Open Access
Issue
Published:
16 August 2018
A Hybrid Forecasting Framework Based on Support Vector Regression with a Modified Genetic Algorithm and a Random Forest for Traffic Flow Prediction
Nawaf R Alharbe(
),
),
Keywords:
machine learning, feature selection, genetic algorithm, parameter optimization, traffic flow forecasting
Cite this article:
Zhang L, Alharbe NR, Luo G, et al.
A Hybrid Forecasting Framework Based on Support Vector Regression with a Modified Genetic Algorithm and a Random Forest for Traffic Flow Prediction.
Tsinghua Science and Technology,
2018, 23(4): 479-492.
https://doi.org/10.26599/TST.2018.9010045
Download citation
593
Views
24
Downloads
Citations
61
Crossref
N/A
WoS
76
Scopus
4
CSCD
The ability to perform short-term traffic flow forecasting is a crucial component of intelligent transportation systems. However, accurate and reliable traffic flow forecasting is still a significant issue due to the complexity and variability of real traffic systems. To improve the accuracy of short-term traffic flow forecasting, this paper presents a novel hybrid prediction framework based on Support Vector Regression (SVR) that uses a Random Forest (RF) to select the most informative feature subset and an enhanced Genetic Algorithm (GA) with chaotic characteristics to identify the optimal forecasting model parameters. The framework is evaluated with real-world traffic data collected from eight sensors located near the I-605 interstate highway in California. Results show that the proposed RF-CGASVR model achieves better performance than other methods.
menu
Abstract
Full text
Outline
About this article
A Hybrid Forecasting Framework Based on Support Vector Regression with a Modified Genetic Algorithm and a Random Forest for Traffic Flow Prediction
Nawaf R Alharbe(
),
),
Abstract
The ability to perform short-term traffic flow forecasting is a crucial component of intelligent transportation systems. However, accurate and reliable traffic flow forecasting is still a significant issue due to the complexity and variability of real traffic systems. To improve the accuracy of short-term traffic flow forecasting, this paper presents a novel hybrid prediction framework based on Support Vector Regression (SVR) that uses a Random Forest (RF) to select the most informative feature subset and an enhanced Genetic Algorithm (GA) with chaotic characteristics to identify the optimal forecasting model parameters. The framework is evaluated with real-world traffic data collected from eight sensors located near the I-605 interstate highway in California. Results show that the proposed RF-CGASVR model achieves better performance than other methods.
Keywords:
machine learning, feature selection, genetic algorithm, parameter optimization, traffic flow forecasting
References(55)
[1]
Y. Huang, X. Guan, Z. P. Cai, and T. Ohtsuki, Multicast capacity analysis for social-proximity urban bus-assisted vanets, in Proc. 2013 IEEE Int. Conf. Communications (ICC), Budapest, Hungary, 2013, pp. 6138-6142.
[2]
X. Zheng, Z. P. Cai, J. Z. Li, and H. Gao, An application-aware scheduling policy for real-time traffic, in Proc. 2015 IEEE 35@th Int. Conf. Distributed Computing Systems, Columbus, OH, USA, 2015, pp. 421-430.
[3]
X. Guan, Y. Huang, Z. P. Cai, and T. Ohtsuki, Intersection-based forwarding protocol for vehicular ad hoc networks, Telecommun. Syst., vol. 62, no. 1, pp. 67-76, 2016.
[4]
Y. Huang, M. Chen, Z. P. Cai, X. Guan, T. Ohtsuki, and Y. Zhang, Graph theory based capacity analysis for vehicular ad hoc networks, in Proc. 2015 IEEE Global Communications Conf. (GLOBECOM), San Diego, CA, USA, 2015, pp. 1-5.
[5]
L. A. Tang, J. W. Han, and G. F. Jiang, Mining sensor data in cyber-physical systems, Tsinghua Sci. Technol., vol. 19, no. 3, pp. 225-234, 2014.
