RSS feed source: National Science Foundation

Managing diabetes is a daily challenge faced by nearly 40 million Americans. It involves tracking food intake, timing medication and engaging in physical activity. Getting it wrong can lead to serious health issues; therefore, developing better prediction tools is a vital part of effective diabetes care.

To support better diabetes management, researchers funded by multiple U.S. National Science Foundation grants are developing innovative tools that help patients predict blood sugar levels more precisely without compromising the privacy of their health data. This cutting-edge approach could transform how people with diabetes monitor and manage their condition in real-time.

At the core of this technology is a method called federated learning, which allows artificial intelligence models to be trained across many patients’ devices without sending any personal data to a central server. This setup is ideal for healthcare, where data privacy is paramount and patients often use battery- and memory-limited smart devices. But early federated learning systems struggled to adapt to individual differences, like how people eat, move or react to insulin.

To address this challenge, the research team grouped patients based on their carbohydrate (e.g., sugar and starch) intake levels. The idea is that people who eat in similar ways tend to show similar glucose patterns. By training the AI on these grouped behaviors, the model became more effective at making personalized blood glucose predictions.

To test

Click this link to continue reading the article on the source website.

RSS feed source: National Science Foundation

With the devastating hurricanes that swept the southeastern United States at the end of 2024, new and better ways to get critical supplies to disaster zones and rural areas are essential. U.S. National Science Foundation Graduate Research Fellow Garrett Asper is devoting his research during his fellowship to advancing flight control systems for electric or hybrid vertical takeoff and landing vehicles (eVTOLs), which can move people and cargo “more quickly, quietly and cost-effectively than traditional helicopters or ground transportation” according to this article from Virginia Tech.

EVTOLs, which combine the vertical takeoff of helicopters with the ability to transition to horizontal flight like airplanes, are being called “the future of flight.” However, the controls during transitioning from horizontal to vertical flight still need improvement before they can be deployed during disasters. Asper’s research focuses on developing and flight-testing new control algorithms to ensure the safety, speed and efficacy of eVTOL transport. He aims to make the tools he’s creating open source, allowing other researchers to use them to test their work. By doing so, he hopes to advance the entire field and bring us closer to the day when critical supplies and aid can be quickly airlifted to disaster zones.

An aerospace engineering doctoral candidate at Virginia Tech, Asper is a researcher in the Nonlinear Systems Laboratory and the NSF-funded Uncrewed Systems Laboratory. He

Click this link to continue reading the article on the source website.

RSS feed source: National Science Foundation

The U.S. National Science Foundation Regional Innovation Engines (NSF Engines) program announced the 29 semifinalists advancing to the next stage of the second competition – spanning critical technologies and applications ranging from energy grid security to maximizing the yield of critical minerals mining to advanced optical sensors. The semifinalist teams, many of whom have been building their regional coalitions for a year or longer, are led by universities, nonprofits, private industry and other organizations from across the United States. View a map of the NSF Engines semifinalists.