Recognizing activities of daily living from UWB radars and deep learning

作者：

Highlights：

• Creation of a unique dataset containing 15 ADLs acquired from three UWB radars.

• Experiments conducted in a real apartment by 10 participants.

• Data augmentation to degrade the activity location influences.

• A voting system based on trained deep learning models.

• Results of ADL recognition reach 90% in some cases.

摘要

•Creation of a unique dataset containing 15 ADLs acquired from three UWB radars.•Experiments conducted in a real apartment by 10 participants.•Data augmentation to degrade the activity location influences.•A voting system based on trained deep learning models.•Results of ADL recognition reach 90% in some cases.

论文关键词：Everyday activities,Classification,Recognition,UWB radar,Deep learning

论文评审过程：Received 29 December 2019, Revised 19 August 2020, Accepted 9 September 2020, Available online 19 September 2020, Version of Record 25 September 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113994