Influenza trend prediction method combining Baidu index and support vector regression based on an improved particle swarm optimization algorithm

Hongxin Xue; Lingling Zhang; Haijian Liang; Liqun Kuang; Huiyan Han; Xiaowen Yang; Lei Guo; Hongxin Xue; Lingling Zhang; Haijian Liang; Liqun Kuang; Huiyan Han; Xiaowen Yang; Lei Guo

doi:10.3934/math.20231303

AIMS Mathematics

2023, Volume 8, Issue 11: 25528-25549. doi: 10.3934/math.20231303

Previous Article Next Article

Research article

Influenza trend prediction method combining Baidu index and support vector regression based on an improved particle swarm optimization algorithm

1.
School of Computer Science and Technology, North University of China, Taiyuan, Shanxi 030051, China
2.
Shanxi Province's Vision Information Processing and Intelligent Robot Engineering Research Center, Taiyuan, Shanxi 030051, China
3.
Shanxi Key Laboratory of Machine Vision and Virtual Reality, Taiyuan, Shanxi 030051, China
4.
School of Software, North University of China, Taiyuan, Shanxi 030051, China

Received: 05 August 2023 Revised: 24 August 2023 Accepted: 27 August 2023 Published: 04 September 2023
MSC : 97R20, 97R50

Web-based search query data have been recognized as valuable data sources for discovering new influenza epidemics. However, selecting search and query keywords and adopting prediction methods pose key challenges to improving the effectiveness of influenza prediction. In this study, web search data were analyzed and excavated using big data and machine learning methods. The flu prediction model for the southern region of China, considering the impact of influenza transmission across regions and based on various keywords and historical influenza-like illness percentage (ILI%) data, was built (models 1–4) to verify the factors affecting the spread of the flu. To improve the accuracy of the influenza trend prediction, a support vector regression method based on an improved particle swarm optimization algorithm was proposed (IPSO-SVR), which was applied to the influenza prediction model to forecast ILI% in southern China. By comparing and analyzing the prediction results of each model, model 4, using the IPSO-SVR algorithm, exhibited higher prediction precision and more effective results, with its prediction indexes including the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) being 0.0596, 0.2441 and 0.1884, respectively. The experimental results show that the prediction precision significantly increased when the IPSO-SVR method was applied to the constructed ILI% model. A new theoretical basis and implementation strategy were provided for achieving more accurate influenza prevention and control in southern China.
- influenza,
- web search data,
- prediction model,
- principal component analysis,
- support vector regression,
- improved PSO algorithm
Citation: Hongxin Xue, Lingling Zhang, Haijian Liang, Liqun Kuang, Huiyan Han, Xiaowen Yang, Lei Guo. Influenza trend prediction method combining Baidu index and support vector regression based on an improved particle swarm optimization algorithm[J]. AIMS Mathematics, 2023, 8(11): 25528-25549. doi: 10.3934/math.20231303

Related Papers:

Abstract

Web-based search query data have been recognized as valuable data sources for discovering new influenza epidemics. However, selecting search and query keywords and adopting prediction methods pose key challenges to improving the effectiveness of influenza prediction. In this study, web search data were analyzed and excavated using big data and machine learning methods. The flu prediction model for the southern region of China, considering the impact of influenza transmission across regions and based on various keywords and historical influenza-like illness percentage (ILI%) data, was built (models 1–4) to verify the factors affecting the spread of the flu. To improve the accuracy of the influenza trend prediction, a support vector regression method based on an improved particle swarm optimization algorithm was proposed (IPSO-SVR), which was applied to the influenza prediction model to forecast ILI% in southern China. By comparing and analyzing the prediction results of each model, model 4, using the IPSO-SVR algorithm, exhibited higher prediction precision and more effective results, with its prediction indexes including the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) being 0.0596, 0.2441 and 0.1884, respectively. The experimental results show that the prediction precision significantly increased when the IPSO-SVR method was applied to the constructed ILI% model. A new theoretical basis and implementation strategy were provided for achieving more accurate influenza prevention and control in southern China.

