Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
COVID-19 forecasting using shifted Gaussian Mixture Model with similarity-based estimation
Date
2022-10-01
Author
Külah, Emre
Çetinkaya, Yusuf Mucahit
Özer, Arif Görkem
Alemdar, HANDE
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
141
views
0
downloads
Cite This
The COVID-19 pandemic has caused a pronounced disturbance in the social environments and economies of many countries worldwide. Credible forecasting methods to predict the pandemic’s progress can allow countries to control the disease’s spread and decrease the number of severe cases. This study presents a novel approach, called the Shifted Gaussian Mixture Model with Similarity-based Estimation (SGSE), that forecasts the future of a specific country’s daily new case values by examining similar behavior in other countries. The model uses daily new case values collected since the pandemic began and finds countries with similar trends using a specific time offset. The daily new case values data between the first day and(today−N)thday are transformed by employing the Gaussian Mixture Model (GMM) and, subsequently, a new vector of features is obtained for each country. Using these feature vectors, countries that show similar statistics in the past are found for any forecasted country. The future of the corresponding country is forecasted by taking the mean of the time-series plots after the offset points of similar countries are calculated. A brand new metric called a trend similarity score, which calculates the similarity between forecasted and actual values is also presented in this study. While the SGSE trend similarity score median varies between 0.903–0.947, based on the selection of the distance metric, the ARIMA model yields only 0.642. The performance of the SGSE was compared in seven European countries using four different public projects submitted to The European COVID-19 Forecast Hub. The SGSE gives the most accurate forecasts compared to all other models. The test sets’ results show that trends and plateaus are predicted accurately for many countries.
URI
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576929/
https://hdl.handle.net/11511/100597
Journal
EXPERT SYSTEMS WITH APPLICATIONS
DOI
https://doi.org/10.1016/j.eswa.2022.119034
Collections
Department of Computer Engineering, Article
Suggestions
OpenMETU
Core
Duygu Düzenleme ve Koronavirüs Kaygısı: Algılanan Sosyal Desteğin Aracı Rolü
Erden, Nazif Kutay; Sarı Arasıl, Ayşe Berna (ODTÜ- AYNA Klinik Psikoloji Destek Ünitesi, 2022-6)
COVID-19 virüsü tüm dünyayı hızla etkisi altına almıştır. Dünya çapında çeşitli karantinalar uygulanmış, insanların zorunlu durumlar haricinde evlerinden çıkmamaları, maske ve mesafe kavramlarına dikkat etmeleri için kesin kurallar konulmuştur. Alışılagelmiş davranış dinamiklerinin dışına çıkmak zorunda kalan bireylerde çeşitli duygu ve davranış değişiklikleri görülebilir. Dolayısıyla COVID-19 küresel salgını yalnızca fiziksel iyi oluş için değil mental iyi oluş için de bir risk faktörü oluşturabilir. Salgı...
Covid-19 Risk Analysis of Turkey in the Context of Syrian Influx
Özen, İlhan Can; Derin Güre, Pınar; Yargici, Ecem (2022-05-01)
the COVID-19 pandemic difference between countries, in the international comparisons of COVID-19performance of countries, and in the experience with COVID-19 of different subgroups within countries.International scholars are needed to understand the reasons behind the long-term strategy differencesbetween countries and why certain populations have been protected and others left unprotected during thisCOVID-19 era.The COVID-19 crisis is finding the unknown vulnerabilities of many countries, as well as allowi...
A PROBABILISTIC ASSESSMENT OF SARS-COV-2 HOST INTERACTIONS IN THE CONTEXT OF META-COMMUNITY AND URBAN ECOLOGY
Nehri, Leman Nur; Eroğlu, Seçkin; Department of Biology (2021-6-29)
Coronavirus disease 2019 (COVID-19) is an ongoing pandemic that was detected in Wuhan, China, in December 2019 and spread all around the world. COVID-19 is caused by Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which spreads through close contact. Many studies have been conducted on the transmission, virulence, and immune response of SARS-CoV-2. The intracellular mechanism of action of the virus and various host interaction pathways are also known. In addition, there are many studies on the...
Socio-cultural Correlates of the COVID-19 Outcomes
Lajunen, Timo; Gaygısız Lajunen, Esma; GAYGISIZ, ÜMMÜGÜLSÜM (2022-08-01)
While basically all countries have been hit by the COVID-19 pandemic, the impact has varied in large degrees among countries. In the present study, national differences in six COVID-19 indicators (COVID-19 deaths per capita, excess mortality, change in GDP per capita, vaccination rate, stringency index, and overall impact of the pandemic) were studied in relation to socio-economic and Hofstede's cultural dimensions by using the latest data available. The results differed to some degree from the studies cond...
Effects of the COVID-19 pandemic on the environment, waste management, and energy sectors: a deeper look into the long-term impacts
Mohamed, Badr A.; Fattah, I. M. Rizwanul; Yousaf, Balal; Periyasamy, Selvakumar (2022-01-01)
The COVID-19 pandemic not only has caused a global health crisis but also has significant environmental consequences. Although many studies are confirming the short-term improvements in air quality in several countries across the world, the long-term negative consequences outweigh all the claimed positive impacts. As a result, this review highlights the positive and the long-term negative environmental effects of the COVID-19 pandemic by evaluating the scientific literature. Remarkable reduction in the leve...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
E. Külah, Y. M. Çetinkaya, A. G. Özer, and H. Alemdar, “COVID-19 forecasting using shifted Gaussian Mixture Model with similarity-based estimation,”
EXPERT SYSTEMS WITH APPLICATIONS
, vol. 214, pp. 110–125, 2022, Accessed: 00, 2022. [Online]. Available: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576929/.