Sequential behavior prediction based on hybrid similarity and cross-user activity transfer

作者：

Highlights：

• Linear algebraic modeling of human behavior with mobile devices.

• Improving behavior prediction by transferring knowledge from different users.

• A hybrid similarity measure based on PCA and longest/daily common behavior.

摘要

•Linear algebraic modeling of human behavior with mobile devices.•Improving behavior prediction by transferring knowledge from different users.•A hybrid similarity measure based on PCA and longest/daily common behavior.

论文关键词：Mobile data,Behavior similarity,Common behavior analysis,Transfer learning,Principal component analysis,Sequential prediction

论文评审过程：Received 20 June 2014, Revised 22 December 2014, Accepted 25 December 2014, Available online 5 January 2015.

论文官网地址：https://doi.org/10.1016/j.knosys.2014.12.026