A hybrid ensemble forecasting model of passenger flow based on improved variational mode decomposition and boosting

Xiwen Qin; Chunxiao Leng; Xiaogang Dong; Xiwen Qin; Chunxiao Leng; Xiaogang Dong

doi:10.3934/mbe.2024014

Mathematical Biosciences and Engineering

2024, Volume 21, Issue 1: 300-324. doi: 10.3934/mbe.2024014

Previous Article Next Article

Research article

A hybrid ensemble forecasting model of passenger flow based on improved variational mode decomposition and boosting

School of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, China

Received: 05 September 2023 Revised: 27 November 2023 Accepted: 05 December 2023 Published: 12 December 2023

An accurate passenger flow forecast can provide key information for intelligent transportation and smart cities, and help promote the development of smart cities. In this paper, a mixed passenger flow forecasting model based on the golden jackal optimization algorithm (GJO), variational mode decomposition (VMD) and boosting algorithm was proposed. First, the data characteristics of the original passenger flow sequence were extended. Second, an improved variational modal decomposition method based on the Sobol sequence improved GJO algorithm was proposed. Next, according to the sample entropy of each intrinsic mode function (IMF), IMF with similar complexity is combined into a new subsequence. Finally, according to the determination rules of the sub-sequence prediction model, the boosting modeling and prediction of different sub-sequences were carried out, and the final passenger flow prediction result was obtained. Based on the experimental results of three scenic spots, the mean absolute percentage error (MAPE) of the mixed set model is 0.0797, 0.0424 and 0.0849, respectively. The fitting degree reached 95.33%, 95.63% and 95.97% simultaneously. The results show that the hybrid model proposed in this study has high prediction accuracy and can provide reliable information sources for relevant departments, scenic spot managers and tourists.
- scenic passenger flow,
- golden jackal optimization,
- variational mode decomposition,
- boosting,
- hybrid ensemble model
Citation: Xiwen Qin, Chunxiao Leng, Xiaogang Dong. A hybrid ensemble forecasting model of passenger flow based on improved variational mode decomposition and boosting[J]. Mathematical Biosciences and Engineering, 2024, 21(1): 300-324. doi: 10.3934/mbe.2024014

Related Papers:

Abstract

An accurate passenger flow forecast can provide key information for intelligent transportation and smart cities, and help promote the development of smart cities. In this paper, a mixed passenger flow forecasting model based on the golden jackal optimization algorithm (GJO), variational mode decomposition (VMD) and boosting algorithm was proposed. First, the data characteristics of the original passenger flow sequence were extended. Second, an improved variational modal decomposition method based on the Sobol sequence improved GJO algorithm was proposed. Next, according to the sample entropy of each intrinsic mode function (IMF), IMF with similar complexity is combined into a new subsequence. Finally, according to the determination rules of the sub-sequence prediction model, the boosting modeling and prediction of different sub-sequences were carried out, and the final passenger flow prediction result was obtained. Based on the experimental results of three scenic spots, the mean absolute percentage error (MAPE) of the mixed set model is 0.0797, 0.0424 and 0.0849, respectively. The fitting degree reached 95.33%, 95.63% and 95.97% simultaneously. The results show that the hybrid model proposed in this study has high prediction accuracy and can provide reliable information sources for relevant departments, scenic spot managers and tourists.

