Smartphone-based Human Fall Detection System

Abstract

The use of technology has proven to be a value asset in the health department. Nowadays, from computers to smartphones, technology helps people in their activities, being these personally or cooperativily. Thanks to these advantages, new research has develop to create systems and applications to help with people's health, in our case detecting fall accidents with the use of smartphones. This paper presents an approach to detect falls using different proposed algorithms with the goal of helping people with their health and security. The system es composed of three different components: data collection, location selection, and fall detection. It utilizes the smartphone's built-in sensors (accelerometer, gyroscope) to identify the location of the smartphone in the user's body (chest, pocket, holster, etc.) and once a location is identified, the fall detection component takes place. A general description on fall detection systems is provided, including the different types of sensors used nowadays. The proposed solution is presented and described in great detail. A total accuracy of 81.3% was calculated from the fall detection proposed algorithm. The top three locations to detect a fall were: texting with a 95.8% fall detection accuracy, pants' side pocket with an 87.5% accuracy, and shirt chest pocket with an 83.3% accuracy. Also an extra study was done using only the holster location generating an excellent 100% location selection accuracy