smartPrediction: a real-time smartphone-based fall risk prediction and prevention system

Abstract

The high risk of falls and the substantial increase in the elderly population have recently stimulated scientific research on Smartphone-based fall detection systems. Even though these systems are helpful for fall detection, the best way to reduce the number of falls and their consequences is to predict and prevent them from happening in the first place. To address the issue of fall prevention, in this paper, we propose a fall prediction system by integrating the sensor data of Smartphones and a Smartshoe. We designed and implemented a Smartshoe that contains four pressure sensors with a Wi-Fi communication module to unobtrusively collect data in any environment. By assimilating the Smartshoe and Smartphone sensors data, we performed an extensive set of experiments to evaluate normal and abnormal walking patterns. The system can generate an alert message in the Smartphone to warn the user about the high-risk gait patterns and potentially save them from an imminent fall. We validated our approach using a decision tree with 10-fold cross validation and found 97.2% accuracy in gait abnormality detection.