Utilization of data mining on asset management of freeway flexible pavement

Po Hsun Sung, Jyh Dong Lin, Shih Huang Chen, Shun Hsing Chen, Hung Peng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Data mining is used to analysis a large number of data. The study was using asset management of freeway flexible pavement and re-dug out new knowledge of pavement cracks by using decision tree of data mining. Road units were built per 20 meters per lane. Construction data (35,828 documents) was built and included road construction type, altitude and topography. Maintenance constructions data (36,439 documents) was built. The historical data included equivalent single axle loads, temperature and rainfall. Decision tree of C5.0 and C&R tree are different from the principle of calculation. The result of C5.0 was 92 rules and accuracy rate was 95%.The result of C&R tree was 21 rules and the accuracy rate was 80%. The results by C5.0 could be used to distinguish the reasons of pavement crack, and the results of C&R tree could be used to forecast the types of pavement crack.

Original languageEnglish
Title of host publicationIEEM2010 - IEEE International Conference on Industrial Engineering and Engineering Management
Pages977-979
Number of pages3
DOIs
StatePublished - 2010
EventIEEE International Conference on Industrial Engineering and Engineering Management, IEEM2010 - Macao, China
Duration: 7 Dec 201010 Dec 2010

Publication series

NameIEEM2010 - IEEE International Conference on Industrial Engineering and Engineering Management

Conference

ConferenceIEEE International Conference on Industrial Engineering and Engineering Management, IEEM2010
Country/TerritoryChina
CityMacao
Period7/12/1010/12/10

Keywords

  • Asset management
  • Data mining
  • Decision tree
  • Pavement management

Fingerprint

Dive into the research topics of 'Utilization of data mining on asset management of freeway flexible pavement'. Together they form a unique fingerprint.

Cite this