Articles
Vector support regression machine hyperparameters optimization by utilizing particle swarms for COVID-19 cases forecasting
Norbey Danilo Muñoz-Cañón- Jairo Andrés Romero-Triana
Published 2021-02-27
Keywords
- covid-19,
- particle swarm,
- hyperparameter,
- swarm intelligence,
- support vector machine
- metaheuristic,
- optimization,
- forecasting,
- efficiency,
- time series ...More
How to Cite
Muñoz-Cañón, N. D., & Romero-Triana, J. A. (2021). Vector support regression machine hyperparameters optimization by utilizing particle swarms for COVID-19 cases forecasting. Revista UIS Ingenierías, 20(2), 181–196. https://doi.org/10.18273/revuin.v20n2-2021015
Abstract
In the present article a hyperparameter optimization of a vectorial-support regression machine via adaptation of metaheuristics of a particle swarm is proposed. This method will be used so that a forecasting of the time series of the total amount of positive accumulated cases of COVID-19 in Bogotá, Colombia. In order to validate the performance of the method, a comparison with a regression vectorial-support machine whose hyperparameters have not been optimized will be made, being the metrics those of performance measurement like mean square error, mean absolute error, and determination coefficient. The proposed method finds itself at a greater level of performance when the mean square error value is that of 0,000045, the determination coefficient corresponds with the value of 0,998884 and the p-value of 0,0015, for the nonparametric Wilcoxon test. Finally, applicability of these sorts of methods for forecasting of cases-behavior amidst epidemics is discussed.
Downloads
Download data is not yet available.
References
[1] J. Zheng, “SARS-coV-2: An emerging coronavirus that causes a global threat,” Int. J. Biol. Sci., vol. 16, no. 10, pp. 1678–1685, 2020, doi: 10.7150/ijbs.45053
[2] A. B. A. Al-Hussein, R. Tahir, “Epidemiological Characteristics of COVID-19 Ongoing Epidemic in Iraq,” Bull. World Heal. Organ., Apr. 2020, doi: 10.2471/BLT.20.251561
[3] E. Estrada, “COVID-19 and SARS-CoV-2. Modeling the present, looking at the future,” Phys. Rep., vol. 869, pp. 1–51, Jul. 2020, doi: 10.1016/j.physrep.2020.07.005
[4] S. Ardabili et al., “COVID-19 Outbreak Prediction with Machine Learning,” SSRN Electron. J., Apr. 2020, doi: 10.1101/2020.04.17.20070094
[5] A. Remuzzi, G. Remuzzi, “COVID-19 and Italy: what next?,” Lancet, vol. 395, no. 10231, pp. 1225–1228, Apr. 2020, doi: 10.1016/S0140-6736(20)30627-9
[6] D. Ivanov, “Predicting the impacts of epidemic outbreaks on global supply chains: A simulation-based analysis on the coronavirus outbreak (COVID-19/SARS-CoV-2) case,” Transp. Res. Part E Logist. Transp. Rev., vol. 136, p. 101922, Apr. 2020, doi: 10.1016/j.tre.2020.101922
[7] F. Koike, N. Morimoto, “Supervised forecasting of the range expansion of novel non-indigenous organisms: Alien pest organisms and the 2009 H1N1 flu pandemic,” Glob. Ecol. Biogeogr., vol. 27, no. 8, pp. 991–1000, Aug. 2018, doi: 10.1111/geb.12754
[8] N. Agarwal, S. Reddy Koti, S. Saran, A. S. Kumar, “Data mining techniques for predicting dengue outbreak in geospatial domain using weather parameters for New Delhi, India,” Curr. Sci., vol. 114, no. 11, 2018, Accessed: Aug. 20, 2020. [Online]. Available: 10.18520/cs/v114/i11/2281-2291
[9] S. S. Chenar, Z. Deng, “Development of artificial intelligence approach to forecasting oyster norovirus outbreaks along Gulf of Mexico coast,” Environ. Int., vol. 111, pp. 212–223, Feb. 2018, doi: 10.1016/j.envint.2017.11.032
[10] L. Tapak, O. Hamidi, M. Fathian, M. Karami, “Comparative evaluation of time series models for predicting influenza outbreaks: Application of influenza-like illness data from sentinel sites of healthcare centers in Iran,” BMC Res. Notes, vol. 12, no. 1, pp. 1–6, Jun. 2019, doi: 10.1186/s13104-019-4393-y
[11] R. Liang et al., “Prediction for global African swine fever outbreaks based on a combination of random forest algorithms and meteorological data,” Transbound. Emerg. Dis., vol. 67, no. 2, pp. 935–946, Mar. 2020, doi: 10.1111/tbed.13424
[12] E.-G. Talbi, “Machine Learning for Metaheuristics - State of the Art and Perspectives,” in International Conference on Knowledge and Smart Technology (KST), Apr. 2019, pp. XXIII–XXIII, doi: 10.1109/kst.2019.8687812
[13] L. Calvet, J. De Armas, D. Masip, A. A. Juan, “Learnheuristics: Hybridizing metaheuristics with machine learning for optimization with dynamic inputs,” Open Math., vol. 15, no. 1, pp. 261–280, Jan. 2017, doi: 10.1515/math-2017-0029
[14] M. A. Muñoz, J. A. López, E. F. Caicedo, “Inteligencia de enjambres: sociedades para la solución de problemas (una revisión) Swarm intelligence: problem-solving societies (a review),” Rev. Ing. E Investig., vol. 28, no. 2, pp. 119–130, 2008.
