A comprehensive study on the use of artificial neural networks in wearable fall detection systems

作者：

Highlights：

• Thorough analysis of wearable Fall Detection Systems (FDS) based on neural networks.

• Existing research has only focused on optimizing the recognition metrics.

• The study reveals significant methodological flaws in the evaluation of FDSs.

• Important implementability issues are normally neglected by the literature.

• Operational and social aspects are also ignored by the related literature.

摘要

•Thorough analysis of wearable Fall Detection Systems (FDS) based on neural networks.•Existing research has only focused on optimizing the recognition metrics.•The study reveals significant methodological flaws in the evaluation of FDSs.•Important implementability issues are normally neglected by the literature.•Operational and social aspects are also ignored by the related literature.

论文关键词：Fall Detection System,Accelerometer,Artificial neural network,Dataset,Machine learning

论文评审过程：Received 23 July 2018, Revised 21 June 2019, Accepted 12 July 2019, Available online 12 July 2019, Version of Record 27 July 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.07.028