Improving wearable-based fall detection with unsupervised learning

Fall detection (FD) is a challenging task that has received the attention of the research community in the recent years. This study focuses on FD using data gathered from wearable devices with tri-axial accelerometers (3DACC), developing a solution centered in elderly people living autonomously. This research includes three different ways to improve a FD method: (i) an analysis of the event detection stage, comparing several alternatives, (ii) an evaluation of features to extract for each detected event and (iii) an appraisal of up to 6 different clustering scenarios to split the samples in subsets that might enhance the classification. For each clustering scenario, a specific classification stage is defined. The experimentation includes publicly available simulated fall data sets. Results show the guidelines for defining a more robust and efficient FD method for on-wrist 3DACC wearable devices.