Abstract
Resource Planning and Service Optimization for operational efficiency constitutes a major factor in the service industry. Internally most of it is dependent on the accuracy of the forecasted demand for the service, which is used to proactively plan resources to match expected demand. In this paper, our focus is on a real-world scenario of vehicle volume forecasting in service stations. Previous work has explored a genetic algorithm (GA) to evolve a regression model based on Neural Networks. Our focus here is to extend on this and show that GA based approach can be also used to evolve other popular regression models for this problem that are widely used in machine learning literature. Each of these techniques considers the historical vehicle volume data along with other correlated data, such as weather, and can have its own set of model parameters as well as other parameters related to data filtration, correction, and feature selections. All of these parameters require proper tuning to achieve the best forecasting accuracy. This can be a challenging task, particularly where different prediction models need to be built for different stations and for different periods, potentially resulting in hundreds of models being built. Manual tuning can be time-consuming, and most importantly, sub-optimal. Our results show that GA can be successfully used to automate the optimization of many popular machine learning models for large-scale vehicle volume forecasting, and more importantly can provide better accuracy than traditionally used manual tuning approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ainslie, R., McCall, J., Shakya, S., Owusu, G.: Predictive planning with neural networks. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 2110–2117. IEEE (2016)
Ashraf, A., Baldwin, D.: Vehicle detection system. U.S. patent no. 8,157,219 (2012)
Awad, M., Khanna, R.: Support vector regression. In: Efficient Learning Machines, pp. 67–80. Apress, Berkeley, CA (2015). https://doi.org/10.1007/978-1-4302-5990-9_4
Bai, J., Ng, S.: Forecasting economic time series using targeted predictors. J. Econometrics 146(2), 304–317 (2008)
Balwani, S.S.V.: Operational efficiency through resource planning optimization and work process improvement. Ph.D. thesis, Massachusetts Institute of Technology (2012)
Dybowski, R., Gant, V., Weller, P., Chang, R.: Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm. Lancet 347(9009), 1146–1150 (1996)
Ekici, B.B., Aksoy, U.T.: Prediction of building energy consumption by using artificial neural networks. Adv. Eng. Softw. 40(5), 356–362 (2009)
Goldberg, D.E., Holland, J.H.: Genetic algorithms and machine learning. Mach. Learn. 3, 95–99 (1988). https://doi.org/10.1023/A:1022602019183
Huang, J., Perry, M.: A semi-empirical approach using gradient boosting and k-nearest neighbors regression for gefcom2014 probabilistic solar power forecasting. Int. J. Forecast. 32(3), 1081–1086 (2016)
Huang, Y.: RFID based parking management system. U.S. patent no. 7,973,641 (2011)
Kaastra, I., Boyd, M.S.: Forecasting futures trading volume using neural networks. J. Futures Markets (1986–1998) 15(18), 953 (1995)
Khargharia, H.S., Santana, R., Shakya, S., Ainslie, R., Owusu, G.: Investigating RNNs for vehicle volume forecasting in service stations. In: 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 2625–2632. IEEE (2020)
Khargharia, H.S., Shakya, S., Ainslie, R., AlShizawi, S., Owusu, G.: Predicting demand in IoT enabled service stations. In: 2019 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA), pp. 81–87. IEEE (2019)
Khargharia, H.S., Shakya, S., Ainslie, R., Owusu, G.: Evolving prediction models with genetic algorithm to forecast vehicle volume in a service station (best application paper). In: Bramer, M., Petridis, M. (eds.) SGAI 2019. LNCS (LNAI), vol. 11927, pp. 167–179. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34885-4_14
Lawrence, R.: Using neural networks to forecast stock market prices. University of Manitoba, vol. 333, pp. 2006–2013 (1997)
Madanhire, I., Mbohwa, C.: Enterprise resource planning (ERP) in improving operational efficiency: case study. Procedia CIRP 40, 225–229 (2016)
Majdi, A., Beiki, M.: Evolving neural network using a genetic algorithm for predicting the deformation modulus of rock masses. Int. J. Rock Mech. Min. Sci. 47(2), 246–253 (2010)
Maltamo, M., Kangas, A.: Methods based on k-nearest neighbor regression in the prediction of basal area diameter distribution. Can. J. For. Res. 28(8), 1107–1115 (1998)
Mitchell, T.: Machine Learning (1997)
Nava, N., Di Matteo, T., Aste, T.: Financial time series forecasting using empirical mode decomposition and support vector regression. Risks 6(1), 7 (2018)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Petrovski, A., Shakya, S., McCall, J.: Optimising cancer chemotherapy using an estimation of distribution algorithm and genetic algorithms. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, pp. 413–418 (2006)
Plakandaras, V., Gupta, R., Gogas, P., Papadimitriou, T.: Forecasting the us real house price index. Econ. Model. 45, 259–267 (2015)
Reeves, C.R.: Genetic algorithms. In: Handbook of Metaheuristics, pp. 109–139. Springer, Heidelberg (2010)
Riedmiller, M., Braun, H.: RPROP-a fast adaptive learning algorithm. In: Proceedings of ISCIS VII (1992)
Schmidt, C., B.S.: Parking control device. U.S. patent application no. 13/723,016 (2013)
Shakya, S., Kern, M., Owusu, G., Chin, C.M.: Neural network demand models and evolutionary optimisers for dynamic pricing. Knowl.-Based Syst. 29, 44–53 (2012)
SKLearn: Sklearn - elasticnetcv. https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.ElasticNetCV.html#sklearn.linear_model.ElasticNetCV
SKLearn: Tuning the hyper-parameters of an estimator. https://scikit-learn.org/stable/modules/grid_search.html#grid-search
Song, Y., Liang, J., Lu, J., Zhao, X.: An efficient instance selection algorithm for k nearest neighbor regression. Neurocomputing 251, 26–34 (2017)
Starkey, A., Hagras, H., Shakya, S., Owusu, G.: A genetic algorithm based system for simultaneous optimisation of workforce skills and teams. KI-Künstliche Intelligenz 32(4), 245–260 (2018)
Székely, G.J., Rizzo, M.L.: Brownian distance covariance. Ann. Appl. Stat. 3(4), 1236–1265 (2009)
Wu, C.H., Ho, J.M., Lee, D.T.: Travel-time prediction with support vector regression. IEEE Trans. Intell. Transp. Syst. 5(4), 276–281 (2004)
Yao, X.: Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)
Yao, Y., Rosasco, L., Caponnetto, A.: On early stopping in gradient descent learning. Constr. Approx. 26(2), 289–315 (2007)
Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 67(2), 301–320 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Khargharia, H.S., Shakya, S., Ainslie, R., Owusu, G. (2021). Evolving Large Scale Prediction Models for Vehicle Volume Forecasting in Service Stations. In: Bramer, M., Ellis, R. (eds) Artificial Intelligence XXXVIII. SGAI-AI 2021. Lecture Notes in Computer Science(), vol 13101. Springer, Cham. https://doi.org/10.1007/978-3-030-91100-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-91100-3_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91099-0
Online ISBN: 978-3-030-91100-3
eBook Packages: Computer ScienceComputer Science (R0)