A mobile solution based on soft computing for fall detection

Abstract

Falling is an important health risk, especially for the elderly people. This situation prevents individuals from living independently. Automatic and high-accuracy detection of the falls will contribute in preventing the negative situations that may occur. In this study, a mobile solution with a new architecture for the detection of falls is presented. For this purpose, motion sensor data have been collected simultaneously from smartwatch and smartphone with Android operating system. Data sets for both smartwatch and smartphone have been created by labeling the falls and actions which are not falling in the data. The performances of Decision Tree, Naive Bayes, and k-Nearest Neighbor (kNN) methods have been tested on these data sets, and the kNN method has given the best result on two data sets. Accordingly, the kNN method is used for classification in the developed Android-based mobile solution. In addition, it is aimed to detect and prevent actions that could lead to bad results by monitoring the heart rate of the user with the built-in heart rate monitor on the smartwatch. © Springer International Publishing AG, part of Springer Nature 2019.