Self-regularized causal structure discovery for trajectory-based networks

作者：

Highlights：

• Existing models rarely consider trajectories' time-varying properties.

• cTVDBN reveals causal relationships among regions.

• More reliable inferences can be made.

• Approximate homotopy automates over-fitting control.

摘要

•Existing models rarely consider trajectories' time-varying properties.•cTVDBN reveals causal relationships among regions.•More reliable inferences can be made.•Approximate homotopy automates over-fitting control.

论文关键词：Causal structure discovery,Time-varying,Bayesian network,Trajectories,Density-based clustering

论文评审过程：Received 30 March 2015, Revised 22 June 2015, Accepted 28 October 2015, Available online 7 December 2015, Version of Record 3 March 2016.

论文官网地址：https://doi.org/10.1016/j.jcss.2015.10.004