User action and facial expression recognition for error detection system in an ambient assisted environment

作者：

Highlights：

• A new method for abnormal behaviors detection using facial expressions is proposed.

• Optimized Convolutional Neural Network is proposed for facial expression recognition.

• A new method for user actions recognition using Radio Frequency IDentification tags.

• Obtained results on several benchmark datasets attest of our system’s efficiency.

• Conducted experiments in a testing smart home reveal the effectiveness of our system.

摘要

•A new method for abnormal behaviors detection using facial expressions is proposed.•Optimized Convolutional Neural Network is proposed for facial expression recognition.•A new method for user actions recognition using Radio Frequency IDentification tags.•Obtained results on several benchmark datasets attest of our system’s efficiency.•Conducted experiments in a testing smart home reveal the effectiveness of our system.

论文关键词：Smart environment,Activity recognition,Radio frequency IDentification,Facial expression recognition,Convolutional neural network,Error detection

论文评审过程：Received 27 January 2018, Revised 1 May 2018, Accepted 14 June 2018, Available online 15 June 2018, Version of Record 26 June 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.06.033