Mobile Applications for Fall Detection

With an increasing population of elderly people the number of falls and fall-related injuries is on the rise. This will cause changes for future health care systems, and both fall detection and fall prevention will pose a major challenge. Ambient Assisted Living (AAL) is a research area in which concepts and information systems for assisting elderly individuals are developed. Fall detection, as an important discipline of AAL, investigates a broad range of approaches including wearable devices. With their growing popularity, mobile devices with their embedded motion sensors, their software capabilities and cost-efficiency are well-suited for fall detection. A test framework for collecting and analyzing data regarding fall detection is presented. The framework consists of a RESTful Web service, a relational database and a Web-based back end. It offers an open interface to support a variety of devices. The system architecture is based on the state-of-the-art theoretical background of AAL and on the evaluation of an existing software. In order to test the framework, a mobile device client recording accelerometer and gyroscope sensor data is implemented on the iOS platform.

Autorentext

Stefan Almer, born 1984 in Judenburg, Austria, studied Software Development and Business Management at Graz University of Technology. Today, he is working as software engineer in the field of mobile applications and systems.