Academic Journal of Computing & Information Science, 2023, 6(6); doi: 10.25236/AJCIS.2023.060601.
Tian Xie1,2, Yan Fang2
1China Design Group Co., Ltd., Nanjing, China
2College of Transport & Communications, Shanghai Maritime University, Shanghai, China
In response to worsening traffic congestion, cities worldwide have prioritized the development of public transportation systems, striving to become 'public transport cities.' To address this issue, conducting an in-depth study of residents' travel choice behavior during peak hours is of vital importance. The paper aims to consider the key factors affecting residents' travel decisions by utilizing revealed preference (RP) samples and proposes a novel RL-SVM model based on the random parameter logit (RL) and support vector machine (SVM) theories for travel mode prediction. Comparative experimental analysis shows that our model outperforms traditional prediction methods regarding classification sensitivity. Therefore, we can further evaluate the anticipated impact of implementing public transport priority strategies to obtain the internal shift patterns of commuters' travel modes from private cars to public transport. It holds significant implications for promoting healthy and sustainable urban development.
Commuting travel; Public transport; Travel mode choice; Random parameter logit; Support vector machine
Tian Xie, Yan Fang. Modeling of Residents' Travel Mode Choice Decisions during Peak Commuting Hours via RL-SVM Method. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 6: 1-7. https://doi.org/10.25236/AJCIS.2023.060601.
[1] Xianyu J. An exploration of the interdependencies between trip chaining behavior and travel mode choice[J]. Procedia-Social and Behavioral Sciences, 2013, 96: 1967-1975.
[2] Ermagun A, Levinson D. Public transit, active travel, and the journey to school: a cross-nested logit analysis[J]. Transportmetrica A: Transport Science, 2017, 13(1): 24-37.
[3] Liu J, Hao X. Travel mode choice in city based on random parameters logit model[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(5): 6.
[4] Omrani H. Predicting travel mode of individuals by machine learning[J]. Transportation research procedia, 2015, 10: 840-849.
[5] Chen Y, Chen L, Zha Q, et al. Forecasting model of travel mode based on latent variable SVM[J]. Journal of Southeast University, 2016, 46(6): 1314-1317.
[6] Xu Z, Shao C, Wang S, et al. Analysis and Prediction Model of Resident Travel Satisfaction[J]. Sustainability, 2020, 12(18):7522.
[7] Hensher D A, Greene W H. The mixed logit model: the state of practice and warnings for the unwary[M]. General Information, 2002, 30(2): 133-176.
[8] Hua Z, Yu W, Xu X, et al. Predicting corporate financial distress based on integration of support vector machine and logistic regression[J]. Expert Systems with Applications, 2007, 33(2):434-440.
[9] McDonald Gary C. Ridge regression[J]. Wiley Interdisciplinary Reviews: Computational Statistics, 2009, 1(1): 93-100.
[10] Omuya E O, Okeyo G O, Kimwele M W. Feature selection for classification using principal component analysis and information gain[J]. Expert Systems with Applications, 2021, 174: 114765.
[11] Yu Q, Liu R. Least Squares Twin SVM Based on Partial Binary Tree Algorithm[C]//2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). IEEE, 2018: 1-4.
[12] Syarif I, Prugel-Bennett A, Wills G. SVM parameter optimization using grid search and genetic algorithm to improve classification performance [J]. TELKOMNIKA (Telecommunication Computing Electronics and Control), 2016, 14(4): 1502-1509.
[13] Zhang Y, Zhu C, Wang Q. LightGBM-based model for metro passenger volume forecasting[J]. IET Intelligent Transport Systems, 2020, 14(13): 1815-1823.