References

[1]	Z. Y. Zhao, M. M. Zhai, G. H. Li, X. F. Gao, W. Z. Song, X. C. Wang, Study on the prediction effect of a combined model of SARIMA and LSTM based on SSA for influenza in Shanxi Province, China, BMC INFECT. DIS., 23 (2023), 71. https://doi.org/10.1186/s12879-023-08025-1 doi: 10.1186/s12879-023-08025-1
[2]	H. Gong, X. Shen, H. Yan, W. Y. Lu, G. J. Zhong, K. G. Dong, et al., Estimating the disease burden of seasonal influenza in China, 2006-2019, Natl. Med. J. China, 101 (2021), 560‒567. https://doi.org/10.3760/cma.j.cn112137-20201210-03323 doi: 10.3760/cma.j.cn112137-20201210-03323
[3]	World Health Organization, Fact sheet on influenza (seasonal). Available from: https://www.who.int/en/news-room/fact-sheets/detail/influenza-(seasonal)
[4]	L. Li, Y. Liu, P. Wu, Z. Peng, X. Wang, T. Chen, et al., Influenza-associated excess respiratory mortality in China, 2010-2015: a population-based study, Lancet Public Health, 4 (2019), e473‒e481. https://doi.org/10.1016/S2468-2667(19)30163-X doi: 10.1016/S2468-2667(19)30163-X
[5]	National Bureau of Statistics, Gross domestic product. Available from: http://www.stats.gov.cn/xxgk/sjfb/zxfb2020/202212/t20221227_1891261.html
[6]	B. Jang, I. Kim, W. Jong, Effective training data extraction method to improve influenza outbreak prediction from online news articles: deep learning model study, JMIR Med. Inf., 9 (2021), e23305. https://doi.org/10.2196/23305 doi: 10.2196/23305
[7]	L. Zhou, J. Li, D. Shi, L. Xu, S. X. Huang, Predicting Influenza Epidemic for United States, Int. J. Environ. Heal. R., 32 (2022), 1231‒1237.
[8]	P. Guo, J. J. Zhang, L. Wang, S. Y. Yang, G. F. Luo, C. Y. Deng, et al., Monitoring seasonal influenza epidemics by using internet search data with an ensemble penalized regression model, Sci. Rep-UK., 7 (2017), 46469. https://doi.org/10.1038/srep46469 doi: 10.1038/srep46469
[9]	S. Y. Yang, Y. K. Bao, Comprehensive learning particle swarm optimization enabled modeling framework for multi-step-ahead influenza prediction, Appl. Soft Comput., 113 (2021), 107994. https://doi.org/10.1016/j.asoc.2021.107994 doi: 10.1016/j.asoc.2021.107994
[10]	R. X. Wang, H. Y. Wu, Y. S. Wu, J. Zheng, Y. Li, Improving influenza surveillance based on multi-granularity deep spatiotemporal neural network, Comput. Biol. Med., 134 (2021), 104482. https://doi.org/10.1016/j.compbiomed.2021.104482 doi: 10.1016/j.compbiomed.2021.104482
[11]	N. Kumar, H. Kumar, K. Kumar, A study for plausible third wave of COVID-19 in India through fuzzy time series modelling based on particle swarm optimization and fuzzy c-means, Math. Probl. Eng., 2022 (2022), 5878268. https://doi.org/10.1155/2022/5878268 doi: 10.1155/2022/5878268
[12]	M. Thomas, H. Rootzen, Real-time prediction of severe influenza epidemics using extreme value statistics, J. R. Stat. Soc. C-Appl., 71 (2022), 376-394. https://doi.org/10.1111/rssc.12537 doi: 10.1111/rssc.12537
[13]	Y. C. Wei, Y. L. Ou, J. Q. Li, W. C. Wu, Forecasting the potential number of influenza-like illness cases by fusing internet public opinion, Sustainability-Basel, 14 (2022), 2803. https://doi.org/10.3390/su14052803 doi: 10.3390/su14052803
[14]	A. Kara, Multi-step influenza outbreak forecasting using deep LSTM network and genetic algorithm, Expert Syst. Appl., 180 (2021), 115153. https://doi.org/10.1016/j.eswa.2021.115153 doi: 10.1016/j.eswa.2021.115153
[15]	N. Kumar, H. Kumar, A novel hybrid fuzzy time series model for prediction of COVID-19 infected cases and deaths in India, ISA T., 124 (2022), 69‒81. https://doi.org/10.1016/j.isatra.2021.07.003 doi: 10.1016/j.isatra.2021.07.003
[16]	S. F. Ackley, S. Pilewski, V. S. Petrovic, L. Worden, E. Murray, T. C. Porco, Assessing the utility of a smart thermometer and mobile application as a surveillance tool for influenza and influenza-like illness, Health Inform. J., 26 (2020), 2148‒2158. https://doi.org/10.1177/1460458219897152 doi: 10.1177/1460458219897152
