Abstract
The deep learning approach has been successfully applied to various disciplines. When using optimization algorithms, there is a need to evaluate the performance of solutions found so far. The simulation system usually serve as the evaluator. However, to speedup the process, an approximation function, called surrogate, can replace the time consuming simulator. We propose to use deep learning to construct the surrogate function in epidemiology. The simulator is an agent-based stochastic model for influenza and the optimization problem is to find vaccination strategy to minimize the number of infected cases or economical impact. The optimizer is a genetic algorithm and the fitness function is the simulation program. An attempt to use the surrogate function with table lookup and interpolation was reported before. The results show that the surrogate constructed by deep learning approach outperforms the interpolation based one for both total case and economical impact. The average of the absolute value of relative error is less than 0.27%, which is quite close to the intrinsic limitation of the stochastic variation of the simulation software 0.2%, and the rank coefficients are all above 0.999. The vaccination strategy recommended is still to vaccine the school age children first which is consistent with the previous studies for minimizing total infected cases. As to minimize economical impact, the priority goes to the middle schoolers then to young working adults The results are encouraging and it should be a worthy effort to use machine learning approach to explore the vast parameter space of simulation models in epidemiology.
An earlier extended abstract of this paper appears in [1].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jian, Z.-D., Chang, H.-J., Hsu, T.-s., Wang, D.-W.: Learning from simulated world - surrogates construction with deep neural network. In: the 7th International Conference on Simulation and Modeling Methodologies, Technologies and Applications, pp. 83–92 (2017)
Germann, T.C., Kadau, K., Longini, I.M., Macken, C.A.: Mitigation strategies for pandemic influenza in the United States. Proc. Natl. Acad. Sci. 103(15), 5935–5940 (2006)
Chao, D.L., Halloran, M.E., Obenchain, V.J., Longini, I.M.: FluTE, a publicly available stochastic influenza epidemic simulation model. PLOS Comput. Biol. 6(1), 1–8 (2010)
Meltzer, M.I., Cox, N.J., Fukuda, K.: The economic impact of pandemic influenza in the United States: priorities for intervention. Emerg. Infect. Dis. 5(5), 659–671 (1999)
Jin, Y.: Surrogate-assisted evolutionary computation: recent advances and future challenges. Swarm Evol. Comput. 2(1), 61–70 (2011)
Grefenstette, J.J., Fitzpatrick, J.M.: Genetic search with approximate fitness evaluations. In: International Conference on Genetic Algorithms and Their Applications, pp. 112–120 (1985)
Jian, Z.-D., Hsu, T.-s., Wang, D.-W.: Searching vaccination strategy with surrogate-assisted evolutionary computing. In: the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications, pp. 56–63 (2016)
Gosavi, A.: Simulation-based optimization. Parametric optimization techniques and reinforcement learning (2015)
Tsai, M.-T., Chern, T.-C., Chuang, J.-H., Hsueh, C.-W., Kuo, H.-S., Liau, C.-J., Riley, S., Shen, B.-J., Shen, C.-H.: Wang, D.-W., Hsu, T.-s.: Efficient simulation of the spatial transmission dynamics of influenza. PLoS ONE 5(11), 1–8 (2010)
Chang, H.-J., Chuang, J.-H., Fu, Y.-C., Hsu, T.-s., Hsueh, C.-W., Tsai, S.-C., Wang, D.-W.: The impact of household structures on pandemic influenza vaccination priority. In: The 5th International Conference on Simulation and Modeling Methodologies, Technologies and Applications, pp. 482–487 (2015)
Fu, Y.-C., Wang, D.-W., Chuang, J.-H.: Representative contact diaries for modeling the spread of infectious diseases in Taiwan. PLoS ONE 7(10), 1–7 (2012)
Basta, N.E., Halloran, M.E., Matrajt, L., Longini, I.M.: Estimating influenza vaccine efficacy from challenge and community-based study data. Am. J. Epidemiol. 168(12), 1343–1352 (2008)
Keras Documentation. https://keras.io/
Loshchilov, I., Schoenauer, M., Sebag, M.: Comparison-Based Optimizers Need Comparison-Based Surrogates, pp. 364–373 (2010)
Acknowledgements
We thank anonymous reviewers for their suggestions. The research is partially funded by the grant of “MOST104-2221-E-001-021-MY3”, and “Multidisciplinary Health Cloud Research Program: Technology Development and Application of Big Health Data. Academia Sinica, Taipei, Taiwan”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Jian, ZD., Chang, HJ., Hsu, Ts., Wang, DW. (2019). Applying Deep Learning for Surrogate Construction of Simulation Systems. In: Obaidat, M., Ören, T., Rango, F. (eds) Simulation and Modeling Methodologies, Technologies and Applications . SIMULTECH 2017. Advances in Intelligent Systems and Computing, vol 873. Springer, Cham. https://doi.org/10.1007/978-3-030-01470-4_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-01470-4_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01469-8
Online ISBN: 978-3-030-01470-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)