An Approach to Evaluate the User Participation Pattern in Highway's Volunteered Geographic Information using Machine Learning

Document Type : Scientific - Research

Authors
Saeedeh Sadati 1
Rahim Ali abbaspour 2
Alireza Chehreghan 3
Abbas Abedini 4
1 M.Sc., School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran
2 Associate Professor, School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran
3 Associate Professor, Faculty of Mining Engineering, Sahand University of Technology, Tabriz, Iran
4 Assistant Professor, School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran
10.22119/jte.2024.435790.2695
Abstract
Highways constitute one of the busiest and most vital linear elements in a country's transportation system, and their significance has grown steadily with the expansion of urban life. Consequently, access to up-to-date and efficient information about these linear elements plays a crucial role in managing the transportation systems of nations. Volunteered Geographic Information (VGI) is generated by users who contribute their experiential or local knowledge of a specific location to a spatial database. Statistical approaches help in understanding the trends of participatory behaviors. This study examines the patterns of contributors' involvement in mapping highways and roads in the OpenStreetMap (OSM) database in Tehran. Analyzing participatory patterns provides rich information on biases, statistics, and user activity directions and shifts, which are instrumental in transportation, urban planning, and management. The proposed approach evaluates how the characteristics of a road impact its classification. Highway classes are categorized using a random forest classifier, and the inferred mapping trends are analyzed based on the classification. Linear data from Tehran city will be used for the upcoming experiment, and the classification algorithm will be applied with the extraction parameters that resulted in the highest classification accuracy. Results demonstrate that the optimal combination of extraction parameters, such as the azimuth of highways, geodesic length of lines, distance from the first mapped point to the nearest street, and the kernel density of the initial points, achieves an F-Score of 71%. An examination of the semantic parameters, such as the highway name and user name, indicates their ineffectiveness on classification accuracy. After assessing the importance of each selected parameter, the azimuth parameter is identified as the most influential factor in the classification of highway types regarding user participation behavior.

Keywords

Subjects

  • Afandizadeh , S., Javanshir , H., & Elyasi , R. (2010). Development of a model for designing urban bus transit network based on tabu search. Transportation Engineering, 5, 13-26. (in Persian)

 

  • Alenouri, H., Meshkani, S. M., Saffarzadeh, M., & Sherafaty Pour, S. (2014). Locating Cameras at the Entrances of Plate Number Rationing Zone to Maximize Violations Detection. Quarterly Journal of Transportation Engineering, 6(2), 181-196. (in Persian)

 

  • Attard, M., Haklay, M., & Capineri, C. (2016). The potential of volunteered geographic information (VGI) in future transport systems. Urban Planning, 1(4), 6-19.

 

  • Bégin, D., Devillers, R., & Roche, S. (2013). Assessing Volunteered Geographic Information (vgi) Quality Based on CONTRIBUTORS'Mapping Behaviours. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 40, 149-154.

 

  • Breiman, L. (1996). Bagging predictors. Machine learning, 24, 123-140.

 

  • Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.

 

  • Breiman, L. (2017). Classification and regression trees. Routledge.

 

  • Chehreghan, A., & Abaspour, R. (2019). "Evaluation of the geometric similarity of voluntary spatial data in the inner city road network. Transportation Engineering, 10, 357-370.. (in Persian)

 

  • Dash, M., & Liu, H. (1997). Feature selection for classification. Intelligent data analysis, 1(1-4), 131-156.

 

  • Davidovic, N., Mooney, P., & Stoimenov, L. (2016). An analysis of tagging practices and patterns in urban areas in OpenStreetMap. Proceedings of the AGILE 2016 Conference, Helsinki, Finland.

 

  • Dietterich, T. G. (2000). An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization. Machine learning, 40, 139-157.

 

  • Farideh Teymourian , A. A. A., Abass Alimohammadi and Abolghasem SadeghiNiaraki (2014). Developing a system for measuring transportation performance and information distribution of urban bus using volunteer geographic information (VGI). Transportation Engineering 6, 225-236. (in Persian)

 

  • Fogliaroni, P., D’Antonio, F., & Clementini, E. (2018). Data trustworthiness and user reputation as indicators of VGI quality. Geo-Spatial Information Science, 21(3), 213-233.

 

  • Forati, A. M., & Ghose, R. (2020). Volunteered Geographic Information Users Contributions Pattern and its Impact on Information Quality.

 

  • Girres, J. F., & Touya, G. (2010). Quality assessment of the French OpenStreetMap dataset. Transactions in GIS, 14(4), 435-459.

 

  • Goodchild, M. F. (2007). Citizens as sensors: the world of volunteered geography. GeoJournal, 69, 211-221.

 

  • Guo, H., Nguyen, H., Vu, D.-A., & Bui, X.-N. (2021). Forecasting mining capital cost for open-pit mining projects based on artificial neural network approach. Resources Policy, 74, 101474.

 

  • Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of machine learning research, 3(Mar), 1157-1182.