[15] E.-G. Talbi, “Machine learning into metaheuristics: A survey and taxonomy of data-driven metaheuristics,” 2020. Accessed: Aug. 20, 2020. [Online]. Available: https://hal.inria.fr/hal-02745295/document.
[16] J. Kennedy, R. Eberhart, “Particle swarm optimization,” in Proceedings of ICNN’95 - International Conference on Neural Networks, 1995, vol. 4, pp. 1942–1948, doi: 10.1109/ICNN.1995.488968
[17] M. Márquez Gómez, “Las metaheurísticas: tendencias actuales y su aplicabilidad en la ergonomía,” Ing. Ind. Actual. y Nuevas Tendencias, vol. 4, no. 12, pp. 108–120, Jan. 2014.
[18] K. Smets, B. Verdonk, E. M. Jordaan, “Evaluation of performance measures for SVR hyperparameter selection,” in IEEE International Conference on Neural Networks - Conference Proceedings, 2007, pp. 637–642, doi: 10.1109/IJCNN.2007.4371031
[19] W. Naudé, “Artificial intelligence vs COVID-19: limitations, constraints and pitfalls,” AI Soc., vol. 1, p. 3, Apr. 2020, doi: 10.1007/s00146-020-00978-0
[20] Y. Mohamadou, A. Halidou, P. T. Kapen, “A review of mathematical modeling, artificial intelligence and datasets used in the study, prediction and management of COVID-19,” Appl. Intell., pp. 1–13, Jul. 2020, doi: 10.1007/s10489-020-01770-9
[21] R. Sujath, J. M. Chatterjee, A. E. Hassanien, “A machine learning forecasting model for COVID-19 pandemic in India,” Stoch. Environ. Res. Risk Assess., vol. 34, no. 7, pp. 959–972, Jul. 2020, doi: 10.1007/s00477-020-01827-8
[22] L. Xu, “Modelling to contain pandemic influenza A (H1N1) with stochastic membrane systems: A work-in-progress paper,” in Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, 2012, vol. 87 LNICST, pp. 74–81, doi: 10.1007/978-3-642-32615-8_10
[23] M. A. A. Al-Qaness, A. A. Ewees, H. Fan, M. A. El Aziz, “Optimization method for forecasting confirmed cases of COVID-19 in China,” Appl. Sci., vol. 9, no. 3, p. 674, Mar. 2020, doi: 10.3390/JCM9030674
[24] W. Hu, L. Yan, K. Liu, H. Wang, “A Short-term Traffic Flow Forecasting Method Based on the Hybrid PSO-SVR,” Neural Process. Lett., vol. 43, no. 1, pp. 155–172, Feb. 2016, doi: 10.1007/s11063-015-9409-6
[25] M. Hasanipanah, A. Shahnazar, H. Bakhshandeh Amnieh, D. Jahed Armaghani, “Prediction of air-overpressure caused by mine blasting using a new hybrid PSO–SVR model,” Eng. Comput., vol. 33, no. 1, pp. 23–31, Jan. 2017, doi: 10.1007/s00366-016-0453-2
[26] Secretaría Distrital de Salud de Bogotá, “Número de casos confirmados por el laboratorio de COVID- 19 - Bogotá D.C. Datos Abiertos Bogotá,” Apr. 07, 2020. https://datosabiertos.bogota.gov.co/dataset/44eacdb7-a535-45ed-be03-16dbbea6f6da
[27] J. D. Kelleher, B. Mac Namee, A. D’Arcy, Fundamentals of Machine Learning for Predictive Data Analytics. The MIT Press, 2015.
