Multi-step influenza forecasting through singular value decomposition and kernel ridge regression with MARCOS-guided gradient-based optimization
Copyright © 2023 Elsevier Ltd. All rights reserved..
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.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:169 |
|---|---|
| Enthalten in: |
Computers in biology and medicine - 169(2024) vom: 05. Feb., Seite 107888 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Hongliang, Guo [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
GBO algorithm |
|---|
| Anmerkungen: |
Date Completed 08.02.2024 Date Revised 08.02.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.compbiomed.2023.107888 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM366484265 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM366484265 | ||
| 003 | DE-627 | ||
| 005 | 20240208232005.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240108s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.compbiomed.2023.107888 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1284.xml |
| 035 | |a (DE-627)NLM366484265 | ||
| 035 | |a (NLM)38157778 | ||
| 035 | |a (PII)S0010-4825(23)01353-7 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Hongliang, Guo |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Multi-step influenza forecasting through singular value decomposition and kernel ridge regression with MARCOS-guided gradient-based optimization |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 08.02.2024 | ||
| 500 | |a Date Revised 08.02.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2023 Elsevier Ltd. All rights reserved. | ||
| 520 | |a 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 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a GBO algorithm | |
| 650 | 4 | |a Influenza forecasting | |
| 650 | 4 | |a Kernel ridge regression | |
| 650 | 4 | |a MARCOS method | |
| 650 | 4 | |a Multi-step ahead | |
| 650 | 4 | |a Singular value decomposition (SVD) | |
| 700 | 1 | |a Zhiyao, Zhang |e verfasserin |4 aut | |
| 700 | 1 | |a Ahmadianfar, Iman |e verfasserin |4 aut | |
| 700 | 1 | |a Escorcia-Gutierrez, José |e verfasserin |4 aut | |
| 700 | 1 | |a Aljehane, Nojood O |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Chengye |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Computers in biology and medicine |d 1970 |g 169(2024) vom: 05. Feb., Seite 107888 |w (DE-627)NLM000382272 |x 1879-0534 |7 nnns |
| 773 | 1 | 8 | |g volume:169 |g year:2024 |g day:05 |g month:02 |g pages:107888 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.compbiomed.2023.107888 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 169 |j 2024 |b 05 |c 02 |h 107888 | ||