| Περίληψη: | Falls can be severe enough to cause disabilities especially to frail populations. Thus, prompt health care provision is essential to prevent and restore any harm. The purpose of this study is to develop a smartphone-based fall detection system.
This thesis first presents valid reports to illustrate the necessity of a fall detection system and then related work and research is discussed. The volume of the literature and the development of high performance systems prove the need to tackle the fall detection problem.
To this effect, the appropriate data processing techniques and development tools are presented. Specifically, signal processing methods and machine learning notions are briefly explained. In addition, it presents the Android architecture and developer tools that allow for the development of a fall detection application. Then, each part of the proposed implementation is shown, i.e. data collection, feature extraction, and classification. The most significant aspects of the Android application are the personalization of the classification system and the regulation of battery drain. Finally, the performance of the developed system is evaluated and compared with other relevant attempts.
In conclusion, the results show that the implementation of a fall detection system based on smartphones is possible and high performance can be achieved. In a future work, the evaluation of the system on real world data, as well as the improvement of the detection and personalization components will be studied.
|
|---|
