A hybrid machine-learning and optimization method for contraflow design in post-disaster cases and traffic management scenarios

作者：

Highlights：

• Contraflow problem has many applications in disaster management, evacuation, traffic control.

• It is an NP-hard problem, difficult to solve.

• Machine learning hybridized with traditional optimization method is employed.

• Numerical results of a real dataset are highly promising.

摘要

•Contraflow problem has many applications in disaster management, evacuation, traffic control.•It is an NP-hard problem, difficult to solve.•Machine learning hybridized with traditional optimization method is employed.•Numerical results of a real dataset are highly promising.

论文关键词：Disaster management,Emergency evacuation,Post-disaster,Machine-learning,Contraflow

论文评审过程：Received 15 March 2018, Revised 21 December 2018, Accepted 14 January 2019, Available online 19 January 2019, Version of Record 24 January 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.042