 

  • Hacar, M. (2020). Analyzing the Contribution Trends of Volunteers by Comparing Tag Metadata of OpenStreetMap Residential Roads [Original title in Turkish: OpenStreetMap Yerleşim-içi Yollarına Ait Etiket Bilgilerinin Karşılaştırılmasıyla Gönüllülerin Katkı Sağlama Eğilimlerinin İncelenmesi]. Harita. Dergisi, 164, 77-87.

 

  • Hacar, M. (2022). Analyzing the behaviors of OpenStreetMap volunteers in mapping building polygons using a machine learning approach. ISPRS International Journal of Geo-Information, 11(1), 70.

 

  • Hacar, M., Kılıç, B., & Şahbaz, K. (2018). Analyzing openstreetmap road data and characterizing the behavior of contributors in Ankara, Turkey. ISPRS International Journal of Geo-Information, 7(10), 400.

 

  • Haklay, M. (2010). How good is volunteered geographical information? A comparative study of OpenStreetMap and Ordnance Survey datasets. Environment and planning B: Planning and design, 37(4), 682-703.

 

  • Haklay, M., Basiouka, S., Antoniou, V., & Ather, A. (2010). How many volunteers does it take to map an area well? The validity of Linus’ law to volunteered geographic information. The cartographic journal, 47(4), 315-322.

 

  • Hastie, T., Tibshirani, R., Friedman, J. H., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction (Vol. 2). Springer.

 

  • Ishwaran, H. (2015). The effect of splitting on random forests. Machine learning, 99, 75-118.

 

  • Jokar Arsanjani, J., Helbich, M., Bakillah, M., & Loos, L. (2015). The emergence and evolution of OpenStreetMap: a cellular automata approach. International Journal of Digital Earth, 8(1), 76-90.

 

  • Li, J., Cheng, K., Wang, S., Morstatter, F., Trevino, R. P., Tang, J., & Liu, H. (2017). Feature selection: A data perspective. ACM computing surveys (CSUR), 50(6), 1-45.

 

  • Liu, H., & Motoda, H. (2007). Computational methods of feature selection. CRC press.
  • Liu, H., & Yu, L. (2005). Toward integrating feature selection algorithms for classification and clustering. IEEE Transactions on knowledge and data engineering, 17(4), 491-502.

 

  • Manandhar, P., Marpu, P. R., Aung, Z., & Melgani, F. (2019). Towards automatic extraction and updating of VGI-based road networks using deep learning. Remote Sensing, 11(9), 1012.

 

  • Mirbaha, B., SHERAFATIPOUR, S., & MAHPOUR, A. (2016). Congestion pricing model for urban congested roads (case study: sadr elevated highway). Transportation Engineering, 7, 353-365.

 

  • Mooney, P., Corcoran, P., & Winstanley, A. C. (2010). Towards quality metrics for OpenStreetMap. Proceedings of the 18th SIGSPATIAL international conference on advances in geographic information systems.

 

  • Nash, A. (2009). Web 2.0 applications for improving public participation in transport planning. Transportation Research Board 89th Annual Meeting,

 

  • Neis, P., & Zipf, A. (2012). Analyzing the contributor activity of a volunteered geographic information project—The case of OpenStreetMap. ISPRS International Journal of Geo-Information, 1(2), 146-165.

 

  • Nembrini, S., König, I. R., & Wright, M. N. (2018). The revival of the Gini importance? Bioinformatics, 34(21), 3711-3718.

 

  • Nicodemus, K. K. (2011). On the stability and ranking of predictors from random forest variable importance measures. Briefings in bioinformatics, 12(4), 369-373.

 

  • O'reilly, T. (2007). What is Web 2.0: Design patterns and business models for the next generation of software. Communications & strategies(1), 17.

 

 

  • Pal, M. (2005). Random forest classifier for remote sensing classification. International journal of remote sensing, 26(1), 217-222.

 

  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., & Dubourg, V. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.

 

  • Rehrl, K., & Gröchenig, S. (2016). A framework for data-centric analysis of mapping activity in the context of volunteered geographic information. ISPRS International Journal of Geo-Information, 5(3), 37.

 

  • Saberian, J., Malek, M., & Hamrah, M. (2014). Using Dual Graph and Wavelet Transform for Evaluation and Planning Transportation systems. Transportation Engineering, 5, 317-328. (in Persian)

 

  • Strobl, C., Boulesteix, A.-L., Zeileis, A., & Hothorn, T. (2007). Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC bioinformatics, 8(1), 1-21.

 

  • Zhao, P., Jia, T., Qin, K., Shan, J., & Jiao, C. (2015). Statistical analysis on the evolution of OpenStreetMap road networks in Beijing. Physica A: Statistical Mechanics and its Applications, 420, 59-72.
Quarterly Journal of Transportation Engineering
Volume 16, Issue 3 - Serial Number 64
Winter 2025
Pages 4645-4666

  • Receive Date 15 January 2024
  • Revise Date 19 March 2024
  • Accept Date 20 April 2024