COMPASS: Unsupervised and online clustering of complex human activities from smartphone sensors

作者：

Highlights：

• Heterogeneous smartphone sensors are used to infer human complex activities.

• COMPASS is an unsupervised and online solution to identify the user context.

• It overcomes the state-of-the-art clustering algorithms in terms of ARI and Purity.

• The algorithm can be entirely executed on resource-constrained devices.

摘要

•Heterogeneous smartphone sensors are used to infer human complex activities.•COMPASS is an unsupervised and online solution to identify the user context.•It overcomes the state-of-the-art clustering algorithms in terms of ARI and Purity.•The algorithm can be entirely executed on resource-constrained devices.

论文关键词：Context-awareness,Unsupervised machine learning,Online clustering,Mobile computing

论文评审过程：Received 29 February 2020, Revised 17 March 2021, Accepted 25 April 2021, Available online 29 April 2021, Version of Record 18 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115124