Online updating extended belief rule-based system for sensor-based activity recognition

作者：

Highlights：

• Propose an eigendecomposition-based method to select sensors in a high-efficiency way.

• Propose a domain division-based method to update rules in a high-efficiency way.

• Propose an online updating EBRBS for achieving activity recognition more efficiently.

• Experiments show the proposed EBRBS has a high accuracy and excellent response time.

摘要

•Propose an eigendecomposition-based method to select sensors in a high-efficiency way.•Propose a domain division-based method to update rules in a high-efficiency way.•Propose an online updating EBRBS for achieving activity recognition more efficiently.•Experiments show the proposed EBRBS has a high accuracy and excellent response time.

论文关键词：Extended belief rule base,Online model updating,Feature selection,Activity recognition,Smart environment

论文评审过程：Received 23 December 2019, Revised 29 June 2021, Accepted 5 August 2021, Available online 13 August 2021, Version of Record 17 August 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115737