An Accurate Crowdsourcing-Based Adaptive Fall Detection Approach Using Smart Devices

A low-cost but high-accuracy mechanism for detecting falls is critical for many health and safety applications, including caring for the elderly. Existing approaches are unduly expensive and sensitive to user physique and biometrics. Additionally, most approaches were developed using limited, simulated fall data and often perform poorly in field tests. To resolve these issues, in this paper we propose an accurate, crowdsourcing-based, adaptive fall detection approach using smart devices with built in wireless connection and sensors. We adaptively refine the fall detection algorithm and user groupings for improved accuracy based on the real, crowdsourced data. Field tests show that our proposed approach improves fall detection accuracy rate to 97%, compared to 68% with other traditional approaches.