[6]
X. J. Wang, L. J. Guo, C. Y. Ai, J. B. Li, and Z. P. Cai, An urban area-oriented traffic information query strategy in VANETs, in Wireless Algorithms, Systems, and Applications, K. Ren, X. Liu, W. F. Liang, M. Xu, X. H. Jia, and K. Xing, eds. Springer, 2013, pp. 313-324.
[7]
M. van der Voort, M. Dougherty, and S. Watson, Combining kohonen maps with ARIMA time series models to forecast traffic flow, Transport. Res. C Emer. Technol., vol. 4, no. 5, pp. 307-318, 1996.
[8]
H. K. Hong, W. H. Huang, X. B. Zhou, S. Z. Du, K. G. Bian, and K. Q. Xie, Short-term traffic flow forecasting: Multi-metric KNN with related station discovery, in Proc. 2015 12@th Int. Conf. Fuzzy Systems and Knowledge Discovery (FSKD), Zhangjiajie, China, 2015, pp. 1670-1675.
[9]
J. H. Guo, W. Huang, and B. M. Williams, Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification, Transport. Res. C Emer. Technol., vol. 43, pp. 50-64, 2014.
[10]
G. Q. Yu and C. S. Zhang, Switching ARIMA model based forecasting for traffic flow, in Proc. 2004 IEEE Int. Conf. Acoustics, Speech, and Signal Processing, Montreal, Canada, vol. 2, pp. ii–429–ii–432, 2004.
[11]
K. I. Wong and Y. C. Hsieh, Short-term traffic flow forecasting for urban roads using space-time ARIMA, in Transportation and Urban Sustainability, Hong Kong, China, 2010.
[12]
X. B. Li, RBF neural network optimized by particle swarm optimization for forecasting urban traffic flow, in Proc. 2009 Third Int. Symp. Intelligent Information Technology Application, Shanghai, China, 2009, pp. 124-127.
[13]
X. Y. Kuang, L. H. Xu, Y. G. Huang, and F. L. Liu, Real-time forecasting for short-term traffic flow based on general regression neural network, in Proc. 2010 8@th World Congress on Intelligent Control and Automation, Ji’nan, China, 2010, pp. 2776-2780.
[14]
G. L. Duan, P. Liu, P. Chen, Q. Jiang, and N. Li, Short-term traffic flow prediction based on rough set and support vector machine, in Proc. 2011 Eighth Int. Conf. Fuzzy Systems and Knowledge Discovery (FSKD), Shanghai, China, 2011, pp. 1526-1530.
[15]
H. Y. Wang and Y. Z. Wang, Vessel traffic flow forecasting with the combined model based on support vector machine, in Proc. 2015 Int. Conf. Transportation Information and Safety (ICTIS), Wuhan, China, 2015, pp. 695-698.
[16]
M. G. Arenas, N. Rico, V. M. Rivas, P. Castillo, A. Fernandez-Ares, P. Garcia-Fernandez, P. Garcia-Sanchez, A. M. Mora, J. J. Asensio, G. Romero, et al., Traffic flow forecasting in real world, in Int. Work-Conf. Time Series (ITISE 2014), 2014, pp. 1436-1445.
[17]
N. Sánchez-Maroño, A. Alonso-Betanzos, and M. Tombilla-Sanromán, Filter methods for feature selection–A comparative study, in Proc. 8th Int. Conf. Intelligent Data Engineering and Automated Learning–IDEAL 2007, Birmingham, UK, 2007, pp. 178-187.
[18]
R. Kohavi and G. H. John, Wrappers for feature subset selection, Artif. Intell., vol. 97, nos. 1&2, pp. 273-324, 1997.
[19]
C. Yao, Y. F. Liu, B. Jiang, J. G. Han, and J. W. Han, LLE score: A new filter-based unsupervised feature selection method based on nonlinear manifold embedding and its application to image recognition, IEEE Trans. Image Process., vol. 26, no. 11, pp. 5257-5269, 2017.
[20]
C. L. Huang and C. Y. Tsai, A hybrid SOFM-SVR with a filter-based feature selection for stock market forecasting, Expert Syst. Appl., vol. 36, no. 2, pp. 1529-1539, 2009.
