Abstract

Due to the continuous spread of COVID-19 worldwide, it is urgent, especially in the data science era, to develop accurate data driven decision-aided method to early detect its outbreak. Currently, Deep Learning and especially Recurrent Neural Networks (RNN) are one of the promising methods to accurately predict COVID-19 outbreak. However, designing an accurate RNN is always a challenging task because RNN often require big data and computational cost. To overcome these challenges, we propose in this paper a novel method to predict daily COVID-19 positive cases that consists of two steps: 1) data integration where medical data and weather data are integrated to improve both data quantity and quality especially when we deal with countries with less facilities of collecting data and 2) quantum improvement where quantum and classical RNN are integrated to provide super-calculator for the prediction. Experiments on six countries from Africa (Tunisia, Algeria, Senegal, Cameron, Niger, and Nigeria) indicate two main results. First, through data integration, a correlation between medical and weather data is detected where we note a real impact of the weather on COVID-19 outbreak. Second, compared with classical RNN, quantum-enhanced RNN trained on augmented data achieved the best results in terms of accuracy as well as root mean square error (RMSE) and it required the lowest time for training. Thus, our main contributions are i) to enrich medical data by weather data to improve data quality and quantity and ii) to enhance RNN by quantum layers to accurately and speedily forecast COVID-19 outbreak. All implementations and datasets are available online to the scientific community at https://github.com/nasriAhmed/Master_Covid.git.

Recommended Citation

Nasri, A., Ben Yahia, N., Ben Saoud, N. B., & Ben Miled, S. (2022). A Hybrid Method Based on Quantum-enhanced RNN and Data Integration for the Prediction of COVID-19 Outbreak. In R. A. Buchmann, G. C. Silaghi, D. Bufnea, V. Niculescu, G. Czibula, C. Barry, M. Lang, H. Linger, & C. Schneider (Eds.), Information Systems Development: Artificial Intelligence for Information Systems Development and Operations (ISD2022 Proceedings). Cluj-Napoca, Romania: Risoprint. ISBN: 978-973-53-2917-4. https://doi.org/10.62036/ISD.2022.2

Paper Type

Short Paper

DOI

10.62036/ISD.2022.2

Share

COinS
 

A Hybrid Method Based on Quantum-enhanced RNN and Data Integration for the Prediction of COVID-19 Outbreak

Due to the continuous spread of COVID-19 worldwide, it is urgent, especially in the data science era, to develop accurate data driven decision-aided method to early detect its outbreak. Currently, Deep Learning and especially Recurrent Neural Networks (RNN) are one of the promising methods to accurately predict COVID-19 outbreak. However, designing an accurate RNN is always a challenging task because RNN often require big data and computational cost. To overcome these challenges, we propose in this paper a novel method to predict daily COVID-19 positive cases that consists of two steps: 1) data integration where medical data and weather data are integrated to improve both data quantity and quality especially when we deal with countries with less facilities of collecting data and 2) quantum improvement where quantum and classical RNN are integrated to provide super-calculator for the prediction. Experiments on six countries from Africa (Tunisia, Algeria, Senegal, Cameron, Niger, and Nigeria) indicate two main results. First, through data integration, a correlation between medical and weather data is detected where we note a real impact of the weather on COVID-19 outbreak. Second, compared with classical RNN, quantum-enhanced RNN trained on augmented data achieved the best results in terms of accuracy as well as root mean square error (RMSE) and it required the lowest time for training. Thus, our main contributions are i) to enrich medical data by weather data to improve data quality and quantity and ii) to enhance RNN by quantum layers to accurately and speedily forecast COVID-19 outbreak. All implementations and datasets are available online to the scientific community at https://github.com/nasriAhmed/Master_Covid.git.