A hybrid deep learning method with attention for COVID-19 spread forecasting

Abdelkader Dairi; Fouzi Harrou; Ying Sun; Sofiane Khadraoui

doi:10.1088/978-0-7503-3795-3ch5

A hybrid deep learning method with attention for COVID-19 spread forecasting

Abdelkader Dairi, Fouzi Harrou, Ying Sun, Sofiane Khadraoui

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

This chapter introduces a hybrid deep learning model for COVID-19 spread forecasting. Specifically, the proposed approach combines the desirable characteristics of bidirectional long short-term memory (BiLSTM), convolutional neural networks (CNN), and an attention mechanism. Importantly, this combination, called BiLSTM-A-CNN, is intended to amalgamate the ability of LSTMs to model time dependencies, the capability of the attention mechanism to highlight relevant features, and the noted ability of CNNs to extract features from complex data. The use of the BiLSTM-A-CNN model is expected to improve the forecasting accuracy of future COVID-19 trends.

Original language	English (US)
Title of host publication	Artificial Intelligence Strategies for Analyzing COVID-19 Pneumonia Lung Imaging, Volume 1
Publisher	IOP Publishing
DOIs	https://doi.org/10.1088/978-0-7503-3795-3ch5
State	Published - Apr 2022

Bibliographical note

KAUST Repository Item: Exported on 2022-04-20
Acknowledged KAUST grant number(s): OSR-2019-CRG7–3800
Acknowledgements: This chapter is based on work supported by the King Abdullah University of Science and Technology (KAUST), Office of Sponsored Research (OSR) under Award No: OSR-2019-CRG7–3800.

Access to Document

10.1088/978-0-7503-3795-3ch5

https://repository.kaust.edu.sa/bitstream/10754/676293/1/Chapter-IOP_AI-COVID-1.pdf

Cite this

@inbook{e39cb1b5437b46ceb565404a69b9a6f5,

title = "A hybrid deep learning method with attention for COVID-19 spread forecasting",

abstract = "This chapter introduces a hybrid deep learning model for COVID-19 spread forecasting. Specifically, the proposed approach combines the desirable characteristics of bidirectional long short-term memory (BiLSTM), convolutional neural networks (CNN), and an attention mechanism. Importantly, this combination, called BiLSTM-A-CNN, is intended to amalgamate the ability of LSTMs to model time dependencies, the capability of the attention mechanism to highlight relevant features, and the noted ability of CNNs to extract features from complex data. The use of the BiLSTM-A-CNN model is expected to improve the forecasting accuracy of future COVID-19 trends.",

author = "Abdelkader Dairi and Fouzi Harrou and Ying Sun and Sofiane Khadraoui",

note = "KAUST Repository Item: Exported on 2022-04-20 Acknowledged KAUST grant number(s): OSR-2019-CRG7–3800 Acknowledgements: This chapter is based on work supported by the King Abdullah University of Science and Technology (KAUST), Office of Sponsored Research (OSR) under Award No: OSR-2019-CRG7–3800.",

year = "2022",

month = apr,

doi = "10.1088/978-0-7503-3795-3ch5",

language = "English (US)",

booktitle = "Artificial Intelligence Strategies for Analyzing COVID-19 Pneumonia Lung Imaging, Volume 1",

publisher = "IOP Publishing",

}

TY - CHAP

T1 - A hybrid deep learning method with attention for COVID-19 spread forecasting

AU - Dairi, Abdelkader

AU - Harrou, Fouzi

AU - Sun, Ying

AU - Khadraoui, Sofiane

N1 - KAUST Repository Item: Exported on 2022-04-20 Acknowledged KAUST grant number(s): OSR-2019-CRG7–3800 Acknowledgements: This chapter is based on work supported by the King Abdullah University of Science and Technology (KAUST), Office of Sponsored Research (OSR) under Award No: OSR-2019-CRG7–3800.

PY - 2022/4

Y1 - 2022/4

N2 - This chapter introduces a hybrid deep learning model for COVID-19 spread forecasting. Specifically, the proposed approach combines the desirable characteristics of bidirectional long short-term memory (BiLSTM), convolutional neural networks (CNN), and an attention mechanism. Importantly, this combination, called BiLSTM-A-CNN, is intended to amalgamate the ability of LSTMs to model time dependencies, the capability of the attention mechanism to highlight relevant features, and the noted ability of CNNs to extract features from complex data. The use of the BiLSTM-A-CNN model is expected to improve the forecasting accuracy of future COVID-19 trends.

AB - This chapter introduces a hybrid deep learning model for COVID-19 spread forecasting. Specifically, the proposed approach combines the desirable characteristics of bidirectional long short-term memory (BiLSTM), convolutional neural networks (CNN), and an attention mechanism. Importantly, this combination, called BiLSTM-A-CNN, is intended to amalgamate the ability of LSTMs to model time dependencies, the capability of the attention mechanism to highlight relevant features, and the noted ability of CNNs to extract features from complex data. The use of the BiLSTM-A-CNN model is expected to improve the forecasting accuracy of future COVID-19 trends.

UR - http://hdl.handle.net/10754/676293

UR - https://iopscience.iop.org/book/978-0-7503-3795-3/chapter/bk978-0-7503-3795-3ch5

U2 - 10.1088/978-0-7503-3795-3ch5

DO - 10.1088/978-0-7503-3795-3ch5

M3 - Chapter

BT - Artificial Intelligence Strategies for Analyzing COVID-19 Pneumonia Lung Imaging, Volume 1

PB - IOP Publishing

ER -

A hybrid deep learning method with attention for COVID-19 spread forecasting

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this