Development of an Enhanced Threshold-Based Fall Detection System Using Smartphones With Built-In Accelerometers
Jin‐Shyan Lee, Hsuan-Han Tseng · IEEE Sensors Journal · 2019
Falls are a primary accident for elderly people living independently. Obviously, timely and accurate fall detection is critical to reduce the injuries and avoid the loss of life. In order to improve existing smartphone-based fall detection systems, this paper investigates the features of triaxial acceleration values acquired from built-in accelerometers of a smartphone, identifies crucial thresholds of the falls and non-falls, and then proposes an enhanced threshold-based fall detection approach, which could not only distinguish fall events from the most of daily activities (including walking, running, and sitting down), but also support four directions (forward, backward, left lateral, and right lateral) of the falls. In addition, once a falling accident is identified, the user position would be instantaneously transmitted to an emergency center in order to have timely medical assistance. As a consequence, experimental results show the feasibility of our enhanced approach with accuracy and detection rates of 99.38% and 96%, respectively, while a set of 650 test activities including 11 different kinds of daily activities are performed.