Imperial College London
Alternate

DrArunaSivakumar

Faculty of Engineering, Department of Civil and Environmental Engineering

Reader in Consumer Demand Modelling And Urban Systems
 
 
 
//

Contact

 

+44 (0)20 7594 6036a.sivakumar Website

 
 
//

Location

 

604Skempton BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Zhu:2019:10.1109/ITSC.2019.8916966,
author = {Zhu, L and Krishnan, R and Guo, F and Polak, J and Sivakumar, A},
doi = {10.1109/ITSC.2019.8916966},
pages = {1--6},
publisher = {IEEE},
title = {Early identification of recurrent congestion in heterogeneous urban traffic},
url = {http://dx.doi.org/10.1109/ITSC.2019.8916966},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Urban  traffic  congestion  has  become  a  criticalissue  that  not  only  affects  the  quality  of  daily  lives  but  alsoharms   the   environment   and   economy.   Traffic   patterns   arerecurrent  in  nature,  so  is  congestion.  However,  little  attentionhas  been  paid  to  the  development  of  methods  that  wouldenable  early  warning  of  the  formation  of  congestion  and  itspropagation.  This  paper  proposes  a  method  for  automatedearly congestion detection operating over time horizons rangingfrom  half  an  hour  to  three  hours.  The  method  uses  a  deeplearning technique, Convolutional Neural Networks (CNN), andadapts  it  to  the  specific  context  of  urban  roads.  Empiricalresults are reported from a busy traffic corridor in the city ofBath.  Comprehensive  evaluation  metrics,  including  DetectionRate,  False  Positive  Rate  and  Mean  Time  to  Detection,  areused  to  evaluate  the  performance  of  the  proposed  methodcompared   to   more   conventional   machine   learning   methodsincluding  Feed-forward  Neural  Network  and  Random  Forest.The  results  indicate  that  recurrent  congestion  can  indeed  bepredicted  before  it  occurs  and  demonstrates  that  CNN  basedmethod  offers  superior  detection  accuracy  compared  to  theconventional  machine  learning  methods  in  this  context.
AU  - Zhu,L
AU  - Krishnan,R
AU  - Guo,F
AU  - Polak,J
AU  - Sivakumar,A
DO  - 10.1109/ITSC.2019.8916966
EP  - 6
PB  - IEEE
PY  - 2019///
SP  - 1
TI  - Early identification of recurrent congestion in heterogeneous urban traffic
UR  - http://dx.doi.org/10.1109/ITSC.2019.8916966
UR  - https://ieeexplore.ieee.org/document/8916966
UR  - http://hdl.handle.net/10044/1/75015
ER  -
Download