[28] “Normalizar datos: referencia para los módulos - Azure Machine Learning | Microsoft Docs,” Feb. 22, 2020. https://docs.microsoft.com/es-es/azure/machine-learning/algorithm-module-reference/normalize-data
[29] R. Adhikari, R. K. Agrawal, “An Introductory Study on Time Series Modeling and Forecasting,” L. Lambert Acad. Publ., Feb. 2013, Accessed: Aug. 20, 2020. [Online]. Available: http://arxiv.org/abs/1302.6613.
[30] Microsoft, “Ajuste de los hiperparámetros de un modelo - Azure Machine Learning | Microsoft Docs,” Documentación Microsoft, 2020. https://docs.microsoft.com/es-es/azure/machine-learning/how-to-tune-hyperparameters
[31] R. Laref, E. Losson, A. Sava, M. Siadat, “On the optimization of the support vector machine regression hyperparameters setting for gas sensors array applications,” Chemom. Intell. Lab. Syst., vol. 184, pp. 22–27, Jan. 2019, doi: 10.1016/j.chemolab.2018.11.011
[32] M. Awad, R. Khanna, M. Awad, R. Khanna, “Support Vector Regression,” in Efficient Learning Machines, Apress, 2015, pp. 67–80.
[33] G. Barrero, “Optimización de hiperparámetros de algoritmos de aprendizaj automático usados para el análisis de la calidad del software,” Res. Gate, no. January, 2019, doi: 10.13140/RG.2.2.15055.74405
[34] S. Kefi, N. Rokbani, A. M. Alimi, “Impact of ant size on ant supervised by PSO, AS-PSO, performances,” in Advances in Intelligent Systems and Computing, Nov. 2017, vol. 552, pp. 567–577, doi: 10.1007/978-3-319-52941-7_56
[35] K. S. Raghuwanshi, “A Qualitative Review of Two Evolutionary Algorithms Inspired by Heuristic Population Based Search Methods: GA & PSO,” in Lecture Notes in Networks and Systems, vol. 18, Singapore: Springer, 2018, pp. 169–175.
[36] K. Demertzis, D. Tsiotas, L. Magafas, “Modeling and forecasting the covid-19 temporal spread in Greece: An exploratory approach based on complex network defined splines,” Int. J. Environ. Res. Public Health, vol. 17, no. 13, pp. 1–18, Jul. 2020, doi: 10.3390/ijerph17134693
[37] S. Sun,Y. Zheng, “Prediction of 2019-nCov in Italy based on PSO and inversion analysis,” medRxiv, May 2020, doi: 10.1101/2020.05.08.20095869
[38] A. Godio, F. Pace, A. Vergnano, “Seir modeling of the italian epidemic of sars-cov-2 using computational swarm intelligence,” Int. J. Environ. Res. Public Health, vol. 17, no. 10, May 2020, doi: 10.3390/ijerph17103535
[39] M. Paggi, “Simulation of Covid-19 epidemic evolution: are compartmental models really predictive?,” arXiv.org, Apr. 2020, Accessed: Aug. 20, 2020. [Online]. Available: http://arxiv.org/abs/2004.08207
[2] A. B. A. Al-Hussein, R. Tahir, “Epidemiological Characteristics of COVID-19 Ongoing Epidemic in Iraq,” Bull. World Heal. Organ., Apr. 2020, doi: 10.2471/BLT.20.251561
[3] E. Estrada, “COVID-19 and SARS-CoV-2. Modeling the present, looking at the future,” Phys. Rep., vol. 869, pp. 1–51, Jul. 2020, doi: 10.1016/j.physrep.2020.07.005
[4] S. Ardabili et al., “COVID-19 Outbreak Prediction with Machine Learning,” SSRN Electron. J., Apr. 2020, doi: 10.1101/2020.04.17.20070094
[5] A. Remuzzi, G. Remuzzi, “COVID-19 and Italy: what next?,” Lancet, vol. 395, no. 10231, pp. 1225–1228, Apr. 2020, doi: 10.1016/S0140-6736(20)30627-9
[6] D. Ivanov, “Predicting the impacts of epidemic outbreaks on global supply chains: A simulation-based analysis on the coronavirus outbreak (COVID-19/SARS-CoV-2) case,” Transp. Res. Part E Logist. Transp. Rev., vol. 136, p. 101922, Apr. 2020, doi: 10.1016/j.tre.2020.101922
[7] F. Koike, N. Morimoto, “Supervised forecasting of the range expansion of novel non-indigenous organisms: Alien pest organisms and the 2009 H1N1 flu pandemic,” Glob. Ecol. Biogeogr., vol. 27, no. 8, pp. 991–1000, Aug. 2018, doi: 10.1111/geb.12754