[21]
J. G. Zhu, S. T. Wang, X. S. Wu, and F. L. Chung, A novel adaptive SVR based filter ASBF for image restoration, Soft Comput., vol. 10, no. 8, pp. 665-672, 2006.
[22]
M. Aladeemy, S. Tutun, and M. T. Khasawneh, A new hybrid approach for feature selection and support vector machine model selection based on self-adaptive cohort intelligence, Expert Syst. Appl., vol. 88, pp. 118-131, 2017.
[23]
S. Maldonado and R. Weber, A wrapper method for feature selection using support vector machines, Inf. Sci., vol. 179, no. 13, pp. 2208-2217, 2009.
[24]
J. Kennedy and R. Eberhart, Particle swarm optimization, in Proc. 1995 IEEE Int. Conf. Neural Networks, Perth, Australia, vol. 4, pp. 1942-1948, 1995.
[25]
X. Q. Wang and J. Gao, Application of particle swarm optimization for tuning the SVR parameters, in Proc. 2015 IEEE Int. Conf. Advanced Intelligent Mechatronics (AIM), Busan, South Korea, 2015, pp. 1173-1177.
[26]
P. Duan, K. G. Xie, T. T. Guo, and X. G. Huang, Short-term load forecasting for electric power systems using the PSO-SVR and FCM clustering techniques, Energies, vol. 4, no. 1, pp. 173-184, 2011.
[27]
H. H. Tsai, Y. J. Jhuang, and Y. S. Lai, An SVD-based image watermarking in wavelet domain using SVR and PSO, Appl. Soft Comput., vol. 12, no. 8, pp. 2442-2453, 2012.
[28]
M. W. Li, W. C. Hong, and H. G. Kang, Urban traffic flow forecasting using Gauss-SVR with cat mapping, cloud model and PSO hybrid algorithm, Neurocomputing, vol. 99, pp. 230-240, 2013.
[29]
D. Bertsimas and J. Tsitsiklis, Simulated annealing, Statist. Sci., vol. 8, no. 1, pp. 10-15, 1993.
[30]
Y. F. Tan, Z. H. Jia, X. Z. Qin, C. Chang, and H. Wang, Application of SA-SVR in mobile communication traffic forecasting, (in Chinese), Comput. Eng., vol. 36, no. 22, pp. 195-196, 2010.
[31]
W. C. Hong, Traffic flow forecasting by seasonal SVR with chaotic simulated annealing algorithm, Neurocomputing, vol. 74, nos. 12&13, pp. 2096-2107, 2011.
[32]
D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning. Boston, MA, USA: Addison-Wesley, 1989.
[33]
M. Mia and N. R. Dhar, Prediction and optimization by using SVR, RSM and GA in hard turning of tempered AISI 1060 steel under effective cooling condition, Neural Comput. Appl., .
[34]
L. Chato, S. Tayeb, and S. Latifi, A genetic algorithm to optimize the adaptive Support Vector Regression model for forecasting the reliability of diesel engine systems, in Proc. 2017 IEEE 7@th Annu. Computing and Communication Workshop and Conf. (CCWC), Las Vegas, NV, USA, 2017, pp. 1-7.
[35]
H. Shafizadeh-Moghadam, A. Tayyebi, M. Ahmadlou, M. R. Delavar, and M. Hasanlou, Integration of genetic algorithm and multiple kernel support vector regression for modeling urban growth, Comput. Environ. Urban Syst., vol. 65, pp. 28-40, 2017.
[36]
C. Mandriota, M. Nitti, N. Ancona, E. Stella, and A. Distante, Filter-based feature selection for rail defect detection, Mach. Vis. Appl., vol. 15, no. 4, pp. 179-185, 2004.
[37]
Z. B. Cao, Y. Wang, Y. Sun, W. Du, and Y. C. Liang, Effective and stable feature selection method based on filter for gene signature identification in paired microarray data, in Proc. 2013 IEEE Int. Conf. Bioinformatics and Biomedicine, Shanghai, China, 2013, pp. 189-192.
