Feature-Filtering Data-Mining Algorithm for Urban Waterlogging Path Optimization in Extreme Weather

DOI

10.2991/icadme-17.2017.1How to use a DOI?

Keywords

city waterlogging; feature selection; risk aversion; data mining; municipal management

Abstract

Good personnel hedge scheme which can reduce the negative effects of urban waterlogging disaster is one of the effective ways and scientific means to improve the level of urban municipal management. Strong randomicity is the characteristics of stormwater runoff route under city extreme weather , this paper analyzes the characteristics and takes the dull phenomenon of traditional hedging model into account under random emergencies in extreme weather . An urban waterlogging personnel hedge mechanism is proposed based on feature selection data mining route decision making model. The flow path of urban waterlogging region is added into the model. Clustering method is used to optimize the extreme weather urban waterlogging personnel hedge path characteristics. Then the optimal data mining decision support analysis model is constructed and a personnel hedge path of urban waterlogging disaster is concluded.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wei Zhong
AU  - Youdong Zhang
PY  - 2017/07
DA  - 2017/07
TI  - Feature-Filtering Data-Mining Algorithm for Urban Waterlogging Path Optimization in Extreme Weather
BT  - Proceedings of the 2017 7th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2017)
PB  - Atlantis Press
SP  - 1
EP  - 4
SN  - 2352-5401
UR  - https://doi.org/10.2991/icadme-17.2017.1
DO  - 10.2991/icadme-17.2017.1
ID  - Zhong2017/07
ER  -