期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2021
卷号：99
期号：1
页码：159
出版社：Journal of Theoretical and Applied
摘要：The world has recently been plagued by the pandemic of Corona Virus Disease 2019 (COVID-19). Since it is reported in Wuhan city of China, on the 8th of December 2019, the COVID-19 invaded every country around the world. As of October 24th, 2020, a total of 42,549,383 confirmed cases of COVID-19 were officially announced and the death toll was 1,150,163. Globally, huge volumes of datasets are generated regarding COVID-19 pandemic to open new research arena for machine learning and artificial intelligence researchers. In this work, an integration of data warehouse with deep learning approach, namely LSTM model, is introduced to predict the spread of the COVID-19 in selected countries. We present the design and development of COVID-warehouse, a data warehouse that integrates and stores the COVID-19 data made available daily by different countries. The basic idea of the framework is to use a COVID19 time-series dataset for analysis by machine learning models to make forecasting of future trend based on present values. Ultimately, the proposed prediction model can be applied to predict for other countries as the nature of the virus is the same everywhere. In terms of R2 metric, the experimental results of the decision tree model outperforms other models for recovery cases compared with confirmed and death cases. Recovery cases have a R2 of 0.996011, death cases have a R2 of 0.993124 and confirmed cases have a R2 of 0.991676. Finally, our results emphasize the importance of enforcing the public health advice of social distancing as well as applying the infection control measures to combat COVID-19 before it becomes too late.
关键词：COVID-19 Virus; Infection control; Artificial intelligence; Data Warehouse; Deep Learning Model; Prediction.
