Deriving Information from Low Spatial Resolution Floor-Based Personnel Detection System

摘要

We developed a low cost floor-based personnel detection system, we call a smart carpet, which consists of a sensor pad placed under a carpet, the electronics reads walking activity to provide an automated health monitoring and alert system. We extended the functionalities of the smart carpet to improve its ability to detect falls, alert health care personnel, estimate gait parameters, and count number of people walking on the carpet. Results showed that our system detects falls, using computational intelligence techniques, with 96.2% accuracy and 81% sensitivity and 97.8% specificity. We extracted and estimated gait parameters, and compared it to the GAITRite system (the gold standard), so that the system reliably estimates the walking speed, stride length and stored time with percentage errors of 1.43%, -4.32%, and -5.73% respectively. Recent results show that the system can count number of people with high accuracy. We developed a database system and web applications for immediate alerts on adverse events, and retain these data in the cloud for years, if necessary, to provide further data analysis.