Time series forecasting of Covid-19 using deep learning models: India-USA comparative case study

Abstract Covid-19 is a highly contagious virus which almost freezes the world along with its economy. Its ability of human-to-human and surface-to-human transmission turns the world into catastrophic phase. In this study, our aim is to predict the future conditions of novel Coronavirus to recede its impact. We have proposed deep learning based comparative analysis of Covid-19 cases in India and USA. The datasets of confirmed and death cases of Covid-19 are taken into consideration. The recurrent neural network (RNN) based variants of long short term memory (LSTM) such as Stacked LSTM, Bi-directional LSTM and Convolutional LSTM are used to design the proposed methodology and forecast the Covid-19 cases for one month ahead. Convolution LSTM outperformed the other two models and predicts the Covid-19 cases with high accuracy and very less error for all four datasets of both countries. Upward/downward trend of forecasted Covid-19 cases are also visualized graphically, which would be helpful for researchers and policy makers to mitigate the mortality and morbidity rate by streaming the Covid-19 into right direction.

[1]  Z. Zhao,et al.  How well can we forecast the COVID-19 pandemic with curve fitting and recurrent neural networks? , 2020, medRxiv.

[2]  Winston H. Hsu,et al.  Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos , 2019, IEEE Transactions on Multimedia.

[3]  Vibhakar Mansotra,et al.  A Model for Forecasting Tourists Arrival in J&K, India , 2015 .

[4]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[5]  Amal I. Saba,et al.  Forecasting the prevalence of COVID-19 outbreak in Egypt using nonlinear autoregressive artificial neural networks , 2020, Process Safety and Environmental Protection.

[6]  C KAHN,et al.  HISTORY OF SMALLPOX AND ITS PREVENTION. , 1963, American journal of diseases of children.

[7]  Ahmad Athif Mohd Faudzi,et al.  COVID-19 epidemic in Malaysia: Impact of lock-down on infection dynamics , 2020, medRxiv.

[8]  Warwick J. McKibbin,et al.  Global Macroeconomic Consequences of Pandemic Influenza , 2006 .

[9]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  Alex Sherstinsky,et al.  Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network , 2018, Physica D: Nonlinear Phenomena.

[11]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[12]  Yong Yu,et al.  A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures , 2019, Neural Computation.

[13]  Burcu Tepekule,et al.  icumonitoring.ch: a platform for short-term forecasting of intensive care unit occupancy during the COVID-19 epidemic in Switzerland. , 2020, Swiss medical weekly.

[14]  Chih-En Kuo,et al.  Automatic Sleep Staging Based on a Hybrid Stacked LSTM Neural Network: Verification Using Large-Scale Dataset , 2020, IEEE Access.

[15]  Wes McKinney,et al.  Data Structures for Statistical Computing in Python , 2010, SciPy.

[16]  P. Horby,et al.  A novel coronavirus outbreak of global health concern , 2020, The Lancet.

[17]  Nilanjan Dey,et al.  Forecasting Models for Coronavirus Disease (COVID-19): A Survey of the State-of-the-Art , 2020, SN Computer Science.

[18]  L. Morawska,et al.  It Is Time to Address Airborne Transmission of Coronavirus Disease 2019 (COVID-19) , 2020, Clinical Infectious Diseases.

[19]  Benny P. L. Lo,et al.  EEG-based user identification system using 1D-convolutional long short-term memory neural networks , 2019, Expert Syst. Appl..

[20]  S. DeWitte,et al.  Mortality Risk and Survival in the Aftermath of the Medieval Black Death , 2014, PloS one.

[21]  Labode Popoola,et al.  ONLINE FORECASTING OF COVID-19 CASES IN NIGERIA USING LIMITED DATA , 2020, Data in Brief.

[22]  Refat Khan Pathan,et al.  Time series prediction of COVID-19 by mutation rate analysis using recurrent neural network-based LSTM model , 2020, Chaos, Solitons & Fractals.

[23]  Y. Hu,et al.  Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China , 2020, The Lancet.

[24]  Yu Zheng,et al.  An ensemble framework based on convolutional bi-directional LSTM with multiple time windows for remaining useful life estimation , 2020, Comput. Ind..

[25]  B. K. Panigrahi,et al.  Prediction and analysis of COVID-19 positive cases using deep learning models: A descriptive case study of India , 2020, Chaos, Solitons & Fractals.

[26]  M. Hariri,et al.  THE COVID-19 FORECAST IN NORTHWEST SYRIAThe Imperative of Global Action to Avoid Catastrophe , 2020, medRxiv.

[27]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[28]  Travis E. Oliphant,et al.  Guide to NumPy , 2015 .

[29]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[30]  Lidia Morawska,et al.  It is Time to Address Airborne Transmission of COVID-19 , 2020, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[31]  David W. Stahle,et al.  Megadrought and Megadeath in 16th Century Mexico , 2002, Emerging infectious diseases.

[32]  SchmidhuberJürgen,et al.  2005 Special Issue , 2005 .

[33]  L. Chaari,et al.  ProgNet: Covid-19 prognosis using recurrent andconvolutional neural networks , 2020, medRxiv.

[34]  Ayesha Sohail,et al.  Forecasting the timeframe of 2019-nCoV and human cells interaction with reverse engineering , 2020, Progress in Biophysics and Molecular Biology.

[35]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[36]  Ali Dehghantanha,et al.  An Enhanced Stacked LSTM Method With No Random Initialization for Malware Threat Hunting in Safety and Time-Critical Systems , 2020, IEEE Transactions on Emerging Topics in Computational Intelligence.