The application of K-means clustering for province clustering in Indonesia of the risk of the COVID-19 pandemic based on COVID-19 data

Abdullah, Dahlan; Susilo, Sidik; Ahmar, Ansari Saleh; Rusli, R.; Hidayat, Rahmat

doi:10.1007/s11135-021-01176-w

Cited by 74 publications

(29 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [24,25], has been analyzed COVID-19 pandemic risk in provinces of Indonesia based on coronavirus disease data. Provinces in Indonesia were grouped based on the data of confirmed, death, and recovered cases of COVID-19 using k-means clustering method.…”

Section: K-means Clustering Analysis On Covid-19 Datamentioning

confidence: 99%

Analyzing the Impact of Vaccination on COVID19 Confirmed Cases and Deaths in Azerbaijan Using Machine Learning Algorithm

Hajirahimova¹,

Aliyeva²

2022

IJEME

View full text Add to dashboard Cite

For almost two years, the world has been battling a global trouble-the COVID-19 pandemic. The disease, which has spread to about 225 countries around the world, has devastated the healthcare system of even the most developed countries. Governments have found the only way out is to impose a strict quarantine regime and state of emergency. Scientists immediately began testing the vaccine. Vaccination would still be the only savior of the planet's inhabitants.Because many of such pandemic infections have exactly been prevented thanks to vaccines in the past. Although the reduction in the number of infections after strict quarantine measures allowed the restrictions to be eased, the next wave was starting soon. This made it necessary the preparation of the vaccine as soon as possible. At the end of last year, the expected news came. Thus, in December 2020, the vaccination process has been launched in a number of countries. Azerbaijan is also one of the first countries to join the vaccination. The vaccination process, which began on January 18, 2021 continues, provided that 4 types of vaccines are available to the population. As a result of vaccination, the epidemiological situation in Azerbaijan is under control, as in many countries. In this article has been attempted to find a correlation between vaccination and COVID-19-confirmed cases and deaths. For this purpose, the kmeans cluster-based machine learning method has been used in the Azerbaijan data collection obtained from the GitHub repository of the Center for Systems Science and Engineering at Johns Hopkins University. This research can benefit governments, stakeholders, and relevant institutions in the health care sector in monitor the vaccination process and more detally assess the epidemiological situation , and make important decisions to control and manage the spread of the disease.

show abstract

Section: K-means Clustering Analysis On Covid-19 Datamentioning

confidence: 99%

Analyzing the Impact of Vaccination on COVID19 Confirmed Cases and Deaths in Azerbaijan Using Machine Learning Algorithm

Hajirahimova¹,

Aliyeva²

2022

IJEME

View full text Add to dashboard Cite

show abstract

“…In this paper, we use k-means clustering, a clustering technique to find the best division of n entity into k groups called the clusters. The algorithm for k-means clustering can be found from many sources, for example, [1].…”

Section: Clusteringmentioning

confidence: 99%

Country Classifications Through a COVID-19 Pandemic Model with Dynamic Parameters and Socioeconomics Indicators

Margaretha

Himawan

Ferdinand

et al. 2022

GCISTEM

View full text Add to dashboard Cite

COVID-19 is a contagious disease that is spreading rapidly to all countries in the world. Data shows that the progression of the disease is different from one country to another. The dynamic of new cases and death are influenced by rules that restrict human interaction, the quality of healthcare services, and the complexity of human behaviors. This paper aims to show how socio-economic factors contribute to the patterns of the pandemic in various countries. The analysis was done for two periods, reflecting two earlier phases of the pandemic: the first six months and the next six months afterward. The results provide helpful lesson-learned for regional and global policymakers to be better prepared with better policies in case of future pandemics. The analysis is done as follows. Firstly, we classify the countries based on the biweekly series of the infection parameter (????) and the recovery one (γ). Both parameters are estimated from the COVID-19 data by using the SIR (Susceptible, Infectious, Recovered) model. Secondly, we classify the countries based on the ???? and γ parameters or the combinations of socio-economic indicators. The chosen indicators are the Economic Complexity Index (ECI), the Compliance Risk Index (CRI), the Anti-Money Laundering (AML) index, the Gross Domestic Product (GDP) per Capita, and School Enrollment. The indices reflect the economic condition, safeness, education, and obedience to the government. For the first six-month phase of the pandemic, we choose 29 countries, and for the second phase, we choose 34 countries. The chosen countries are the ones that rank highest in terms of COVID-19 testing. Our analysis shows how countries are classified based on the pattern of COVID-19 progression and which indices are the most relevant for each cluster.

show abstract

“…Many recent research works have used the elbow method, such as Bholowalia and Kumar [18], Syakur et al [19], Abdullah et al [20], Kong et al [21], Thamrin and Wijayanto [22].…”

Section: Number Of Clusters (K)mentioning

confidence: 99%

“…Recently, the COVID-19 pandemic led for the need of classifying countries, cities, and locations. Accordingly, Abdullah et al [20] proposed an approach for clustering provinces in Indonesia based on COVID-19 data using the K-Means clustering technique for the purpose of clustering the risk of the COVID-19 pandemic in Indonesia. Their research aims to provide input to the government, in regard to making policies related to restrictions on community activities or other policies, to overcome the spread of COVID-19.…”

Section: Related Workmentioning

confidence: 99%

Applying Machine Learning to DEM Raster Images

et al. 2021

View full text Add to dashboard Cite

Geospatial data analysis can be improved by using data-driven algorithms and techniques from the machine learning field. The aim of our research is to discover interrelationships among topographical data to support the decision-making process. In this paper, we extracted topographical geospatial data from digital elevation model (DEM) raster images, and we discovered hidden patterns among this data based on the K-means clustering algorithm, to uncover relationships and find clusters of elevation values for the area of Jordan. We introduce a method for querying and clustering geospatial data and we built an interactive map accordingly. The method discovers hidden patterns and uncovers relationships in given large datasets. We demonstrate the applicability of the method using the Jordan map and we report on geospatial data analysis and retrieval improvements. The results show that the optimal decision is in favor of four clusters (classes). The first class includes the high elevation values, the second class includes the very low elevation values, the third class includes the medium-high elevation values, and the fourth class includes the very high elevation values.

show abstract

The application of K-means clustering for province clustering in Indonesia of the risk of the COVID-19 pandemic based on COVID-19 data

Cited by 74 publications

References 14 publications

Analyzing the Impact of Vaccination on COVID19 Confirmed Cases and Deaths in Azerbaijan Using Machine Learning Algorithm

Analyzing the Impact of Vaccination on COVID19 Confirmed Cases and Deaths in Azerbaijan Using Machine Learning Algorithm

Country Classifications Through a COVID-19 Pandemic Model with Dynamic Parameters and Socioeconomics Indicators

Applying Machine Learning to DEM Raster Images

Contact Info

Product

Resources

About