References

[1]	J. D. Ortúzar, Future transportation: Sustainability, complexity and individualization of choices, Commun. Transp. Res., 1 (2021). https://doi.org/10.1016/j.commtr.2021.100010 doi: 10.1016/j.commtr.2021.100010
[2]	X. Nan, K. Kayo, Role of information security-based tourism management system in the intelligent recommendation of tourism resources, Math. Biosci. Eng., 18 (2021), 7955–7964. https://doi.org/10.3934/mbe.2021394 doi: 10.3934/mbe.2021394
[3]	F. L. Chu, Forecasting tourism demand with ARMA-based methods, Tourism Manage., 30 (2009), 740–751. https://doi.org/10.1016/j.tourman.2008.10.016 doi: 10.1016/j.tourman.2008.10.016
[4]	M. Geurts, Forecasting the Hawaiian tourist market, J. Travel Res., 21 (1982), 18–21. https://doi.org/10.1177/004728758202100105 doi: 10.1177/004728758202100105
[5]	M. Milenković, L. Švadlenka, V. Melichar, N. Bojovic, Z. Avramovi, SARIMA modelling approach for railway passenger flow forecasting, Transport, 33 (2016), 1113–1120. https://doi.org/10.3846/16484142.2016.1139623 doi: 10.3846/16484142.2016.1139623
[6]	Q. Chen, W. Q. Li, J. H. Zhao, The use of LS-SVM for short–term passenger flow prediction, Transport, 26 (2011), 5–10. https://doi.org/10.3846/16484142.2011.555472 doi: 10.3846/16484142.2011.555472
[7]	H. Y. Li, Y. T. Wang, X. Y. Xu, L. Q. Qin, H. Y. Zhang, Short-term passenger flow prediction under passenger flow control using a dynamic radial basis function network, Appl. Soft Comput., 83 (2019), 1568–4946. https://doi.org/10.1016/j.asoc.2019.105620 doi: 10.1016/j.asoc.2019.105620
[8]	Z. W. Gao, J. Q. Zhang, Z. J Xu, X. D. Zhang, R. X. Shi, J. C. Wang, et al., Method of predicting passenger flow in scenic areas considering multisource traffic data, Sens. Mater., 32 (2020), 3907–3921. https://doi.org/10.18494/SAM.2020.2970 doi: 10.18494/SAM.2020.2970
[9]	W. X. Lu, H. D. Rui, C. Y. Liang, L. Jiang, S. P. Zhao, K. Q. Li, A method based on GA-CNN-LSTM for daily tourist flow prediction at scenic spots, Entropy, 22 (2020), 261. https://doi.org/10.3390/e22030261 doi: 10.3390/e22030261
[10]	L. Zou, S. S. Shu, X. Lin, K. S. Lin, J. S. Zhu, L. C. Li, Passenger flow prediction using smart card data from connected bus system based on interpretable XGBoost, Wireless Commun. Mobile Comput., 2022 (2022), https://doi.org/10.1155/2022/5872225 doi: 10.1155/2022/5872225
[11]	Y. J. Tan, B. Sun, L. Guo, B. B. Jing, Novel model for integrated demand–responsive transit service considering rail transit schedule, Mathe. Biosci. Eng., 19 (2022), 12371–12386. https://doi.org/10.3934/mbe.2022577 doi: 10.3934/mbe.2022577
[12]	Y. Liu, Z. Y. Liu, R. Jia, DeepPF: A deep learning based architecture for metro passenger flow prediction, Transp. Rese. Part C, 101 (2019), 18–34. https://doi.org/10.1016/j.trc.2019.01.027 doi: 10.1016/j.trc.2019.01.027
[13]	Y. Liu, F. Y. Wu, Z. Y. Liu, K. Wang, F. Y. Wang, X. B. Qu, Can language models be used for real-world urban-delivery route optimization?, Innovation, 4 (2023), https://doi.org/10.1016/j.xinn.2023.100520 doi: 10.1016/j.xinn.2023.100520
[14]	N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. A. Zheng, et al., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non–stationary time series analysis, Proc. R. Soc. Lond. A., 454 (1998), 903–995. https://doi.org/10.1098/rspa.1998.0193 doi: 10.1098/rspa.1998.0193
[15]	J. Gilles, Empirical wavelet transform, IEEE Trans. Signal Process., 61 (2013), 3999–4010. https://doi.org/10.1109/TSP.2013.2265222 doi: 10.1109/TSP.2013.2265222
[16]	Z. H. Wu, N. E. Huang, Ensemble empirical mode decomposition: A noise-assisted data analysis method, Adv. Adapt. Data Anal., 1 (2009), 1–41. https://doi.org/10.1142/S1793536909000047 doi: 10.1142/S1793536909000047
[17]	K. Dragomiretskiy, D. Zosso, Variational mode decomposition, IEEE Trans. Signal Process., 62 (2014), 531–544. https://doi.org/10.1109/TSP.2013.2288675 doi: 10.1109/TSP.2013.2288675
