Abstract

Trip generation models are traditionally developed using linear regression. This study focuses on enhancing trip generation models by exploring the potential of support vector machine (SVM) based models. The primary objective is to improve the accuracy and efficiency of travel demand estimation for transportation planning. To achieve this, SVM models were constructed using the radial basis function (RBF) and linear kernel functions and then compared to conventional linear regression models. The performance of these models was evaluated to determine their effectiveness in predicting trip production and attraction. The results revealed that the SVM model with the RBF kernel outperformed both the SVM model with the linear kernel and the traditional linear regression model. Specifically, the R2 for the trip production and trip attraction predictions using the RBF kernel were 1 and 0.95, respectively. Additionally, the Kruskal Wallis (KW) test was employed to assess the statistical significance of the differences between the models. The findings suggest that SVM models, particularly those utilizing the RBF kernel, offer a superior alternative to conventional regression models for trip generation, providing transportation planners with a more efficient tool for travel demand estimation.

Keyword

Trip generation, Support vector machine, Radial basis function kernel, Linear regression, Travel demand estimation, Transportation planning.

Cite this article

Kumar A, Kumar A, Sinha S.Advancing urban transportation planning: a comparative analysis of machine learning and conventional regression-based trip generation models. International Journal of Advanced Technology and Engineering Exploration. 2024;11(121):1768-1783. DOI:10.19101/IJATEE.2024.111100198

Refference

[1]Smart A, Smart J. Urbanization and the global perspective. Annual Review of anthropology. 2003; 32(1):263-85.

[2]https://www.un.org/development/desa/pd/sites/ospects-2017_revision_databooklet.pdf. Accessed 25 November 2024.

[3]Goldman T, Gorham R. Sustainable urban transport: four innovative directions. Technology in Society. 2006; 28(1-2):261-73.

[4]Oladimeji D, Gupta K, Kose NA, Gundogan K, Ge L, Liang F. Smart transportation: an overview of technologies and applications. Sensors. 2023; 23(8):1-32.

[5]Dodeen AM. Developing trip generation models utilizing linear regression analysis: Jericho city as a case study. Doctoral Dissertation, An-Najah National University, Nablus. 2014.

[6]Sofia GG, Ali AH, Al-zubaidy HA. Trip generation modeling for selected zone in Al-Diwaniyah city. Journal of Engineering and Sustainable Development. 2012; 16(4):167-80.

[7]De OLK, Herédia RT, Bertoncini BV, De ORL. Freight trip generation to buildings under construction: a comparative analysis with linear regression and generalised linear regression. Transportes. 2020; 28(5):28-42.

[8]Monzon J, Goulias K, Kitamura R. Trip generation models for infrequent trips. Transportation Research Record. 1989; 1220:40-6.

[9]Amavi AA, Romero JP, Dominguez A, Dell’olio L, Ibeas A. Advanced trip generation/attraction models. Procedia-Social and Behavioral Sciences. 2014; 160:430-9.

[10]Cordera R, Coppola P, Dell’olio L, Ibeas Á. Is accessibility relevant in trip generation modelling the interaction between trip generation and accessibility taking into account spatial effects. Transportation. 2017; 44:1577-603.

[11]Chang JS, Jung D, Kim J, Kang T. Comparative analysis of trip generation models: results using home-based work trips in the Seoul metropolitan area. Transportation Letters. 2014; 6(2):78-88.

[12]Triantakonstantis D, Mountrakis G. Urban growth prediction: a review of computational models and human perceptions. Journal of Geographic Information System. 2012; 4(6): 555-87.

[13]Wegener M. Overview of land use transport models. In handbook of transport geography and spatial systems 2004 (pp. 127-46). Emerald Group Publishing Limited.

[14]Linard C, Tatem AJ, Gilbert M. Modelling spatial patterns of urban growth in Africa. Applied Geography. 2013; 44:23-32.

[15]Banister D. Cities, mobility and climate change. Journal of Transport Geography. 2011; 19(6):1538-46.

[16]Liu Z, Liu Y, Meng Q, Cheng Q. A tailored machine learning approach for urban transport network flow estimation. Transportation Research Part C: Emerging Technologies. 2019; 108:130-50.

[17]Müller-hannemann M, Rückert R, Schiewe A, Schöbel A. Estimating the robustness of public transport schedules using machine learning. Transportation Research Part C: Emerging Technologies. 2022; 137:103566.

