Prediction of the dynamics COVID19 epidemic process of using the Lasso regression model
DOI:
https://doi.org/10.26565/2304-6201-2024-64-06Keywords:
prediction, neural network, Lasso Regression Model, LSTM, COVID-19 prediction, Machine Learning, Deep Learning, Multi-scale model, databaseAbstract
This study integrates machine learning and deep learning methods to predict the COVID-19 pandemic.
Relevance. The global outbreak of the COVID-19 pandemic has had a profound impact on public health systems and socio-economic structures worldwide, highlighting the urgent need for effective forecasting tools to aid decision-making. The work is devoted to the development of multi-model framework for epidemic forecasting by integrating advanced methods of mathematical modeling and forecasting theory.
Goal. The purpose of the work was to analyze methods and algorithms for cumulative prediction of COVID-19 cases in order to provide scientific support for public health decision-making.
Research methods. The research methods are based on modern theories of mathematical modeling, artificial intelligence, epidemiological diagnostics, and forecasting theory, namely: Lasso regression, Long Short-Term Memory (LSTM) networks, and LSTM-Attention models. The research details the processes of data preprocessing, model training, evaluation, and visualization to maintain generalization and adaptability in the dynamic pandemic scenario.
The results. The application of Lasso regression model Long Short-Term Memory (LSTM) network for cumulative prediction of COVID-19 cases was investigated to provide scientific support for decision-making. The research details the processes of data preprocessing, model training, evaluation, and visualization to maintain generalization and adaptability in the dynamic pandemic scenario. Additionally, a Multi-Scale LSTM-Attention (MSLA) model was proposed to extract multi-period features from input sequences. These features are critical for addressing data non-stationary.
Conclusions. The task of developing a comprehensive multi-model COVID-19 prediction system by integrating machine learning and deep learning techniques was solved. The system combines Lasso regression, Long Short-Term Memory (LSTM) networks, and a novel Multi-Scale Cumulative Infection Prediction model based on an attention mechanism (MSLA), significantly enhancing prediction accuracy and reliability.
References
Ciotti, M., Ciccozzi, M., Terrinoni, A., Jiang, W. C., Wang, C. B., & Bernardini, S. (2020). The COVID-19 pandemic. Critical Reviews in Clinical Laboratory Sciences, 57(6), 365–388. https://doi.org/10.1080/10408363.2020.1783198
Santosh, K.C. COVID-19 Prediction Models and Unexploited Data. J Med Syst 44, 170 (2020). https://doi.org/10.1007/s10916-020-01645-z
Singh, R. K., Rani, M., Bhagavathula, A. S., Sah, R., Rodriguez-Morales, A. J., Kalita, H., ... & Kumar, P. (2020). Prediction of the COVID-19 pandemic for the top 15 affected countries: Advanced autoregressive integrated moving average (ARIMA) model. JMIR public health and surveillance, 6(2), e19115. https://doi.org/10.2196/19115
Alabdulrazzaq, H., Alenezi, M. N., Rawajfih, Y., Alghannam, B. A., Al-Hassan, A. A., & Al-Anzi, F. S. (2021). On the accuracy of ARIMA based prediction of COVID-19 spread. Results in Physics, 27, 104509. https://doi.org/10.1016/j.rinp.2021.104509
Heidari, A., Jafari Navimipour, N., Unal, M. et al. Machine learning applications for COVID-19 outbreak management. Neural Comput & Applic 34, 15313–15348 (2022). https://doi.org/10.1007/s00521-022-07424-w
Alakus, T. B., & Turkoglu, I. (2020). Comparison of deep learning approaches to predict COVID-19 infection. Chaos, Solitons & Fractals, 140, 110120. https://doi.org/10.1016/j.chaos.2020.110120
Shahid, F., Zameer, A., & Muneeb, M. (2020). Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM. Chaos, Solitons & Fractals, 140, 110212. https://doi.org/10.1016/j.chaos.2020.110212
Islam, M. Z., Islam, M. M., & Asraf, A. (2020). A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images. Informatics in medicine unlocked, 20, 100412. https://doi.org/10.1016/j.imu.2020.100412
Shah, P. M., Ullah, F., Shah, D., Gani, A., Maple, C., Wang, Y., & Islam, S. U. (2021). Deep GRU-CNN model for COVID-19 detection from chest X-rays data. Ieee Access, 10, 35094-35105. https://doi.org/10.1109/ACCESS.2021.3077592
Yu, Y., Si, X., Hu, C., & Zhang, J. (2019). A review of recurrent neural networks: LSTM cells and network architectures. Neural computation, 31(7), 1235-1270. https://doi.org/10.1162/neco_a_01199
Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., & Wang, Y. (2021). Transformer in transformer. Advances in neural information processing systems, 34, 15908-15919.
Ranstam, J., & Cook, J. A. (2018). LASSO regression. Journal of British Surgery, 105(10), 1348-1348. https://doi.org/10.1002/bjs.10895
Van Tinh, N. (2020). Forecasting of COVID-19 confirmed cases in Vietnam using fuzzy time series model combined with particle swarm optimization. Comput Res Prog Appl Sci Eng, 6(2), 114-120. https://crpase.com/archive/CRPASE-Vol-06-issue-02-20802699.pdf
Song, J., Xie, H., Gao, B., Zhong, Y., Gu, C., & Choi, K. S. (2021). Maximum likelihood-based extended Kalman filter for COVID-19 prediction. Chaos, Solitons & Fractals, 146, 110922. https://doi.org/10.1016/j.chaos.2021.110922
Chen Guoxin (2024) Prediction of the dynamics covid19 epidemic process of using the Lasso regression model (master diploma) V. N. Karazin Kharkiv National University.
