{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:31:26Z","timestamp":1760059886911,"version":"build-2065373602"},"reference-count":29,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T00:00:00Z","timestamp":1752796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62263018"],"award-info":[{"award-number":["62263018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>The spread of COVID-19 is influenced by multiple factors, including control policies, virus characteristics, individual behaviors, and environmental conditions, exhibiting highly complex nonlinear dynamic features. The time series of new confirmed cases shows significant nonlinearity and non-stationarity. Traditional prediction methods that rely solely on one-dimensional case data struggle to capture the multi-dimensional features of the data and are limited in handling nonlinear and non-stationary characteristics. Their prediction accuracy and generalization capabilities remain insufficient, and most existing studies focus on single-step forecasting, with limited attention to multi-step prediction. To address these challenges, this paper proposes a multi-module fusion prediction model\u2014TSMixer-BiKSA network\u2014that integrates multi-feature inputs, Variational Mode Decomposition (VMD), and a dual-branch parallel architecture for 1- to 3-day-ahead multi-step forecasting of new COVID-19 cases. First, variables highly correlated with the target sequence are selected through correlation analysis to construct a feature matrix, which serves as one input branch. Simultaneously, the case sequence is decomposed using VMD to extract low-complexity, highly regular multi-scale modal components as the other input branch, enhancing the model\u2019s ability to perceive and represent multi-source information. The two input branches are then processed in parallel by the TSMixer-BiKSA network model. Specifically, the TSMixer module employs a multilayer perceptron (MLP) structure to alternately model along the temporal and feature dimensions, capturing cross-time and cross-variable dependencies. The BiGRU module extracts bidirectional dynamic features of the sequence, improving long-term dependency modeling. The KAN module introduces hierarchical nonlinear transformations to enhance high-order feature interactions. Finally, the SA attention mechanism enables the adaptive weighted fusion of multi-source information, reinforcing inter-module synergy and enhancing the overall feature extraction and representation capability. Experimental results based on COVID-19 case data from Italy and the United States demonstrate that the proposed model significantly outperforms existing mainstream methods across various error metrics, achieving higher prediction accuracy and robustness.<\/jats:p>","DOI":"10.3390\/computers14070290","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T14:38:36Z","timestamp":1752849516000},"page":"290","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Forecasting Method for COVID-19 Epidemic Trends Using VMD and TSMixer-BiKSA Network"],"prefix":"10.3390","volume":"14","author":[{"given":"Yuhong","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China"}]},{"given":"Guihong","family":"Bi","sequence":"additional","affiliation":[{"name":"Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China"}]},{"given":"Taonan","family":"Tong","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China"}]},{"given":"Shirui","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Xu, L., Magar, R., and Farimani, A.B. (2022). Forecasting COVID-19 new cases using deep learning methods. Comput. Biol. Med., 144.","DOI":"10.1016\/j.compbiomed.2022.105342"},{"key":"ref_2","first-page":"1003","article-title":"Prediction method of the pandemic trend of COVID-19 based on machine learning","volume":"63","author":"Jianqiang","year":"2023","journal-title":"J. Tsinghua Univ. (Sci. Technol.)"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"165","DOI":"10.21037\/jtd.2020.02.64","article-title":"Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions","volume":"12","author":"Yang","year":"2020","journal-title":"J. Thorac. Dis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/j.ijforecast.2020.10.001","article-title":"Comparing the accuracy of several network-based COVID-19 prediction algorithms","volume":"38","author":"Achterberg","year":"2022","journal-title":"Int. J. Forecast."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Gupta, R., Pandey, G., Chaudhary, P., and Pal, S.K. (2020). Machine learning models for government to predict COVID-19 outbreak. Digit. Gov. Res. Pract., 1.","DOI":"10.1145\/3411761"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Liu, X.X., and Fong, S. (2020, January 22\u201324). Towards a realistic model for simulating spread of infectious COVID-19 disease. Proceedings of the 2020 4th International Conference on Big Data and Internet of Things, Singapore.","DOI":"10.1145\/3421537.3421550"},{"key":"ref_7","first-page":"1495","article-title":"Prediction model of COVID-19 based on spatiotemporal attention mechanism","volume":"48","author":"Bao","year":"2021","journal-title":"J. Beihang Univ. (Beijing Univ. Aeronaut. Astronaut.)"},{"key":"ref_8","first-page":"49","article-title":"Review of COVID-19 Propagation Prediction Methods","volume":"59","author":"Wang","year":"2023","journal-title":"J. Comput. Eng. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, S.T., and Yang, L.H. (2025). A hybrid data assimilation method based on real-time Ensemble Kalman filtering and KNN for COVID-19 prediction. