Carnegie Mellon University Civil and Environmental Engineering Assistant Professor Hae Young Noh has received a $500,000 Faculty Early Career Development Program (CAREER) grant from the National Science Foundation to study how sensor technology can be used to enable “smart buildings” to locate and identify specific inhabitants and to use the vibrations of their movements within the building to classify their activity.
The project, titled “Structures as sensors: elder activity level monitoring through structural vibrations,” aims to use buildings themselves as activity sensors by passively sensing the floor vibration caused by footsteps, and then using advanced sparse-signal approximation to assign those footsteps to specific individuals. The project focuses primarily on the application of this technology in elder care.
“Elder care facilities aim to maintain or improve quality of life and independence of elders while reducing costs and capacity needs for care-professionals,” Noh states in the award’s abstract. “One key to achieving this goal is to understand the activities of each occupant.”
To achieve this goal, Noh will first install vibration sensors in three different elder care facilities, and through detailed vibrational analysis, extract individual persons’ footstep vibration signals. From there, she will use that information to localize those footstep signals by dynamically fusing multiple sources of frequency information, all the while improving the model’s accuracy by iteratively fusing location information and signal separation.
This will allow elder care facilities to non-invasively monitor its patients’ health and activity through the use of simple vibration sensors, as well as locate portions of the building that may provide unsafe footing for occupants.
The NSF CAREER Program is a foundation-wide initiative, offering prestigious awards to encourage faculty early in their careers to serve as role models in research and education, and to build the foundation for a lifetime of leadership in their field.