Research Article
An Open Labelled Dataset for Mobile Phone Sensing Based Fall Detection
@INPROCEEDINGS{10.4108/eai.22-7-2015.2260160, author={Alfred Wertner and Paul Czech and Viktoria Pammer-Schindler}, title={An Open Labelled Dataset for Mobile Phone Sensing Based Fall Detection}, proceedings={12th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services}, publisher={ACM}, proceedings_a={MOBIQUITOUS}, year={2015}, month={8}, keywords={mobile phone sensing open training dataset fall detection accelerometer gyroscope martial artists}, doi={10.4108/eai.22-7-2015.2260160} }- Alfred Wertner
Paul Czech
Viktoria Pammer-Schindler
Year: 2015
An Open Labelled Dataset for Mobile Phone Sensing Based Fall Detection
MOBIQUITOUS
ICST
DOI: 10.4108/eai.22-7-2015.2260160
Abstract
Fall detection is a classical use case for mobile phone sensing. Nonetheless, no open dataset exists that could be used to train, test and compare fall detection algorithms. We present a dataset for mobile phone sensing-based fall detection. The dataset contains both accelerometer and gyroscope data. Data were labelled with four types of falls (e.g., "stumbling") and ten types of non-fall activities (e.g., "sit down"). The dataset was collected with martial artists who simulated falls. We used five different state-of-the-art Android smartphone models worn on the hip in a small bag. Due to the dataset’s properties of using multiple devices and being labelled with multiple fall and non-fall categories, we argue that it is suitable to serve as benchmark dataset.
