Detecting unseen falls from wearable devices using channel-wise ensemble of autoencoders

作者：

Highlights：

• Investigated the use of Autoencoders to learn generic features from wearable devices.

• Proposed channel-wise ensemble approaches for Autoencoders to identify unseen falls.

• Developed new threshold tightening approaches on reconstruction error of Autoencoder.

• Demonstrated better performance on two fall recognition datasets.

摘要

•Investigated the use of Autoencoders to learn generic features from wearable devices.•Proposed channel-wise ensemble approaches for Autoencoders to identify unseen falls.•Developed new threshold tightening approaches on reconstruction error of Autoencoder.•Demonstrated better performance on two fall recognition datasets.

论文关键词：Fall detection,One-class classification,Autoencoder,Anomaly detection

论文评审过程：Received 30 March 2017, Revised 2 June 2017, Accepted 7 June 2017, Available online 15 June 2017, Version of Record 22 June 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.06.011