[17]	T. Murayama, N. Shimizu, S. Fujita, S. Wakamiya, E. Aramaki, Predicting regional influenza epidemics with uncertainty estimation using commuting data in Japan, PLoS One, 16 (2021), e0250417. https://doi.org/10.1371/journal.pone.0250417 doi: 10.1371/journal.pone.0250417
[18]	C.Y. Yang, R. J. Chen, W. L. Chou, Y. J. Lee, Y. S. Lo, An Integrated Influenza Surveillance Framework Based on National Influenza-Like Illness Incidence and Multiple Hospital Electronic Medical Records for Early Prediction of Influenza Epidemics: Design and Evaluation, J. Med. Internet Res., 21 (2019), e12341. https://doi.org/10.2196/13699 doi: 10.2196/13699
[19]	S. I. Leuba, R. Yaesoubi, M. Antillon, T. Cohen, C. Zimmer, Tracking and predicting US influenza activity with a real-time surveillance network, PLoS Comput. Biol., 16 (2020), e1008180.
[20]	B. Jang, L. Kim, J. W. Kim, Long-Term Influenza Outbreak Forecast Using Time-Precedence Correlation of Web Data, IEEE T. Neur. Net. Lear., 34 (2023), 2400‒2412. https://doi.org/10.1371/journal.pcbi.1008180 doi: 10.1371/journal.pcbi.1008180
[21]	D. Viglino, A. Vesin, S. Ruckly, X. Morelli, R. Slama, G. Debaty, et al. Daily volume of cases in emergency call centers: construction and validation of a predictive model, Scand. J. Trauma Resus., 25 (2017): 86. https://doi.org/10.1186/s13049-017-0430-9 doi: 10.1186/s13049-017-0430-9
[22]	A. H. Gutierrez, V. J. Rapp-Gabrielson, F. E. Terry, C. L. Loving, L. Moise, W. D. Martin, et al., T-cell epitope content comparison (EpiCC) of swine H1 influenza A virus hemagglutinin, Influenza Other Resp., 11 (2018), 531‒542. https://doi.org/10.1111/irv.12513 doi: 10.1111/irv.12513
[23]	S. N. Chen, J. Xu, Y. S. Wu, X. Wang, S. S. Fang, J. Q. Cheng, et al., Predicting temporal propagation of seasonal influenza using improved gaussian process model, J. Biomed. Inform., 93 (2019). https://doi.org/103144.10.1016/j.jbi.2019.103144
[24]	F. S. Lu, M. W. Hattab, C. L. Clemente, M. Biggerstaff, M. Santillana, Improved state-level influenza nowcasting in the United States leveraging Internet-based data and network approaches, Nat. Commun., 10 (2019), 1‒10. https://doi.org/10.1038/s41467-018-08082-0 doi: 10.1038/s41467-018-08082-0
[25]	C. Zimmer, S. I. Leuba, R. Yaesoubi, T. Cohen, Use of daily Internet search query data improves real-time projections of influenza epidemics, J. R. Soc. Interface, 15 (2018), 1‒7. https://doi.org/10.1098/rsif.2018.0220 doi: 10.1098/rsif.2018.0220
[26]	I. Miliou, X. Xiong, S. Rinzivillo, Q. Zhang, G. Rossetti, F. Giannotti, et al., Predicting seasonal influenza using supermarket retail records, PLoS Comput. Bilo., 17 (2021), e1009087. https://doi.org/10.1371/journal.pcbi.1009087 doi: 10.1371/journal.pcbi.1009087
[27]	Z. Y. Huang, Exploration of the Accuracy of epidemic prediction based on the Baidu index——taking H7N9 subtype avian influenza in Guangdong Province as an Example, Chinese Journal of Zoonoses, 36 (2020), 962‒968.
[28]	Y. Lu, S. Wang, J. Y. Wang, G. Y. Zhou, Q. Zhang, X. Zhou, et al., An Epidemic Avian Influenza Prediction Model Based on Google Trends, Lett. Org. Chem., 16 (2019), 303‒310. https://doi.org/10.2174/1570178615666180724103325 doi: 10.2174/1570178615666180724103325
[29]	X. Y. Zhou, Y. Zhang, C. J. Shen, A. L. Liu, Y. M. Wang, Q. Yu, et al., Knowledge, attitudes, and practices associated with avian influenza along the live chicken market chains in Eastern China: A cross-sectional survey in Shanghai, Anhui, and Jiangsu, Transbound. Emerg. Dis., 66 (2019), 1529‒1538. https://doi.org/10.1111/tbed.13178 doi: 10.1111/tbed.13178