[8] N. Agarwal, S. Reddy Koti, S. Saran, A. S. Kumar, “Data mining techniques for predicting dengue outbreak in geospatial domain using weather parameters for New Delhi, India,” Curr. Sci., vol. 114, no. 11, 2018, Accessed: Aug. 20, 2020. [Online]. Available: 10.18520/cs/v114/i11/2281-2291
[9] S. S. Chenar, Z. Deng, “Development of artificial intelligence approach to forecasting oyster norovirus outbreaks along Gulf of Mexico coast,” Environ. Int., vol. 111, pp. 212–223, Feb. 2018, doi: 10.1016/j.envint.2017.11.032
[10] L. Tapak, O. Hamidi, M. Fathian, M. Karami, “Comparative evaluation of time series models for predicting influenza outbreaks: Application of influenza-like illness data from sentinel sites of healthcare centers in Iran,” BMC Res. Notes, vol. 12, no. 1, pp. 1–6, Jun. 2019, doi: 10.1186/s13104-019-4393-y
[11] R. Liang et al., “Prediction for global African swine fever outbreaks based on a combination of random forest algorithms and meteorological data,” Transbound. Emerg. Dis., vol. 67, no. 2, pp. 935–946, Mar. 2020, doi: 10.1111/tbed.13424
[12] E.-G. Talbi, “Machine Learning for Metaheuristics - State of the Art and Perspectives,” in International Conference on Knowledge and Smart Technology (KST), Apr. 2019, pp. XXIII–XXIII, doi: 10.1109/kst.2019.8687812
[13] L. Calvet, J. De Armas, D. Masip, A. A. Juan, “Learnheuristics: Hybridizing metaheuristics with machine learning for optimization with dynamic inputs,” Open Math., vol. 15, no. 1, pp. 261–280, Jan. 2017, doi: 10.1515/math-2017-0029
[14] M. A. Muñoz, J. A. López, E. F. Caicedo, “Inteligencia de enjambres: sociedades para la solución de problemas (una revisión) Swarm intelligence: problem-solving societies (a review),” Rev. Ing. E Investig., vol. 28, no. 2, pp. 119–130, 2008.
[15] E.-G. Talbi, “Machine learning into metaheuristics: A survey and taxonomy of data-driven metaheuristics,” 2020. Accessed: Aug. 20, 2020. [Online]. Available: https://hal.inria.fr/hal-02745295/document.
[16] J. Kennedy, R. Eberhart, “Particle swarm optimization,” in Proceedings of ICNN’95 - International Conference on Neural Networks, 1995, vol. 4, pp. 1942–1948, doi: 10.1109/ICNN.1995.488968
[17] M. Márquez Gómez, “Las metaheurísticas: tendencias actuales y su aplicabilidad en la ergonomía,” Ing. Ind. Actual. y Nuevas Tendencias, vol. 4, no. 12, pp. 108–120, Jan. 2014.
[18] K. Smets, B. Verdonk, E. M. Jordaan, “Evaluation of performance measures for SVR hyperparameter selection,” in IEEE International Conference on Neural Networks - Conference Proceedings, 2007, pp. 637–642, doi: 10.1109/IJCNN.2007.4371031
[19] W. Naudé, “Artificial intelligence vs COVID-19: limitations, constraints and pitfalls,” AI Soc., vol. 1, p. 3, Apr. 2020, doi: 10.1007/s00146-020-00978-0
[20] Y. Mohamadou, A. Halidou, P. T. Kapen, “A review of mathematical modeling, artificial intelligence and datasets used in the study, prediction and management of COVID-19,” Appl. Intell., pp. 1–13, Jul. 2020, doi: 10.1007/s10489-020-01770-9
[21] R. Sujath, J. M. Chatterjee, A. E. Hassanien, “A machine learning forecasting model for COVID-19 pandemic in India,” Stoch. Environ. Res. Risk Assess., vol. 34, no. 7, pp. 959–972, Jul. 2020, doi: 10.1007/s00477-020-01827-8
[22] L. Xu, “Modelling to contain pandemic influenza A (H1N1) with stochastic membrane systems: A work-in-progress paper,” in Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, 2012, vol. 87 LNICST, pp. 74–81, doi: 10.1007/978-3-642-32615-8_10
