Scribd
Upload
49 views

Presentation 1

This paper proposes a time series forecasting model for COVID-19 cases in different countries. It analyzes COVID-19 data accuracy across nations and identifies research gaps in prior work focusing only on quantitative analysis. The authors aim to create novel predictions by considering both numerical data and other factors using a recurrent neural network model. The methodology examines data from multiple countries, compares accuracy, and builds a prediction system incorporating supplementary knowledge beyond numbers.

Uploaded by

Ashwitha Girish K
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
49 views

Presentation 1

This paper proposes a time series forecasting model for COVID-19 cases in different countries. It analyzes COVID-19 data accuracy across nations and identifies research gaps in prior work focusing only on quantitative analysis. The authors aim to create novel predictions by considering both numerical data and other factors using a recurrent neural network model. The methodology examines data from multiple countries, compares accuracy, and builds a prediction system incorporating supplementary knowledge beyond numbers.

Uploaded by

Ashwitha Girish K
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

2nd IEEE International Conference on Data Decision Support

Systems [ICDDS- 2023]


1st - 2nd December 2023

Paper ID: 23
Title : Time Series Based Forecasting model for Covid-19 in Different Countries
Authors: Ashwitha K & Sowmya K
Affiliation: Nitte Meenakshi Institute of Technology
Outline
RV College of
Engineering

 Introduction
 Literature Survey
 Research gap
 Objectives & Methodology
 Novelty
 Design and Implementation
 Result Analysis
 Conclusion and Future Work
 References
RV College of

Introduction
Engineering

• COVID-19 has been officially diagnosed in approximately 43 million people, claiming


nearly 1 million lives.
• Significant impact on daily activities and economic growth.
• Importance of understanding COVID-19 spread and protective measures.
• Forecasting is complicated by the requirement for significant historical data and the
unpredictability of the future.
• This work examines how data reliability, external variables, and social views affect
forecasting accuracy.
• Since 2019, COVID-19 has grown globally, requiring aggressive measures without a
cure.
• This research attempts to create a deep learning model that forecasts future trends using
all available data to influence community safety decisions
Literature Survey
RV College of
Engineering

• AI Integration : Modified SEIR(susceptible-exposed-infectious-


recovered )model with AI techniques to evaluate intervention impacts. The
calibrated model, incorporating AI techniques, effectively captured
intervention impacts on disease transmission and evaluated the effectiveness
of different measures.

• Fractional-Order Model: Mathematical model with fractional derivatives


for complex dynamics. The findings underscore the efficacy of this
fractional-order model in capturing the inherent nonlinearity and memory
effects associated with the dynamics of the COVID-19 outbreak

• Age Distribution Profiles: Predicting COVID-19 infection origin based on


age distribution. The findings indicated variations in the age distribution of
infected individuals based on the infection's source
Research gap
RV College of
Engineering

The research gap involves exploring differences in data accuracy among countries and
suggests a chance to enhance predictions by including both quantitative and qualitative
aspects beyond the current focus on quantitative analysis.
RV College of
Engineering
Objectives & Methodology

Objectives : To better forecast outcomes by taking consideration not only numerical


values but also other significant factors by examining and comprehending the
accuracy of Covid-19 data in different nations.

Methodology: To gain a more comprehensive understanding of the Covid-19


situation, analyze data from other nations, compare its accuracy, and create a
prediction system using RNN algorithm that incorporates both supplementary
knowledge and numerical data.
RV College of
Engineering
Novelty

• The study is distinctive in that it examines the degree of completeness and accuracy of
the Covid-19 data across different countries. This has not received much prior research.

• In contrast to previous research that mostly relies on numerical data, this study attempts
to create novel predictions regarding Covid-19 by considering both numerical data like
Number of cases, total deaths, new cases, new deaths, and other relevant characteristics
like smokers, diabetic and many more
RV College of
Engineering
Design and Implementation
RV College of
Engineering
Result Analysis
RV College of
Engineering
Conclusion

According to time series forecasts, India will have fewer cases by the end of 2023, and
early reports indicate this prediction. However, there may be potential rises in cases due
to the new Omicron subtype in both China and the United States. In accordance with the
data from its training and validation sets, the Simple RNN model's results utilizing
RMSLE metrics indicate that the best predictions were made in the United States and
India.
RV College of
Engineering
References
[1] Liu, M., Thomadsen, R. & Yao, S. Forecasting the spread of COVID-19 under different reopening strategies. Sci Rep 10,
20367 (2020). https://doi.org/10.1038/s41598-020-77292-8
[2] Ma, R., Zheng, X., Wang, P. et al. The prediction and analysis of COVID- 19 epidemic trend by combining LSTM and
Markov method. Sci Rep 11, 17421 (2021). https://doi.org/10.1038/s41598-021-97037-5
[3] Petropoulos F, Makridakis S (2020) Forecasting the novel coronavirus COVID-19. PLOS ONE 15(3):e0231236.
https://doi.org/10.1371/journal.pone.0231236
[4] Ahmed S. Potential of age distribution profiles for the prediction of COVID-19 infection origin in a patient group. Inform
Med Unlocked. 2020;20:100364.
[5] Shinde GR, Kalamkar AB, Mahalle PN, Dey N, Chaki J, Hassanien AE. Forecasting models for coronavirus disease
(COVID-19): a survey of the state-of-the-art. SN Comput Sci. 2020;1(197):1–15. https://doi.org/10.1007/s42979-020-00209-9.
[6] Yang Z, Zeng Z, Wang K, Wong S-S, Liang W, Zanin M, et al. Modified SEIR and AI prediction of the epidemics trend of
COVID-19 in China under public health interventions. J Thorac Dis. 2020;12(3):165–74.
https://doi.org/10.21037/jtd.2020.02.64.
[7] Rajagopal K, Hasanzadeh N, Parastesh F, Hamarash II, Jafari S. A fractional-order model for the novel coronavirus
(COVID-19) outbreak. Nonlinear Dyn. 2020;101(2020):711–8. https://doi.org/10.1007/s11071- 020-05757-6
[8] Lynch CJ, Gore R. Application of one-, three-, and seven-day forecasts during early onset on the COVID-19 epidemic
dataset using moving average, autoregressive, autoregressive moving average, autoregressive integrated moving average, and
naïve forecasting methods. Data Brief. 2021 Apr;35:106759. doi: 10.1016/j.dib.2021.106759. Epub 2021 Jan 15. PMID:
33521186; PMCID: PMC7834853.
RV College of
Engineering

Thank You

You might also like