Kennesaw State University researcher Bobin Deng is working to make artificial intelligence (AI) more accessible by developing technology that can operate on everyday devices without relying on large data centers or internet connections. Supported by a grant from the National Science Foundation, Deng aims to move AI processing from remote servers directly onto personal devices such as smartphones, drones, and industrial sensors.
Deng, an assistant professor in the College of Computing and Software Engineering at Kennesaw State, explained the potential impact of this shift. “Most of today’s AI runs on large, expensive servers,” Deng said. “But many applications don’t need that level of computing power. If we can run AI directly on a mobile phone, a drone, or other smaller systems, then we remove the reliance on costly supercomputers and make AI easier and faster access in more situations.”
The research focuses on activation sparsity—a method where only certain parts of an AI model are active at any time. By predicting which pieces of data will be needed ahead of time and loading only those into memory, the system uses less energy and operates more efficiently.
“Other methods shrink models by reducing the precision of data or pruning less important parameters,” Deng said. “Our approach is different. We predict which values will be activated. That allows us to combine our method with existing techniques like pruning or quantization to make models even more efficient.”
As part of the project, Deng’s team is building an open-source simulator for researchers and students to further explore these methods. The initiative supports KSU’s new Master of Science in Artificial Intelligence program and aims to help industry partners implement advanced AI solutions.
“This grant supports fundamental research that can benefit students in our new Master of Science in Artificial Intelligence program, as well as industry partners,” he said. “From monitoring factory robots to predicting equipment failures, embedding AI in smaller devices has the potential to transform many industries.”
Deng conducts his work at the Sustainable Smart System Lab located on KSU’s Marietta Campus. He credited university leadership for providing essential support throughout his research process.
“The leadership here has been very supportive,” he said. “Whenever I have needed resources or assistance, from graduate assistants to proposal submissions, the university has been there to help.”
Yiming Ji, interim dean for the College of Computing and Software Engineering at KSU, highlighted how this project aligns with institutional goals: “Dr. Deng’s research represents the kind of forward-looking work that positions KSU as a leader in AI,” Ji said. “His approach not only addresses technical challenges but also creates real-world opportunities for students, industry partners, and the community.”