[23] M. A. A. Al-Qaness, A. A. Ewees, H. Fan, M. A. El Aziz, “Optimization method for forecasting confirmed cases of COVID-19 in China,” Appl. Sci., vol. 9, no. 3, p. 674, Mar. 2020, doi: 10.3390/JCM9030674
[24] W. Hu, L. Yan, K. Liu, H. Wang, “A Short-term Traffic Flow Forecasting Method Based on the Hybrid PSO-SVR,” Neural Process. Lett., vol. 43, no. 1, pp. 155–172, Feb. 2016, doi: 10.1007/s11063-015-9409-6
[25] M. Hasanipanah, A. Shahnazar, H. Bakhshandeh Amnieh, D. Jahed Armaghani, “Prediction of air-overpressure caused by mine blasting using a new hybrid PSO–SVR model,” Eng. Comput., vol. 33, no. 1, pp. 23–31, Jan. 2017, doi: 10.1007/s00366-016-0453-2
[26] Secretaría Distrital de Salud de Bogotá, “Número de casos confirmados por el laboratorio de COVID- 19 - Bogotá D.C. Datos Abiertos Bogotá,” Apr. 07, 2020. https://datosabiertos.bogota.gov.co/dataset/44eacdb7-a535-45ed-be03-16dbbea6f6da
[27] J. D. Kelleher, B. Mac Namee, A. D’Arcy, Fundamentals of Machine Learning for Predictive Data Analytics. The MIT Press, 2015.
[28] “Normalizar datos: referencia para los módulos - Azure Machine Learning | Microsoft Docs,” Feb. 22, 2020. https://docs.microsoft.com/es-es/azure/machine-learning/algorithm-module-reference/normalize-data
[29] R. Adhikari, R. K. Agrawal, “An Introductory Study on Time Series Modeling and Forecasting,” L. Lambert Acad. Publ., Feb. 2013, Accessed: Aug. 20, 2020. [Online]. Available: http://arxiv.org/abs/1302.6613.
[30] Microsoft, “Ajuste de los hiperparámetros de un modelo - Azure Machine Learning | Microsoft Docs,” Documentación Microsoft, 2020. https://docs.microsoft.com/es-es/azure/machine-learning/how-to-tune-hyperparameters
[31] R. Laref, E. Losson, A. Sava, M. Siadat, “On the optimization of the support vector machine regression hyperparameters setting for gas sensors array applications,” Chemom. Intell. Lab. Syst., vol. 184, pp. 22–27, Jan. 2019, doi: 10.1016/j.chemolab.2018.11.011
[32] M. Awad, R. Khanna, M. Awad, R. Khanna, “Support Vector Regression,” in Efficient Learning Machines, Apress, 2015, pp. 67–80.
[33] G. Barrero, “Optimización de hiperparámetros de algoritmos de aprendizaj automático usados para el análisis de la calidad del software,” Res. Gate, no. January, 2019, doi: 10.13140/RG.2.2.15055.74405
[34] S. Kefi, N. Rokbani, A. M. Alimi, “Impact of ant size on ant supervised by PSO, AS-PSO, performances,” in Advances in Intelligent Systems and Computing, Nov. 2017, vol. 552, pp. 567–577, doi: 10.1007/978-3-319-52941-7_56
[35] K. S. Raghuwanshi, “A Qualitative Review of Two Evolutionary Algorithms Inspired by Heuristic Population Based Search Methods: GA & PSO,” in Lecture Notes in Networks and Systems, vol. 18, Singapore: Springer, 2018, pp. 169–175.
[36] K. Demertzis, D. Tsiotas, L. Magafas, “Modeling and forecasting the covid-19 temporal spread in Greece: An exploratory approach based on complex network defined splines,” Int. J. Environ. Res. Public Health, vol. 17, no. 13, pp. 1–18, Jul. 2020, doi: 10.3390/ijerph17134693
[37] S. Sun,Y. Zheng, “Prediction of 2019-nCov in Italy based on PSO and inversion analysis,” medRxiv, May 2020, doi: 10.1101/2020.05.08.20095869
[38] A. Godio, F. Pace, A. Vergnano, “Seir modeling of the italian epidemic of sars-cov-2 using computational swarm intelligence,” Int. J. Environ. Res. Public Health, vol. 17, no. 10, May 2020, doi: 10.3390/ijerph17103535
[39] M. Paggi, “Simulation of Covid-19 epidemic evolution: are compartmental models really predictive?,” arXiv.org, Apr. 2020, Accessed: Aug. 20, 2020. [Online]. Available: http://arxiv.org/abs/2004.08207