[18]	Y. Wei, M. C. Chen, Forecasting the short–term metro passenger flow with empirical mode decomposition and neural networks, Transp. Res. Part C, 21 (2012), 148–162. https://doi.org/10.1016/j.trc.2011.06.009 doi: 10.1016/j.trc.2011.06.009
[19]	R. J. Liu, Y. H. Wang, H. Zhou, Z. Q. Qian, Short-term passenger flow prediction based on wavelet transform and kernel extreme learning machine, IEEE Access, 7 (2019), 158025–158034. https://doi.org/10.1109/ACCESS.2019.2950327 doi: 10.1109/ACCESS.2019.2950327
[20]	Y. Cao, X. L. Hou, N. Chen, Short-term forecast of OD passenger flow based on ensemble empirical mode decomposition, Sustainability, 14 (2022), 8562. https://doi.org/10.3390/su14148562 doi: 10.3390/su14148562
[21]	H. R. Cui, X. X. Yang, Y. L. Yu, Prediction of tourists flow based on EMD-GRU model: A case study of Black Valley scenic area in Chongqing, J. China West Normal Univ., 44 (2023), 179–185.
[22]	Y. L. Bai, M. D. Liu, L. Ding, Y. J. Ma, Double-layer staged training echo-state networks for wind speed prediction using variational mode decomposition, Appl. Energy, 301 (2021), 117461. https://doi.org/10.1016/j.apenergy.2021.117461 doi: 10.1016/j.apenergy.2021.117461
[23]	X. R. Wang, X. Y. Li, S. T. Li, Point and interval forecasting system for crude oil price based on complete ensemble extreme–point symmetric mode decomposition with adaptive noise and intelligent optimization algorithm, Appl. Energy, 328 (2022), 120194. https://doi.org/10.1016/j.apenergy.2022.120194 doi: 10.1016/j.apenergy.2022.120194
[24]	H. L. Niu, Y. Z. Zhao, Crude oil prices and volatility prediction by a hybrid model based on kernel extreme learning machine, Math. Biosci. Eng., 18 (2021), 8096–8122. https://doi.org/10.3934/mbe.2021402 doi: 10.3934/mbe.2021402
[25]	J. J. Wang, Q. Cui, M. L He, Hybrid intelligent framework for carbon price prediction using improved variational mode decomposition and optimal extreme learning machine, Chaos Solitons Fractals, 156 (2022), 111783. https://doi.org/10.1016/j.chaos.2021.111783 doi: 10.1016/j.chaos.2021.111783
[26]	S. Boyd, N. Parikh, E. Chu, B. Peleato, J. Eckstein, Distributed optimization and statistical learning via the alternating direction method of multipliers, FNT Mach. Learn., 3 (2010), 1–122. https://doi.org/10.1561/2200000016 doi: 10.1561/2200000016
[27]	N. Chopra, M. M. Ansari, Golden jackal optimization: A novel nature-inspired optimizer for engineering applications, Exp. Syst. Appl., 198 (2022), 116924. https://doi.org/10.1016/j.eswa.2022.116924 doi: 10.1016/j.eswa.2022.116924
[28]	X. Z. Gao, L. Wang, J. Tian, J. L. Liu, Q. H. Liu, et al., Research on hybrid energy storage power distribution strategy based on parameter optimization variational mode decomposition, Energy Storage Sci. Technol., 11 (2022), 147–155.
[29]	Y. Freund, R. E. Schapire, A Decision-theoretic generalization of on-line learning and an application to boosting, J. Comput. Syst. Sci., 55 (1997), 119–139. https://doi.org/10.1006/jcss.1997.1504 doi: 10.1006/jcss.1997.1504
[30]	J. H. Friedman, Greedy function approximation: A gradient boosting machine, Ann. Stat., 29 (2001). https://doi.org/10.1214/aos/1013203451 doi: 10.1214/aos/1013203451
[31]	G. L. Ke, Q. Meng, T. Finley, T. F.Wamg, W.Chen, W. D. Ma, et al., LightGBM: A highly efficient gradient boosting decision tree, Adv. Neural Inf. Process. Syst., 2017 (2017), 30.
[32]	T. Q. Chen, C. Guestrin, XGBoost: A scalable tree boosting system, Assoc. Comput. Mach., 2016 (2016), 785–794. https://doi.org/10.1145/2939672.2939785 doi: 10.1145/2939672.2939785
[33]	L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, A. Gulin, CatBoost: unbiased boosting with categorical features, Adv. Neural Inf. Process. Syst., 2018 (2018), 31.
[34]	J. Z. Wang, Y. Wang, H. M. Li, H. F. Yang, Z. W. Liu, Ensemble forecasting system based on decomposition–selection–optimization for point and interval carbon price prediction, Appl. Math. Modell., 113 (2023), 262–286. https://doi.org/10.1016/j.apm.2022.09.004 doi: 10.1016/j.apm.2022.09.004

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)