Hybrid models toward traffic detector data treatment and data fusion

Yuh Horng Wen*, Tsu Tian Lee, Hsun-Jung Cho

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

14 Scopus citations


This paper develops a data processing with hybrid models toward data treatment and data fusion for traffic detector data on freeways. Hybrid grey-theory-based pseudo-nearest-neighbor method and grey time-series model are developed to recover spatial and temporal data failures. Both spatial and temporal patterns of traffic data are also considered in travel time data fusion. Two travel time data fusion models are presented using a speed-based link travel time extrapolation model for analytical travel time estimation and a recurrent neural network with grey-models for real-time travel time prediction. Field data from the Taiwan national freeway no.1 were used as a case study for testing the proposed models. Study results shown that the data treatment models for faulty data recovery were accurate. The data fusion models were capable of accurately predicting travel times. The results indicated that the proposed hybrid data processing approaches can ensure the accuracy of travel time estimation with incomplete data sets.

Original languageEnglish
Number of pages6
StatePublished - 1 Dec 2005
Event2005 IEEE Networking, Sensing and Control, ICNSC2005 - Tucson, AZ, United States
Duration: 19 Mar 200522 Mar 2005


Conference2005 IEEE Networking, Sensing and Control, ICNSC2005
CountryUnited States
CityTucson, AZ


  • Data fusion
  • Data processing
  • Traffic detectors
  • Traffic information systems

Fingerprint Dive into the research topics of 'Hybrid models toward traffic detector data treatment and data fusion'. Together they form a unique fingerprint.

Cite this