Fall Detection with Supervised Machine Learning using Wearable Sensors

- 1 min read

Abstract

Unintentional falls can cause severe injuries to a person, and even death, especially when no immediate assistance is provided. The aim of Fall Detection Systems (FDSs) is to detect the occurrence of a fall and to automatically and promptly request the necessary assistance. This work proposes a FDS based on wearable sensors - i.e., accelerometers and gyroscopes - and Machine Learning (ML), for the automatic detection of falls. The proposed system is composed of a wearable device that collects data from the sensors and a smartphone that processes the data and implements the ML algorithm. The ML algorithm is trained using a dataset of falls and Activities of Daily Living (ADLs) collected from volunteers. The performance of the proposed system is evaluated using different ML algorithms, showing that the Random Forest algorithm achieves the best performance with an accuracy of 98.7%.

Paper: https://ieeexplore.ieee.org/document/8972246

Bibtex

@inproceedings{Giuffrida2019FallDetection,
  author = {Giuffrida, Davide and Benetti, Guido and De Martini, Daniele and Facchinetti, Tullio},
  title = {Fall Detection with Supervised Machine Learning using Wearable Sensors},
  booktitle = {2019 IEEE 17th International Conference on Industrial Informatics (INDIN)},
  year = {2019},
  pages = {253--259},
  publisher = {IEEE},
  address = {Helsinki, Finland},
  doi = {10.1109/INDIN41052.2019.8972246},
  month = {July}
}