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-85593-z"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yan, Z., Wang, D., Yang, M., Li, Z., Gong, X., Wu, D., Zhai, L., Zhang, W., and Wang, Y. (2022). Prediction and analysis of COVID-19 daily new cases and cumulative cases: Times series forecasting and machine learning models. BMC Infect. Dis., 22.","DOI":"10.1186\/s12879-022-07472-6"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nikparvar, B., Rahman, M.M., Hatami, F., and Thill, J.-C. (2021). Spatio-temporal prediction of the COVID-19 pandemic in US counties: Modeling with a deep LSTM neural network. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-01119-3"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tang, S., and Yu, G. (2023). An interpretable hybrid predictive model of COVID-19 cases using autoregressive model and LSTM. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-33685-z"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, C., and Sun, G.X. (2024). COVID-19 spreading prediction model based on a multi-head self-attention mechanism. Preprint.","DOI":"10.21203\/rs.3.rs-4051560\/v1"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jin, W., Dong, S., Yu, C., and Luo, Q. (2022). A data-driven hybrid ensemble AI model for COVID-19 infection forecast using multiple neural networks and reinforced learning. Comput. Biol. Med., 146.","DOI":"10.1016\/j.compbiomed.2022.105560"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3981","DOI":"10.1109\/ACCESS.2023.3347403","article-title":"Models for COVID-19 data prediction based on improved LSTM-ARIMA algorithms","volume":"12","author":"Jin","year":"2024","journal-title":"IEEE Access"},{"key":"ref_16","unstructured":"Chen, S.A., Li, C.L., Arik, S.O., Yoder, N.C., and Pfister, T. (2023). Tsmixer: An all-mlp architecture for time series forecasting. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100143","DOI":"10.1016\/j.jfds.2024.100143","article-title":"Time-mixing and feature-mixing modelling for realized volatility forecast: Evidence from TSMixer model","volume":"10","author":"Souto","year":"2024","journal-title":"J. Financ. Data Sci."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lee, Y., and Jeong, J. (2025). TSMixer- and Transfer Learning-Based Highly Reliable Prediction with Short-Term Time Series Data in Small-Scale Solar Power Generation Systems. Energies, 18.","DOI":"10.3390\/en18040765"},{"key":"ref_19","unstructured":"Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Soljacic, M., Hou, T.Y., and Tegmark, M. (2024). Kan: Kolmogorov-arnold networks. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"133417","DOI":"10.1016\/j.energy.2024.133417","article-title":"Battery state of charge estimation for electric vehicle using Kolmogorov-Arnold networks","volume":"311","author":"Sulaiman","year":"2024","journal-title":"Energy"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"132430","DOI":"10.1016\/j.jhydrol.2024.132430","article-title":"EKLT: Kolmogorov-Arnold attention-driven LSTM with Transformer model for river water level prediction","volume":"649","author":"Ren","year":"2025","journal-title":"J. Hydrol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"105415","DOI":"10.1016\/j.cageo.2023.105415","article-title":"Land subsidence simulation based on Extremely Randomized Trees combined with Monte Carlo algorithm","volume":"178","author":"Wang","year":"2023","journal-title":"Comput. Geosci."},{"key":"ref_23","first-page":"422","article-title":"Short-term wind power prediction based on VMD and improved BiLSTM","volume":"45","author":"Zhu","year":"2024","journal-title":"J. Sol. Energy"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhang, X.S., Vynnycky, E., Charlett, A., Angelis, D.D., Chen, Z., and Wei Liu, W. (2021). Transmission dynamics and control measures of COVID-19 outbreak in China: A modelling study. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-81985-z"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, N., Bi, G., Chen, S., Luo, Z., and Shen, X. (2025). Carbon Price Forecasting Using a Hybrid Deep Learning Model: TKMixer-BiGRU-SA. Symmetry, 17.","DOI":"10.3390\/sym17060962"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"106157","DOI":"10.1016\/j.engappai.2023.106157","article-title":"Improved LSTM-based deep learning model for COVID-19 prediction using optimized approach","volume":"122","author":"Zhou","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2365334","DOI":"10.1080\/09540091.2024.2365334","article-title":"TfrAdmCov: A robust transformer encoder based model with Adam optimizer algorithm for COVID-19 mutation prediction","volume":"36","author":"Burukanli","year":"2024","journal-title":"Connect. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e26158","DOI":"10.1016\/j.heliyon.2024.e26158","article-title":"LSTM algorithm optimization for COVID-19 prediction model","volume":"10","author":"Sembiring","year":"2024","journal-title":"Heliyon"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"8805","DOI":"10.1016\/j.egyr.2022.07.005","article-title":"Decomposition-based wind power forecasting models and their boundary issue: An in-depth review and comprehensive discussion on potential solutions","volume":"8","author":"Chen","year":"2022","journal-title":"Energy Rep."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/7\/290\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:12:24Z","timestamp":1760033544000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/7\/290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":29,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["computers14070290"],"URL":"https:\/\/doi.org\/10.3390\/computers14070290","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2025,7,18]]}}}