Detection of abnormal behaviour for dementia sufferers using Convolutional Neural Networks
作者：
Highlights：
• Elderly people may suffer from the consequences of cognitive decline.
• Detecting the indicators of dementia before it gets worse would be helpful for further diagnosis.
• Activity recognition can be considered as a sequence labelling problem.
• Data reflecting on abnormal behaviour is generated.
• CNNs are promising to detect abnormal behaviour related to dementia.
摘要
•Elderly people may suffer from the consequences of cognitive decline.•Detecting the indicators of dementia before it gets worse would be helpful for further diagnosis.•Activity recognition can be considered as a sequence labelling problem.•Data reflecting on abnormal behaviour is generated.•CNNs are promising to detect abnormal behaviour related to dementia.
论文关键词：Smart homes,Sensor based activity recognition,Convolutional Neural Networks,Long short term memory recurrent neural networks,Dementia,Abnormal behaviour detection
论文评审过程：Received 25 January 2018, Revised 20 May 2018, Accepted 22 January 2019, Available online 10 February 2019, Version of Record 19 February 2019.
论文官网地址：https://doi.org/10.1016/j.artmed.2019.01.005
