Please use this identifier to cite or link to this item:
|Title:||Analysis of traffic flow data for iterative tuning strategy in urban traffic signal control||Authors:||Yang, Chule||Keywords:||DRNTU::Engineering::Electrical and electronic engineering||Issue Date:||2016||Abstract:||With the rapid development of big data analysis and intelligent devices, data mining approach makes it possible to obtain the useful information among the large-scale database. Here this data mining technique is applied to our urban traffic system in order to dig out useful information from the vast and chaotic traffic flow raw data and help improve traffic control strategies. Lots of effort has been devoted to utilize traffic flow data for travel-time and congestion prediction and fine tuning for improving traffic. Recently, a novel traffic signal control strategy, Iterative Tuning (IT), has been proposed on the strength of the repetitive traffic flow patterns. This dissertation take advantage of statistical methods to observe the implementation of the IT strategy based on real traffic flow data from Singapore. Two important issues have been discussed. One is the phase-based repetitive identification of traffic flows in urban road networks. The statistical analysis shows that there is a strong phase-based repetitiveness on weekdays which is confirmed with 15 minutes sampling interval, and less than 20% and 30% of the coefficients of variations for critical junctions with heavy traffic flows on working days and weekends, respectively. The other issue is the real-time classification of traffic flow patterns for implementation of IT controller. Data analysis process mainly covers data validity, pattern recognition and pattern updating. Real traffic flow raw data on a key network, Jurong East, of Singapore is evaluated to test the repetitiveness and classify daily traffic flow patterns. The presented results make IT strategy feasible and practical for real time applications to improve traffic conditions in urban road networks.||URI:||http://hdl.handle.net/10356/68546||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Theses|
Updated on May 10, 2021
Updated on May 10, 2021
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.