Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods

被引:69
作者
Ayoobi, Nooshin [1 ]
Sharifrazi, Danial [2 ]
Alizadehsani, Roohallah [3 ]
Shoeibi, Afshin [4 ,5 ]
Gorriz, Juan M. [6 ]
Moosaei, Hossein [7 ]
Khosravi, Abbas [3 ]
Nahavandi, Saeid [3 ]
Chofreh, Abdoulmohammad Gholamzadeh [8 ]
Goni, Feybi Ariani [9 ]
Klemes, Jiri Jaromir [8 ]
Mosavi, Amir [10 ,11 ]
机构
[1] Savitribai Phule Pune Univ, Dept Math, Pune 411007, Maharashtra, India
[2] Islamic Azad Univ, Sch Tech & Engn, Dept Comp Engn, Shiraz, Iran
[3] Deakin Univ, Inst Intelligent Syst Res & Innovat IISRI, Waurn Ponds, Vic 3217, Australia
[4] Ferdowsi Univ Mashhad, Comp Engn Dept, Mashhad, Razavi Khorasan, Iran
[5] KN Toosi Univ Technol, Biomed Data Acquisit Lab, Fac Elect & Comp Engn, Tehran, Iran
[6] Univ Granada, Dept Signal Theory Networking & Commun, Granada, Spain
[7] Univ Bojnord, Fac Sci, Dept Math, Bojnurd, Iran
[8] Brno Univ Technol VUT Brno, Fac Mech Engn, NETME Ctr, Sustainable Proc Integrat Lab SPIL, Tech 2896-2, Brno 61669, Czech Republic
[9] Brno Univ Technol VUT Brno, Fac Business & Management, Dept Management, Kolejni 2906-4, Brno 61200, Czech Republic
[10] Obuda Univ, John von Neumann Fac Informat, H-1034 Budapest, Hungary
[11] Norwegian Univ Life Sci, Sch Business & Econ, N-1430 As, Norway
关键词
Long Short Term Memory (LSTM); Convolutional Long Short Term Memory (Conv-LSTM); Gated Recurrent Unit (GRU); Bidirectional New Cases of COVID-19; New Deaths of COVID-19; COVID-19; Prediction; Deep learning; Machine learning; MODEL;
D O I
10.1016/j.rinp.2021.104495
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The first known case of Coronavirus disease 2019 (COVID-19) was identified in December 2019. It has spread worldwide, leading to an ongoing pandemic, imposed restrictions and costs to many countries. Predicting the number of new cases and deaths during this period can be a useful step in predicting the costs and facilities required in the future. The purpose of this study is to predict new cases and deaths rate one, three and seven-day ahead during the next 100 days. The motivation for predicting every n days (instead of just every day) is the investigation of the possibility of computational cost reduction and still achieving reasonable performance. Such a scenario may be encountered in real-time forecasting of time series. Six different deep learning methods are examined on the data adopted from the WHO website. Three methods are LSTM, Convolutional LSTM, and GRU. The bidirectional extension is then considered for each method to forecast the rate of new cases and new deaths in Australia and Iran countries. This study is novel as it carries out a comprehensive evaluation of the aforementioned three deep learning methods and their bidirectional extensions to perform prediction on COVID-19 new cases and new death rate time series. To the best of our knowledge, this is the first time that Bi-GRU and Bi-Conv-LSTM models are used for prediction on COVID-19 new cases and new deaths time series. The evaluation of the methods is presented in the form of graphs and Friedman statistical test. The results show that the bidirectional models have lower errors than other models. A several error evaluation metrics are presented to compare all models, and finally, the superiority of bidirectional methods is determined. This research could be useful for organisations working against COVID-19 and determining their long-term plans.
引用
收藏
页数:15
相关论文
共 44 条
  • [11] A familial cluster of pneumonia associated with the 2019 novel coronavirus indicating person-to-person transmission: a study of a family cluster
    Chan, Jasper Fuk-Woo
    Yuan, Shuofeng
    Kok, Kin-Hang
    To, Kelvin Kai-Wang
    Chu, Hin
    Yang, Jin
    Xing, Fanfan
    Liu, Jieling
    Yip, Cyril Chik-Yan
    Poon, Rosana Wing-Shan
    Tsoi, Hoi-Wah
    Lo, Simon Kam-Fai
    Chan, Kwok-Hung
    Poon, Vincent Kwok-Man
    Chan, Wan-Mui
    Ip, Jonathan Daniel
    Cai, Jian-Piao
    Cheng, Vincent Chi-Chung
    Chen, Honglin
    Hui, Christopher Kim-Ming
    Yuen, Kwok-Yung
    [J]. LANCET, 2020, 395 (10223) : 514 - 523
  • [12] Mathematical analysis and simulation of a stochastic COVID-19 Levy jump model with isolation strategy
    Danane, Jaouad
    Allali, Karam
    Hammouch, Zakia
    Nisar, Kottakkaran Sooppy
    [J]. RESULTS IN PHYSICS, 2021, 23
  • [13] Dey R, 2017, MIDWEST SYMP CIRCUIT, P1597, DOI 10.1109/MWSCAS.2017.8053243
  • [14] Di Persio Luca, 2016, International Journal of Circuits, Systems and Signal Processing, V10, P403
  • [15] Demographic science aids in understanding the spread and fatality rates of COVID-19
    Dowd, Jennifer Beam
    Andriano, Liliana
    Brazel, David M.
    Rotondi, Valentina
    Block, Per
    Ding, Xuejie
    Liu, Yan
    Mills, Melinda C.
    [J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2020, 117 (18) : 9696 - 9698
  • [16] Eskandarian R, IDENTIFICATION CLIN IDENTIFICATION CLIN, V2021
  • [17] Analysis and forecast of COVID-19 spreading in China, Italy and France
    Fanelli, Duccio
    Piazza, Francesco
    [J]. CHAOS SOLITONS & FRACTALS, 2020, 134 (134)
  • [18] A comparison of alternative tests of significance for the problem of m rankings
    Friedman, M
    [J]. ANNALS OF MATHEMATICAL STATISTICS, 1940, 11 : 86 - 92
  • [19] New investigation of bats-hosts-reservoir-people coronavirus model and application to 2019-nCoV system
    Gao, Wei
    Baskonus, Haci Mehmet
    Shi, Li
    [J]. ADVANCES IN DIFFERENCE EQUATIONS, 2020, 2020 (01)
  • [20] A new study of unreported cases of 2019-nCOV epidemic outbreaks
    Gao, Wei
    Veeresha, P.
    Baskonus, Haci Mehmet
    Prakasha, D. G.
    Kumar, Pushpendra
    [J]. CHAOS SOLITONS & FRACTALS, 2020, 138