Multi-step influenza forecasting through singular value decomposition and kernel ridge regression with MARCOS-guided gradient-based optimization

Guo Hongliang; Zhang Zhiyao; Iman Ahmadianfar; José Escorcia-Gutierrez; Nojood O Aljehane; Chengye Li

doi:10.1016/j.compbiomed.2023.107888

Multi-step influenza forecasting through singular value decomposition and kernel ridge regression with MARCOS-guided gradient-based optimization

Comput Biol Med. 2024 Feb:169:107888. doi: 10.1016/j.compbiomed.2023.107888. Epub 2023 Dec 23.

Authors

Guo Hongliang¹, Zhang Zhiyao², Iman Ahmadianfar³, José Escorcia-Gutierrez⁴, Nojood O Aljehane⁵, Chengye Li⁶

Affiliations

¹ College of Information Technology, Jilin Agricultural University, Changchun, 130118, China. Electronic address: guohongliang@jlau.edu.cn.
² College of Information Technology, Jilin Agricultural University, Changchun, 130118, China. Electronic address: Zhangzhiyao0715@163.com.
³ Information and Communication Technology Research Group, Scientific Research Center, Al-Ayen University, Thi-Qar, Nasiriyah, 64001, Iraq. Electronic address: im.ahmadian@gmail.com.
⁴ Department of Computational Science and Electronics, Universidad de La Costa, CUC, Barranquilla, 080002, Colombia. Electronic address: jescorci56@cuc.edu.co.
⁵ Faculty of Computers and Information Technology, University of Tabuk, Tabuk, Saudi Arabia, Tabuk University, KSA. Electronic address: noaljohani@ut.edu.sa.
⁶ Department of Pulmonary and Critical Care Medicine, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, 325000, China. Electronic address: lichengye41@126.com.

PMID: 38157778
DOI: 10.1016/j.compbiomed.2023.107888

Abstract

This research delves into the significance of influenza outbreaks in public health, particularly the importance of accurate forecasts using weekly Influenza-like illness (ILI) rates. The present work develops a novel hybrid machine-learning model by combining singular value decomposition with kernel ridge regression (SKRR). In this context, a novel hybrid model known as H-SKRR is developed by combining two robust forecasting approaches, SKRR and ridge regression, which aims to improve multi-step-ahead predictions for weekly ILI rates in Southern and Northern China. The study begins with feature selection via XGBoost in the preprocessing phase, identifying optimal precursor information guided by importance factors. It decomposes the original signal using multivariate variational mode decomposition (MVMD) to address non-stationarity and complexity. H-SKRR is implemented by incorporating significant lagged-time components across sub-components. The aggregated forecasted values from these sub-components generate ILI values for two horizons (i.e., 4-and 7-weekly ahead). Employing the gradient-based optimization (GBO) algorithm fine-tunes model parameters. Furthermore, the deep random vector functional link (dRVFL), Ridge regression, and gated recurrent unit neural network (GRU) models were employed to validate the MVMD-H-SKRR-GBO paradigm's effectiveness. The outcomes, assessed using the MARCOS (Measurement of alternatives and ranking according to compromise solution) method as a multi-criteria decision-making method, highlight the superior accuracy of the MVMD-H-SKRR-GBO model in predicting ILI rates. The results clearly highlight the exceptional performance of the MVMD-H-SKRR-GBO model, with outstanding precision demonstrated by impressive R, RMSE, IA, and U95 % values of 0.946, 0.388, 0.970, and 1.075, respectively, at t + 7.

Keywords: GBO algorithm; Influenza forecasting; Kernel ridge regression; MARCOS method; Multi-step ahead; Singular value decomposition (SVD).

MeSH terms

Algorithms
Disease Outbreaks
Humans
Influenza, Human* / epidemiology
Neural Networks, Computer
Public Health