Tian Guo
The National Science Foundation has awarded $399,999 to WPI researcher Tian Guo for collaborative research investigating how heterogeneous edge computing resources can better support Artificial Intelligence of Things (AIoT) devices.
The four-year collaborative project involves researchers at WPI and the University of Massachusetts Amherst. Professor Sandip Kundu at UMass Amherst is principal investigator (PI) of the overall project, joined by UMass Amherst Professor Russell Tessier, who is co-PI. Guo, an associate professor in the WPI Department of Computer Science, is PI of the WPI side of the project.
Broadly, AIoT leverages artificial intelligence (AI) to make the Internet of Things (IoT) smarter including network-connected devices, machines, or objects. Drones can use onboard camera views and computer vision algorithms to assist in tasks such as search and rescue and digital agriculture. However, AIoT devices are often constrained by computational resources and battery capacity, which makes it critical to carefully plan the executions of those algorithms on the AIoT devices and on edge servers.
“This project provides good opportunities for cross-layer research, from application-level algorithms like computer vision to management of hardware resources like AIoT and edge devices. To disseminate and promote the research in this area, we will organize annual research workshops that will be run by WPI and UMass graduate students,” Guo said. “We also plan to integrate projects that are based on this research into undergraduate and graduate courses.”
Guo is an expert in designing computing mechanisms and policies that balance cost, performance, and efficiency for emerging applications. She has previously been awarded NSF funding for research that pinpointed and developed improvements for performance bottlenecks in mobile deep-learning applications. She received a CAREER Award for a project to develop techniques to improve performance and privacy in mobile augmented reality systems, and she recently was awarded NSF funding to develop a framework for quantum cloud computing.
Learn More About WPI Faculty
I am a system researcher by training and am particularly passionate about designing systems mechanisms and policies to handle trade-offs in cost, performance, and efficiency for emerging applications. Since joining WPI, my group’s research has focused on improving system support and performance for machine learning (ML)-related workloads. Because ML is widely adopted in many applications, it is critical to have performant systems that can effectively train, serve, and manage ML models.