[38]
K. Y. Leong, A. Sitiol, and K. S. Anbananthen, Enhance neural networks training using GA with chaos theory, in Proc. 6@th Int. Symp. Neural Networks: Advances in Neural Networks - Part II, Wuhan, China, 2009, pp. 520-529.
[39]
C. Cortes and V. Vapnik, Support-vector networks, Mach. Learn., vol. 20, no. 3, pp. 273-297, 1995.
[40]
M. S. Emami and K. Omar, A low-cost method for reliable ownership identification of medical images using SVM and Lagrange duality, Expert Syst. Appl., vol. 40, no. 18, pp. 7579-7587, 2013.
[41]
H. Z. Yang, X. G. Shao, and F. Ding, A new smooth support vector regression based on ε
[42]
O. L. Mangasarian and D. R. Musicant, Robust linear and support vector regression, IEEE Trans. Pattern Anal. Mach. Intell., vol. 22, no. 9, pp. 950-955, 2000.
[43]
J. Jahn, Karush–Kuhn–Tucker conditions in set optimization, J. Optim. Theory Appl., vol. 172, no. 3, pp. 707-725, 2017.
[44]
H. Frohlich, O. Chapelle, and B. Scholkopf, Feature selection for support vector machines by means of genetic algorithm, in Proc. 15th IEEE Int Conf. Tools with Artificial Intelligence, Sacramento, CA, USA, 2003, pp. 142-148.
[45]
D. Agnihotri, K. Verma, and P. Tripathi, Variable global feature selection scheme for automatic classification of text documents, Expert Syst. Appl., vol. 81, pp. 268-281, 2017.
[46]
D. Antonucci, U. F. Oberegger, W. Pasut, and A. Gasparella, Building performance evaluation through a novel feature selection algorithm for automated ARX model identification procedures, Energy and Buildings, vol. 150, pp. 432-446, 2017.
[47]
L. M. Abualigah, A. T. Khader, M. A. Al-Betar, and O. A. Alomari, Text feature selection with a robust weight scheme and dynamic dimension reduction to text document clustering, Expert Syst. Appl., vol. 84, pp. 24-36, 2017.
[49]
L. Lin, F. Wang, X. L. Xie, and S. S. Zhong, Random forests-based extreme learning machine ensemble for multi-regime time series prediction, Expert Syst. Appl., vol. 83, pp. 164-176, 2017.
[50]
M. L. Huang, Intersection traffic flow forecasting based on ν
[51]
M. Mitchell, An Introduction to Genetic Algorithms. Cambridge, MA, USA: MIT Press, 1996.
[52]
California Department of Transportation, Caltrans Performance Measurement System (PeMS), http://pems.dot.ca.gov, 2017.
[53]
G. E. P. Box and G. M. Jenkins, Time Series Analysis: Forecasting and Control. San Francisco, CA, USA: Holden-Day, 1976.
[54]
J. Wen, J. L. Zhao, S. W. Luo, and Z. Han, The improvements of BP neural network learning algorithm, in Proc. 5th Int. Conf. Signal Processing, 16th World Computer Congress 2000, Beijing, China, vol. 3, pp. 1647-1649, 2000.
[55]
M. L. Guo, X. Z. Qin, L. Chen, and Z. H. Jia, The prediction of holidays’ traffic based on improved grid search SVR, in Proc. 2012 4@th Int. C. Environmental Science and Information Application Technology, Ser. Advances in Biomedical Engineering, Newark, NJ, USA, 2013, pp. 688-693.
Publication history
Copyright
Acknowledgements
Rights and permissions
Publication history
Received: 14 November 2017
Accepted: 23 December 2017
Published:
16 August 2018
Issue date: August 2018
Copyright
© The authors 2018
Acknowledgements
This work was supported by the Science and Technology Department of Sichuan Province of China (Nos. 2017JY0007, 2016JY0073, and 2016JZ0031), the Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry, and the Fundamental Research Funds for the Central Universities (No. ZYGX2015J063).
FEEDBACK 
TOP