bebi 21: e2

Research Article

Automated Pipeline for Continual Data Gathering and Retraining of the Machine Learning-Based COVID-19 Spread Models

Download30 downloads
  • @ARTICLE{10.4108/eai.4-5-2021.169582,
        author={S. Baressi Šegota and I. Lorencin and N. Anđelić and D. Štifanić and J. Musulin and S. Vlahinić and T. Šušteršič and A. Blagojević and Z. Car},
        title={Automated Pipeline for Continual Data Gathering and Retraining of the Machine Learning-Based COVID-19 Spread Models},
        journal={EAI Endorsed Transactions on Bioengineering and Bioinformatics: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={BEBI},
        year={2021},
        month={5},
        keywords={Artificial Intelligence, Bio-engineering, Bio-inspired systems, Bio-inspired models, COVID-19, Epidemiology Curves, Machine Learning, Multilayer Perceptron},
        doi={10.4108/eai.4-5-2021.169582}
    }
    
  • S. Baressi Šegota
    I. Lorencin
    N. Anđelić
    D. Štifanić
    J. Musulin
    S. Vlahinić
    T. Šušteršič
    A. Blagojević
    Z. Car
    Year: 2021
    Automated Pipeline for Continual Data Gathering and Retraining of the Machine Learning-Based COVID-19 Spread Models
    BEBI
    EAI
    DOI: 10.4108/eai.4-5-2021.169582
S. Baressi Šegota1,*, I. Lorencin1, N. Anđelić1, D. Štifanić1, J. Musulin1, S. Vlahinić1, T. Šušteršič2,3, A. Blagojević2,3, Z. Car1
  • 1: University of Rijeka, Faculty of Engineering, Vukovarska 58, 51000 Rijeka, Croatia
  • 2: Bioengineering Research and Development Center (BioIRC), Prvoslava Stojanovića 6, 34000 Kragujevac, Serbia
  • 3: University of Kragujevac, Faculty of Engineering, Sestre Janjić 6, 34000 Kragujevac, Serbia
*Contact email: sbaressisegota@riteh.hr

Abstract

INTRODUCTION: The development of epidemiological curve models is one of the key factors in the combat of epidemiological diseases such as COVID-19.

OBJECTIVES: The goal of this paper is to develop a system for automatic training and testing of AI-based regressive models of epidemiological curves using public data, which involves automating the data acquisition and speeding up the training of the models.

METHODS: The research applies Multilayer Perceptron (MLP) for the creation of models, implemented within a system for automatic data fetching and training, and e valuated using the coefficient of determination (R2). Training time is lowered through the application of data filtering and simplifying the model selection.

RESULTS: The developed system can train high precision models rapidly, allowing for quick model delivery All trained models achieve scores which are higher than 0.95.

CONCLUSION: The results show that the development of a quick COVID-19 spread modeling system is possible.