[18]Chaturvedi V, De VWT. Machine learning algorithms for urban land use planning: a review. Urban Science. 2021; 5(3):1-16.

[19]Surden H. Machine learning and law: an overview. Research Handbook on Big Data Law. 2021:171-84.

[20]Tripathi RP, Pandey K. Gene-expression programming for scour around spur dike. International Journal of Hydrology Science and Technology. 2023; 15(3):295-303.

[21]Talpur MA, Khahro SH, Ali TH, Waseem HB, Napiah M. Computing travel impendences using trip generation regression model: a phenomenon of travel decision-making process of rural households. Environment, Development and Sustainability. 2023; 25(7):5973-96.

[22]Kumar A, Sinha S, Pandey D, Maurya MC, Chauhan VB. Advanced regression models for assessing the strength of multi-walled carbon nanotube-modified high-volume fly ash concrete. Asian Journal of Civil Engineering. 2024; 25(2):2247-68.

[23]Gupta N, Patel J, Gond S, Tripathi RP, Omar PJ, Dikshit PK. Projecting future maximum temperature changes in river Ganges basin using observations and statistical downscaling model (SDSM). In river dynamics and flood hazards: studies on risk and mitigation 2022 (pp. 561-85). Singapore: Springer Nature Singapore.

[24]Parsaie A, Haghiabi AH, Latif SD, Tripathi RP. Predictive modelling of piezometric head and seepage discharge in earth dam using soft computational models. Environmental Science and Pollution Research. 2021; 28(43):60842-56.

[25]Kumar A, Sinha S. Policy options for sustainable urban transportation: a quadrant analysis approach. In risk, reliability and sustainable remediation in the field of civil and environmental engineering 2022 (pp. 487-97). Elsevier.

[26]Ranjan R, Sinha S. Mode choice analysis for work trips of urban residents using multinomial logit model. Innovative Infrastructure Solutions. 2024; 9(10):1-4.

[27]Kumar R, Madhu E, Dahiya A, Sinha S. Analytical hierarchy process for assessing sustainability: indicators of public transportation systems, pedestrians and feeder services in developing countries. World Journal of Science, Technology and Sustainable Development. 2015; 12(4):281-93.

[28]Mcnally MG. The four-step model. In handbook of transport modelling 2007 (pp. 35-53). Emerald Group Publishing Limited.

[29]Shan R, Zhong M, Du D, Lu C. Comparison of trip generation results from activity-based and traditional four-step travel demand modeling: a case study of Tampa, Florida. In conference of the transportation association of Canada 2012 (pp. 1-19).

[30]Mustafa RA. Developing a high-fidelity GIS-based travel demand model framework for improved network-wide traffic estimation. Doctoral Dissertation, The University of New Brunswick. 2019.

[31]Sarna AC, Prakash A, Mukhopadhaya D, Bhatia N, Suthar HH. Planning of mass rapid transit system-a case study of Delhi. In Journal of the Indian Roads Congress 1992; 53(3):553-88.

[32]Anderson MD, Olander JP. Evaluation of two trip generation techniques for small area travel models. Journal of Urban Planning and Development. 2002; 128(2):77-88.

[33]Navya SV, Kumar SS, Kattoor GJ. Trip generation model for the core area of Thiruvananthapuram city. International Journal of Innovative Research in Science, Engineering and Technology. 2013; 2(1):99-106.

[34]Pangotra P, Sharma S. Modeling travel demand in a metropolitan city case study of Bangalore, India. IIM Ahmedabad, 2006.

[35]Walker J, Li J, Srinivasan S, Bolduc D. Travel demand models in the developing world: correcting for measurement errors. Transportation Letters. 2010; 2(4):231-43.

[36]Tiwari G, Jain D. Accessibility and safety indicators for all road users: case study Delhi BRT. Journal of Transport Geography. 2012; 22:87-95.

[37]Abdel-aal MM. Calibrating a trip distribution gravity model stratified by the trip purposes for the city of Alexandria. Alexandria Engineering Journal. 2014; 53(3):677-89.

[38]Jin PJ, Cebelak M, Yang F, Zhang J, Walton CM, Ran B. Location-based social networking data: exploration into use of doubly constrained gravity model for origin–destination estimation. Transportation Research Record. 2014; 2430(1):72-82.