SmartFABER: Recognizing fine-grained abnormal behaviors for early detection of mild cognitive impairment

作者：

Highlights：

• SmartFABER is an innovative hybrid activity and anomaly recognition framework.

• It supports early diagnosis of MCI.

• It overcomes the shortcomings of purely statistical methods.

• We experimented SmartFABER with real-world datasets.

• SmartFABER detects most anomalies producing a small number of false positives.

摘要

Highlights•SmartFABER is an innovative hybrid activity and anomaly recognition framework.•It supports early diagnosis of MCI.•It overcomes the shortcomings of purely statistical methods.•We experimented SmartFABER with real-world datasets.•SmartFABER detects most anomalies producing a small number of false positives.

论文关键词：Mild cognitive impairment,Cognitive decline,Abnormal behavior detection,Activity recognition,Pervasive computing

论文评审过程：Received 23 July 2015, Revised 26 October 2015, Accepted 29 December 2015, Available online 7 January 2016, Version of Record 15 March 2016.

论文官网地址：https://doi.org/10.1016/j.artmed.2015.12.001