Page 117 - NGTU_paper_withoutVideo

Modern Geomatics Technologies and Applications

24:00
1-hour intervals 12:00
18:00
18

18

18
6:00
0:00
18
1 5 10 15 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 100 105 110 115

Zone
Fig.6. Trend of changes in average traffic congestion of weekends in one-hour time intervals in the study area during the time
of study
5. Conclusion
Parameters of evaluating the traffic state such as travel time or congestion, play a critical role in assessing most of
transportation systems and can be regarded as a criterion to analyse transportation systems. In this research, the feasibility of
employing chronological traffic data images obtained from Google Map Services as traffic big data has been investigated. By
extracting congestion data and image processing, the congestion index was calculated and the trend of change in the average of
traffic congestion was analysed over areal units within CCZ, AQCZ and out of both regions on weekdays and weekends.
Following, the pattern of traffic congestion was investigated. Then, spatial autocorrelation of traffic congestion was evaluated
using Moran’s I spatial autocorrelation index and the area with highly congested index was analysed. The spatio-temporal
changes of traffic congestion in the study area was also illustrated using Hovmöller diagrams on which, the start time and duration
of congestion could be extracted. In this study, data relating to traffic images obtained from Google Maps Service has been used
to perform spatio-temporal analysis of traffic congestion. The results can be effective in most traffic management purposes such
as helping to improve congestion charging zones or air pollution control zones, as well as contributing to studies relating to road
pricing.

6. References
[1]. Grisolía, J.M., F. López, and J.d.D. Ortúzar, Increasing the acceptability of a congestion charging scheme. Transport
Policy, 2015. 39: p. 37-47.
[2]. Li, G., et al., Influence of traffic congestion on driver behavior in post-congestion driving. Accident Analysis &
Prevention, 2020. 141: p. 105508.
[3]. Zhao, P. and H. Hu, Geographical patterns of traffic congestion in growing megacities: Big data analytics from Beijing.
Cities, 2019. 92: p. 164-174.
[4]. Atta, A., et al., An adaptive approach: Smart traffic congestion control system. Journal of King Saud University-
Computer and Information Sciences, 2018.
[5]. Agyapong, F. and T.K. Ojo, Managing traffic congestion in the Accra central market, Ghana. Journal of Urban
Management, 2018. 7(2): p. 85-96.
[6]. Jain, S., S.S. Jain, and G. Jain, Traffic congestion modelling based on origin and destination. Procedia Engineering,
2017. 187: p. 442-450.
[7]. He, F., et al., A Traffic Congestion Assessment Method for Urban Road Networks Based on Speed Performance Index.
Procedia Engineering, 2016. 137: p. 425-433.
[8]. Bertini, R.L., M. Leal, and D.J.R.B. Lovell, Generating Performance Measures from Portland’s Archived Advanced
Traffic Management System Data, in Transportation Research Board. 2002: Washington D.C.
[9]. Turochy, R.E. and B.L. Smith, Measuring variability in traffic conditions by using archived traffic data. Transportation
Research Record, 2002. 1804(1): p. 168-172.
[10]. Bertini, R.L. and S. Tantiyanugulchai, Transit buses as traffic probes: Use of geolocation data for empirical evaluation.
Transportation Research Record, 2004. 1870(1): p. 35-45.
[11]. Fouladgar, M., et al. Scalable deep traffic flow neural networks for urban traffic congestion prediction. in 2017
International Joint Conference on Neural Networks (IJCNN). 2017. IEEE.
[12]. Hashemi, H. and K.F. Abdelghany, Real-time traffic network state estimation and prediction with decision support
capabilities: Application to integrated corridor management. Transportation Research Part C: Emerging Technologies,
2016. 73: p. 128-146.
[13]. Ito, T. and R. Kaneyasu, Predicting traffic congestion using driver behavior. Procedia Computer Science, 2017. 112:
p. 1288-1297.

6