Geospatial data integration for intelligent transportation systems: A review of the state of the art of spatio-temporal traffic forecasting
DOI:
https://doi.org/10.48346/IMIST.PRSM/ajlp-gs.v6i4.41748Keywords:
Intelligent transportation, artificial intelligence, geospatial data, prediction, congestion, trafficAbstract
Context and background:
Intelligent transportation is a dynamic field focused on enhancing travel efficiency, reducing congestion, and increasing convenience. Central to this domain is the collection and analysis of spatio-temporal data, enabling precise traffic flow predictions and the development of intelligent traffic management systems. Integrating geospatial data, encompassing road topology and proximity to public infrastructure and transportation services, presents a significant challenge in designing effective intelligent transportation systems. Despite the availability of extensive geospatial databases, their optimal utilisation necessitates advanced data analysis techniques.
Goal and Objectives:
This research aims to seamlessly incorporate geospatial data into intelligent transportation systems, utilising advanced analysis techniques. The primary objective is to leverage geospatial data to improve system performance.
Methodology:
Various data analysis techniques are explored for integrating geospatial data into spatio-temporal traffic prediction. Expert systems, DBMS, spatial data analysis, machine learning, and AI algorithms are evaluated for their effectiveness in leveraging geospatial and temporal data.
Results:
Machine learning algorithms demonstrate promise in accurate traffic forecasting using geospatial and temporal data. Diverse geospatial data sources, like aerial imagery and navigation systems, refine predictions and contribute vital insights for urban planning.
These integrated spatial data categories—On network data and Off network data—contribute vital insights. On network data provides road network characteristics, encompassing lane counts, speed limits, and adjoining sections, while Off network data encompasses demographic, socio-economic, and land use information, crucial for deciphering transportation patterns and identifying growth prospects in urban development. Overall, this comprehensive study advances our understanding of efficient and convenient transportation systems, their environmental and societal implications, and offers valuable insights to mitigate traffic issues and enhance transportation services' quality.
References
B. Singh, A. Gupta. Recent trends in intelligent transportation systems: a review. Journal of Transport Literature, 2015
A. Faghri, K. Hamad. Applicition of GPS in Traffic Management Systems. GPS Solutions, 5(3), 52-60, 2002.
H. Feng and Y. Shu. Study on network traffic prediction techniques. Wireless Communications, Networking and Mobile Computing. Proceedings. 2005 International Conference on, vol. 2. IEEE, 2005, pp. 1041–1044, 2005.
P. Cortez, M. Rio, M. Rocha, and P. Sousa. Internet traffic forecasting using neural networks. Neural Networks, 2006. IJCNN’06. International Joint Conference on. IEEE, pp. 2635–2642, 2006
A. Medina, N. Taft, K. Salamatian, S. Bhattacharyya, and C. Diot. Traffic matrix estimation: Existing techniques and new directions. ACM SIGCOMM Computer Communication Review, vol. 32, no. 4, pp. 161–174, 2002.
T. Ma, C. Antoniou, T. Toledo. Hybrid machine learning algorithm and statistical time series model for network-wide traffic forecast. Transportation Research Part C: Emerging Technologies, 2019
M. Barabas, G. Boanea, A. B. Rus, V. Dobrota, and J. DomingoPascual. Evaluation of network traffic prediction based on neural networks with multi-task learning and multiresolution decomposition. Intelligent Computer Communication and Processing (ICCP), 2011 IEEE International Conference on. IEEE, pp. 95–102, 2011.
S. Prajam, C. Wechtaisong, A. A. Khan. Applying machine learning approaches for network traffic forecasting. Indian Journal of Computer Science and Engineering (IJCSE), 2022.
Polson, N.G., Sokolov, V.O. Deep learning for short-term traffic flow prediction. Transp. Res. Part C: Emerg. Technol. 79, 1–17, 2017
A. Ermagun, D. Levinson. Development and application of the network weight matrix to predict traffic flow for congested and uncongested conditions. Environment and Planning B: Urban Analytics and City Science, 1, 1–22. doi:10.1177/2399808318763368, 2018
Y. Li, C. Shahabi. A brief overview of machine learning methods for short-term traffic forecasting and future directions. SIGSPATIAL Special, 2018.
Y. Wu and H. Tan. Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework. arXiv preprint arXiv:1612.01022, 2016.
Y. Li, R. Yu, C. Shahabi, and Y. Liu. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In International Conference on Learning Representations (ICLR), 2018.
X. Cheng, R. Zhang, J. Zhou, and W. Xu. Deeptransport: Learning spatial-temporal dependency for traffic condition forecasting. arXiv preprint arXiv:1709.09585, 2017.
J. Zhang, Y. Zheng, and D. Qi. Deep spatio-temporal residual networks for citywide crowd flows prediction.
In AAAI, pages 1655–1661, 2017.
P. Xie, T. Li, J. Liu,S. Du, X. Yang, J. Zhang. Urban flow prediction from spatiotemporal data using machine learning: a survey. Inf Fusion 59:1–12, 2020
A. Gowtham, K. Anuj, K. Vipin. Spatio-Temporal Data Mining: A Survey of Problems and Methods. ACM Computing Surveys Volume 51 Issue 4 Article No.: 83, 20, 2018.
S. Pulugurtha ; P. Kusam. Modeling Annual Average Daily Traffic with Integrated Spatial Data from Multiple Network Buffer Bandwidths. Transportation Research Record: Journal of the Transportation Research Board,2012.
Y. Haitao; L. Guoliang. A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation . Data Science and Engineering, 2021
S. Wang; J. Cao; P. Yu. Deep Learning for Spatio-Temporal Data Mining: A Survey. IEEE Transactions on Knowledge and Data Engineering, 2020.
J. Raj; H. Bahuleyan; L. D. Vanajakshi. Application of Data Mining Techniques for Traffic Density Estimation and Prediction. Transportation
Research Procedia, 2016.
S. P. Kalli, R. Seelam. An Efficient Traffic Forecasting System Based on Spatial Data and Decision Trees. The International Arab Journal of Information Technology, 2013.
M. May, D. Hecker, C. Körner, S. Scheider, D. Schulz. A Vector-Geometry Based Spatial kNN-Algorithm for Traffic Frequency Predictions. IEEE 2008 IEEE International Conference on Data Mining Workshops (ICDMW), 2008.
S. Pulugurtha; P. Kusam. Modeling Annual Average Daily Traffic with Integrated Spatial Data from Multiple Network Buffer Bandwidths. Transportation Research Record: Journal of the Transportation Research Board, 2012
A. Ermagun; S. Chatterjee; D. Levinson; X, Ma. Using temporal detrending to observe the spatial correlation of traffic. PLOS ONE, 12(5), 2017.