[30]	M. Athanasiou, G. Fragkozidis, K. Zarkogianni, K. S. Nikita, Long short-term memory-based prediction of the spread of influenza-like illness leveraging surveillance, weather, and twitter data: model development and validation, J. Med. Internet Res., 25 (2023), e42519. https://doi.org/10.2196/42519 doi: 10.2196/42519
[31]	T. Lazebnik, S. Bunimovich-Mendrazitsky, S. Ashkenazi, E. Levner, A. Benis, Early detection and control of the next epidemic wave using health communications: development of an artificial intelligence-based tool and its validation on COVID-19 data from the US, Int. J. Env. Res. Pub. He., 19 (2022), 16023. https://doi.org/10.3390/ijerph192316023 doi: 10.3390/ijerph192316023
[32]	C. Wu, S. C. Kao, Knowledge discovery in open data for epidemic disease prediction, Health Policy Techn., 10 (2021), 126‒134. https://doi.org/10.1016/j.hlpt.2021.01.001 doi: 10.1016/j.hlpt.2021.01.001
[33]	S. B. Choi, J. Kim, I. Ahn, Forecasting type-specific seasonal influenza after 26 weeks in the United States using influenza activities in other countries, PLoS One, 14 (2019), e0220423. https://doi.org/10.1371/journal.pone.0220423 doi: 10.1371/journal.pone.0220423
[34]	A. Boukobza, A. Burgun, B. Roudier, R. Tsopra, Deep neural networks for simultaneously capturing public topics and sentiments during a pandemic: application on a COVID-19 Tweet data set, JMIR Med. Inf., 10 (2022), e34306. https://doi.org/10.2196/34306 doi: 10.2196/34306
[35]	Chinese National Influenza Center, Weekly report of influenza-like cases. Available from: https://ivdc.chinacdc.cn/cnic/
[36]	Baidu search engine, Bai index. Available from: https://index.baidu.com
[37]	R. J. WANG, Machanism and empirical research on forecasting influenza epidemic fused with Baidu index, Journal of the China society for scientific and technical information, 37 (2018), 206‒219.
[38]	N. Sultana, N. Sharma, K. P. Sharma, S. Verma, A Sequential Ensemble Model for Communicable Disease Forecasting, Curr. Bioinform., 15 (2020), 309‒317. https://doi.org/10.2174/1574893614666191202153824 doi: 10.2174/1574893614666191202153824
[39]	H. S. Cai, X. D. Jia, J. S. Feng, W. Z. Li, Y. M. Hsu, J. Lee, Gaussian Process Regression for numerical wind speed prediction enhancement, Renew. Energ., 146 (2020), 2112‒2123. https://doi.org/10.1016/j.renene.2019.08.018 doi: 10.1016/j.renene.2019.08.018
[40]	B. J. Zhang, L. Sun, W. B. Wang, Two stage prediction model of sunspots monthly value based on CEEMDAN and particle swarm optimization ELM, IEEE Access, 10 (2022), 102981‒102991. https://doi.org/10.1109/ACCESS.2022.3206542 doi: 10.1109/ACCESS.2022.3206542
[41]	Y. P. Wen, Y. Wang, J. X. Liu, B. Q. Cao, Q. Fu, CPU usage prediction for cloud resource provisioning based on deep belief network and particle swarm optimization, Concurr. Comp.-Pract. E., 32 (2020), e5730. https://doi.org/10.1002/cpe.5730 doi: 10.1002/cpe.5730
[42]	W. P. Gong, S. Tian, L. Wang, Z. B. Li, H. M. Tang, T. Z. Li, et al., Interval prediction of landslide displacement with dual-output least squares support vector machine and particle swarm optimization algorithms, Acta Geotech., 17 (2022), 4013‒4031. https://doi.org/10.1007/s11440-022-01455-2 doi: 10.1007/s11440-022-01455-2
[43]	Q. Ma, H. Wang, P. Luo, Y. S. Peng, Q. R. Li, Ultra-short-term Railway traction load prediction based on DWT-TCN-PSO_SVR combined model, Int. J. Elec. Power., 135 (2022), 107595. https://doi.org/10.1016/j.ijepes.2021.107595 doi: 10.1016/j.ijepes.2021.107595
[44]	C. L. Dong, X. Meng, L. X. Guo, J. M. Hu, 3D sea surface electromagnetic scattering prediction model based on IPSO-SVR, Remote Sens.-Basel., 14 (2022), 4657. https://doi.org/10.3390/rs14184657 doi: 10.3390/rs14184657

Reader Comments

Your name:*

Email:*
© 2023 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)