Traffic pattern analysis is an active and essential part of transportation research. When traffic condition is adverse and unprecedented, traffic sequences are useful in the analysis of traffic behaviour. The sequence through which traffic congestion has arisen can be predicted using sequence rules from the generated traffic sequence. This work aims at mining traffic sequence pattern and prediction of traffic volume based on traffic sequence rules. To mine peak hour traffic sequences in order to make better travel decision, travel time based PrefixSpan (TT‐PrefixSpan) algorithm is proposed to analyse traffic flow on highways. As a result, the prediction of traffic volume is effected by the generated traffic sequences. Such analysis would pave the way for devising data driven computational methods in reducing traffic congestion. Real‐time traffic volume data for 53 weeks is collected at a centralised toll system comprising toll collections centres at three different sites. To show the significance of this problem‐solving approach, TT‐PrefixSpan is experimented on three different sites. The extraction of a frequent traffic sequence pattern is reported with experimental analysis. The evaluation of different traffic condition present at each site has shown promising results. Towards the end, a summary of results is presented with directions for future research.
Prediction of traffic volume by mining traffic sequences using travel time based PrefixSpan
IET Intelligent Transport Systems ; 13 , 7 ; 1199-1210
2019-07-01
12 pages
Article (Journal)
Electronic Resource
English
traffic congestion , traffic congestion reduction , traffic pattern analysis , travel time , travel time based PrefixSpan , road traffic , centralised toll system , traffic sequences mining , traffic flow analysis , traffic engineering computing , different traffic condition , traffic sequence rules , TT‐PrefixSpan , transportation , traffic volume prediction , data driven computational methods , toll collection centres , data mining , frequent traffic sequence pattern , peak hour traffic sequences , traffic behaviour , time 53.0 week , real‐time traffic volume data , generated traffic sequence , PrefixSpan algorithm
Prediction of traffic volume by mining traffic sequences using travel time based PrefixSpan
IET | 2019
|Vehicle frequent track mining method and system based on prefixspan algorithm
European Patent Office | 2020
|Bus travel time prediction with real-time traffic information
Elsevier | 2019
|