the Department of Biology in the College of Science and the director of George �鶹��Ƶ’s Ted R. Bradley Herbarium.

One of the most puzzling aspects of the discovery is the seed’s location. Found in a Levantine cave, the seed had been preserved for centuries in an area far outside the modern range of Commiphora.

Andrea Weeks. Photo by Evan Cantwell/Office of University Branding

“Radiocarbon dating reveals that this seed formed long after biblical times, but that doesn’t explain how or why it ended up in a cave in the Judean desert 800 to 1,000 years ago,” said Weeks.

Funding from previous grants awarded to Weeks by the National Science Foundation (NSF) helped lay the groundwork for her involvement and impact in this discovery of the ancient seed, which the researchers selected to call “Sheba.” “The use of NSF-funded data in identifying Sheba shows how foundational research can have lasting, unexpected benefits,” she said.

The study’s findings could significantly influence future research on biodiversity by enhancing our understanding of historical flora and their evolution within current ecosystems.

The interdisciplinary nature of the research, combining archaeology, ethnobotany, chemistry, and plant taxonomy, contributed to the team’s success. Moving forward, Weeks and her lab plan to deepen their exploration of Commiphora diversity. “Like most scientific inquiries, this project leaves us with more questions than answers,” Weeks said. “It sheds light on the complexity of biodiversity and also serves as a reminder of life’s interconnectedness across time.”

Learn more about research at George �鶹��Ƶ

Transforming emergency response training through AI and interactive games

Katarina Benson — Tue, 17 Dec 2024 20:42:18 +0000

Transforming emergency response training through AI and interactive games Katarina Benson Tue, 12/17/2024 - 15:42

Emergency management training doesn’t usually involve game controllers or artificial intelligence (AI) algorithms, but at �鶹��Ƶ, faculty and students are redefining what it means to prepare for crises. Through cutting-edge, AI-augmented games, they’re transforming complex challenges into interactive learning experiences that build skills and resilience.

The project, led by Shima Mohebbi, an assistant professor in the Department of Systems Engineering and Operations Research at George �鶹��Ƶ’s College of Engineering and Computing, along with PhD student Pavithra Sripathanallur Murali and Nischal Newar, MS Computer Science ’24, began as part of a National Science Foundation (NSF) initiative to develop simulation-based games for resilient infrastructure. Inspired by a webinar hosted by George �鶹��Ƶ’s Center for Resilient and Sustainable Communities (C-RASC), where the Arlington County Department of Public Safety Communications and Emergency Management (PSCEM) shared their training needs, Mohebbi and her team expanded the project’s focus to emergency preparedness.

This shift led to the creation of two interactive AI-powered games—Go-Repair and Go-Rescue —which were developed over the course of a year to train utility managers and volunteers to make critical decisions in scenarios like infrastructure repairs and hurricane disaster evacuations.

The games simulate emergency scenarios and provide participants with tailored insights into their decision-making process. By using advanced algorithms, the games create a dynamic learning environment where strategies can be tested and adapted in real time.

“Go-Repair and Go-Rescue aim to provide volunteers and utility managers with realistic emergency scenarios in a comfortable environment, free from the stress and panic of an actual crisis,” said Mohebbi. “Through AI optimization and reinforcement learning models, players can assess whether their decisions lead to better or worse outcomes compared to the AI-generated solutions, helping them improve their skills in making science-formed decisions.”

From left, Nischal Newar, Shima Mohebbi, and Pavithra Sripathanallur Murali. Photo provided

Traditional emergency training has relied on Federal Emergency Management Agency (FEMA) guidelines and in-person role-playing sessions known as “war gaming.” While valuable, these methods have limitations in scope, flexibility, and interactive feedback. The AI-powered games introduce a new dimension to address these gaps.

The project’s impact is already gaining recognition. Go-Repair: Resilient Infrastructure Learning Game to Evaluate Restoration Decisions was named as one of four finalists in the 2024 Institute of Industrial and Systems Engineers (IISE) Data Analytics and Information Systems (DAIS) Student Mobile App Competition. Presenting the project at the conference in Montreal, Canada, this past May provided an invaluable opportunity to gather feedback and engage with other researchers tackling similar challenges. This exchange of ideas offered fresh perspectives and inspired new approaches to improve the game’s design and effectiveness.

“The feedback and engagement we’ve received, from Arlington County to the IISE community, are vital to advancing this project,” said Mohebbi. “The collaboration fosters innovation and ensures that our work aligns with the real needs of emergency responders and volunteers.”

“The gamified approach to emergency response training provides us with a unique tool to build the skills and confidence needed to serve our residents when they need us most,” said Hannah Winant, Arlington County deputy director, Department of Public Safety Communications and Emergency Management. “We’re deeply grateful for George �鶹��Ƶ’s proactive, innovative work, and the opportunity to collaborate on this important effort. This project reflects our belief in the power of local partnerships to drive impactful, real-world solutions for the benefit of our community.”

Looking ahead, the team is incorporating feedback to introduce more complex resource allocation tasks and expand participation to include more George �鶹��Ƶ students and utility managers. By continuously refining the games with fresh input, the goal is to develop a versatile and effective training tool emergency response and preparedness. As the project evolves, the team aims to expand its reach, offering a smarter, more scalable solution for communities nationwide.

Research at George �鶹��Ƶ

In This Story

Shima Mohebbi

Inquiring Minds

George �鶹��Ƶ partners with DoD agency to bring closure to the families of lost U.S. service members

Related News

When the mosquitos bite, the Biomedical Research Lab bites back

In This Story

Related news

Virtual reality adds empathy to dementia care

Support for an unsung profession

In This Story

Related Stories

George �鶹��Ƶ researchers look at low-cost solutions to increase solved cases and boost public trust in police

Related News

Trial by virtual fire: Augmented reality project tailors training for firefighters

In This Story

Related News

Engineering professors develop human-AI colorization tool for cartoonists

In This Story

Related News

Using AI to uncover human smuggling networks

In This Story

Related News

Advancing sensor tech for foggy situations

In This Story

Related News

George �鶹��Ƶ scientist identifies 1,000-year-old seedling linked to biblical myrrh

Read more research stories

Transforming emergency response training through AI and interactive games

In This Story

Related Stories