Data analysis of Covid-19 pandemic and short-term cumulative case forecasting using machine learning time series methods

Ballı, Serkan

doi:10.1016/j.chaos.2020.110512

Cited by 99 publications

(74 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several models have been developed for the prediction of potential risk, such as infection rate increases, using different data forms [12][13][14][15][16][17][18]. With the emerging of new virus mutations [19], it has become unclear how such forecasting models designed using data obtained at the first generation of the virus spread can still be efficient to predict effects from emerging variants of the virus.…”

Section: Introductionmentioning

confidence: 99%

Infectivity Upsurge by COVID-19 Viral Variants in Japan: Evidence from Deep Learning Modeling

Rashed

Hirata

2021

IJERPH

View full text Add to dashboard Cite

The significant health and economic effects of COVID-19 emphasize the requirement for reliable forecasting models to avoid the sudden collapse of healthcare facilities with overloaded hospitals. Several forecasting models have been developed based on the data acquired within the early stages of the virus spread. However, with the recent emergence of new virus variants, it is unclear how the new strains could influence the efficiency of forecasting using models adopted using earlier data. In this study, we analyzed daily positive cases (DPC) data using a machine learning model to understand the effect of new viral variants on morbidity rates. A deep learning model that considers several environmental and mobility factors was used to forecast DPC in six districts of Japan. From machine learning predictions with training data since the early days of COVID-19, high-quality estimation has been achieved for data obtained earlier than March 2021. However, a significant upsurge was observed in some districts after the discovery of the new COVID-19 variant B.1.1.7 (Alpha). An average increase of 20–40% in DPC was observed after the emergence of the Alpha variant and an increase of up to 20% has been recognized in the effective reproduction number. Approximately four weeks was needed for the machine learning model to adjust the forecasting error caused by the new variants. The comparison between machine-learning predictions and reported values demonstrated that the emergence of new virus variants should be considered within COVID-19 forecasting models. This study presents an easy yet efficient way to quantify the change caused by new viral variants with potential usefulness for global data analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Infectivity Upsurge by COVID-19 Viral Variants in Japan: Evidence from Deep Learning Modeling

Rashed

Hirata

2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…While the number of new cases in Brazil, if no second peak wave in 2021, the cumulative number of cases may rise to 30 M. Its cumulative number of deaths may reach to 700,000, due to its relatively high case fatality rate. The numbers of cumulative cases from only these 3 countries will exceed 120 M, that will be far over some estimation of 80 M in 2021 worldwide [37] . From a global perspective, countries and regions where epidemic prevention measures were in place, community isolation, public health supervision, and government regulation were better, the epidemic trends could be seen to have slowed down [8,10,19] .…”

Section: Discussionmentioning

confidence: 86%

Global Pandemic Trends of COVID-19 in 2020

Chen

Cai

Chen

2021

Preprint

View full text Add to dashboard Cite

Background: The novel coronavirus pneumonia (COVID-19) has been global threaten to public health. This paper provides perspective to the decision-making for public health control of the pandemic or the spread of epidemic.Methods: According to the WHO global reported database, we developed and used the number of cumulative cases, and the number of cumulative deaths to calculate and analyze rates of incidence, mortality, and fatality by country, with respect to the 30 highest outbreak (Top 30) countries.Results： As of December 31, 2020, of the global population of 7.585 billion, the cumulative number of reported cases was 81,475,053, and the cumulative number of deaths was 1,798,050. The incidence rate of COVID-19 was 1074.13 per 100,000 population, the mortality rate was 23.70 per 100,000, and the case fatality rate was 2.21%. Among the Top 30 countries, the five countries with the highest number of reported cumulative cases were, in rank, the United States (19,346,790 cases), India (10,266,674), Brazil (7,563,551), Russia (3,159,297) and France (2,556,708), and the five countries with the highest number of cumulative deaths were the United States (335,789 cases), Brazil (192,681), India (148,738), Mexico (123,845) and Italy (73,604). Globally, the countries with the highest incidence rate were, in rank, Andorra, Luxembourg, Montenegro, San Marino, and Czechia; the countries with the highest mortality rate were, in rank, San Marino, Belgium, Slovenia, Italy, and North Macedonia. The highest fatality rate was found in Yemen, Mexico, Montserrat, Isle of Man, and Ecuador, respectively. In China, 96,673 cases of COVID-19 and 4788 deaths were reported in 2020, ranking the 78th and the 43rd, respectively, in the world. The incidence rate and mortality rate were 6.90/105 and 0.34/105, respectively, ranking 207th and 188th in the world. The case fatality rate was 4.95%, ranking 11th in the world.Conclusions： The COVID-19 prevalence is still on the rise, and the turning points of incidence and mortality are not yet forecasted. Personal protection, anti-epidemic measures and efforts from public health personnel, medical professionals, biotechnology R&D personnel, effectiveness of the vaccination programs and the governments, are the important factors to determine the future prevalence of this coronavirus disease.

show abstract

“…Kumar & Kumara ( 2020 ) utilized pre and post COVID-19 effects in market capitalization. Ballı ( 2020 ) also proposed data analysis of the pandemic using machine learning techniques like learning regression, support vector machine (SVM), multilayer perceptron, and random forecast.…”

Section: Review Of the Literaturementioning

confidence: 99%

Integration of genetic algorithm with artificial neural network for stock market forecasting

Sharma

Hota

Brown

et al. 2021

Int J Syst Assur Eng Manag

View full text Add to dashboard Cite

Traditional statistical as well as artificial intelligence techniques are widely used for stock market forecasting. Due to the nonlinearity in stock data, a model developed using the traditional or a single intelligent technique may not accurately forecast results. Therefore, there is a need to develop a hybridization of intelligent techniques for an effective predictive model. In this study, we propose an intelligent forecasting method based on a hybrid of an Artificial Neural Network (ANN) and a Genetic Algorithm (GA) and uses two US stock market indices, DOW30 and NASDAQ100, for forecasting. The data were partitioned into training, testing, and validation datasets. The model validation was done on the stock data of the COVID-19 period. The experimental findings obtained using the DOW30 and NASDAQ100 reveal that the accuracy of the GA and ANN hybrid model for the DOW30 and NASDAQ100 is greater than that of the single ANN (BPANN) technique, both in the short and long term.

show abstract

Data analysis of Covid-19 pandemic and short-term cumulative case forecasting using machine learning time series methods

Abstract: Highlights The cumulative coronavirus cases for USA, Germany and Global are forecasted. Four different machine learning time series models are employed. SVM model achieves the best trend. Largest extreme value distribution fits best for Covid-19 global cumulative weekly cases.

Cited by 99 publications

References 18 publications

Infectivity Upsurge by COVID-19 Viral Variants in Japan: Evidence from Deep Learning Modeling

Infectivity Upsurge by COVID-19 Viral Variants in Japan: Evidence from Deep Learning Modeling

Global Pandemic Trends of COVID-19 in 2020

Integration of genetic algorithm with artificial neural network for stock market forecasting

Contact Info

Product

Resources

About