Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges

作者：

Highlights：

• Review of deep learning methods for sensor based human activity recognition.

• Categorize the studies into generative, discriminative and hybrid methods.

• Present training, evaluation procedures and Common datasets.

• Outline open research issues presented as future directions.

摘要

•Review of deep learning methods for sensor based human activity recognition.•Categorize the studies into generative, discriminative and hybrid methods.•Present training, evaluation procedures and Common datasets.•Outline open research issues presented as future directions.

论文关键词：Deep learning,Mobile and wearable sensors,Human activity recognition,Feature representation,Review

论文评审过程：Received 29 May 2017, Revised 26 March 2018, Accepted 27 March 2018, Available online 1 April 2018, Version of Record 24 April 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.03.056