Identifying multiuser activity with overlapping acoustic data for mobile decision making in smart home environments

作者：

Highlights：

• Identifying multiuser activity with overlapping acoustic data is challenging.

• A statistical method to distinguish multiple activities is proposed.

• The method outperforms current classification algorithms in terms of the accuracy.

• The method is used to implement activity-aware personalization service in smart space.

摘要

•Identifying multiuser activity with overlapping acoustic data is challenging.•A statistical method to distinguish multiple activities is proposed.•The method outperforms current classification algorithms in terms of the accuracy.•The method is used to implement activity-aware personalization service in smart space.

论文关键词：Smart home environment,Mobile decision making,Activity recognition,Multiuser activity,Acoustic classification

论文评审过程：Received 11 February 2016, Revised 27 March 2017, Accepted 28 March 2017, Available online 29 March 2017, Version of Record 3 April 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.03.062