Clustering of Countries for COVID-19 Cases based on Disease Prevalence, Health Systems and Environmental Indicators

Rizvi, Amna; Umair, Muhammad; Cheema, Muhammad Aamir

doi:10.1101/2021.02.15.21251762

Cited by 5 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We start from a real model with correlated covariance matrices, the values at convergence are of the same nature. It can be interpreted that high positive correlation exists, in the third phase of the epidemic's spread, between Confirmed cases and Recovered cases (0.70), Confirmed cases and Death cases (0.67) and Recovered cases and Death cases (0.85) [10]. To evaluate clusters "Confirmed -Recovered" and "Recovered -Death"; values are in forms four categories (low, lower-middle, uppermiddle, and high), on the order hand "Confirmed -Death" data is in forms three phase (low, medium, and high).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

COVID-19 Dataset Clustering based on K-Means and EM Algorithms

Boutazart¹,

Satori²,

M.³

et al. 2023

IJACSA

View full text Add to dashboard Cite

In this paper, a COVID-19 dataset is analyzed using a combination of K-Means and Expectation-Maximization (EM) algorithms to cluster the data. The purpose of this method is to gain insight into and interpret the various components of the data. The study focuses on tracking the evolution of confirmed, death, and recovered cases from March to October 2020, using a two-dimensional dataset approach. K-Means is used to group the data into three categories: "Confirmed-Recovered", "Confirmed-Death", and "Recovered-Death", and each category is modeled using a bivariate Gaussian density. The optimal value for k, which represents the number of groups, is determined using the Elbow method. The results indicate that the clusters generated by K-Means provide limited information, whereas the EM algorithm reveals the correlation between "Confirmed-Recovered", "Confirmed-Death", and "Recovered-Death". The advantages of using the EM algorithm include stability in computation and improved clustering through the Gaussian Mixture Model (GMM).

show abstract

Section: Resultsmentioning

confidence: 99%

“…Recently an important report using C++ can be used to "track" the daily evolution of new confirmed cases of the COVID-19 epidemic [9]. Rizvi et al [10] have described K-Means clustering of 79 countries has been performed for COVID-19 confirmed cases and COVID-19 death cases based on 18 feature variables.…”

Section: Introductionmentioning

confidence: 99%

COVID-19 Dataset Clustering based on K-Means and EM Algorithms

Boutazart¹,

Satori²,

M.³

et al. 2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…New cases per million adalah jumlah orang baru per hari yang positif menderita Covid-19 per satu juta penduduk. Perkembangan new cases per million Covid-19 adalah data time series [11], sehingga jumlah pada masa mendatang dapat diramalkan menggunakan data yang sudah ada. Banyak penelitian telah dilakukan terhadap perkembangan kasus Covid-19, baik dengan melakukan prediksi [12][13] ataupun forecasting [14]- [17].…”

Section: Pendahuluanunclassified

Pemodelan Perkembangan New Cases Covid-19 di Indonesia Menggunakan Multi-Layer Perceptron dan Support Vector Machine

Rachmatullah¹

2022

JEPIN

View full text Add to dashboard Cite

Meningkatnya ketersediaan data historis dalam jumlah besar dan kebutuhan untuk membuat perkiraan yang akurat tentang perilaku masa depan menjadi perhatian khusus dalam mencari teknik yang dapat menarik kesimpulan dari mengamati hubungan antara data tertentu, antara data masa lalu dan data masa depan. Domain peramalan mengalami peningkatan sejak tahun 1960-an, dengan metode statistik linier, misalnya menggunakan model ARIMA. Baru-baru ini, model pembelajaran mesin telah menarik perhatian dan dapat digunakan sebagai teknik lain selain model statistik klasik untuk kasus peramalan. Penelitian ini memprediksi perubahan kasus baru positif Covid-19 per satu juta penduduk (new cases per million Covid-19) di Indonesia menggunakan pembelajaran mesin. Pemodelan perubahan new cases per million diperlukan karena penyakit ini merupakan penyakit baru, sehingga sampai saat ini belum ada pemodelan deret waktu yang cukup akurat untuk menggambarkan kasus tersebut. Teknik machine learning yang akan digunakan adalah Multi-Layer Perceptron (MLP) dan Support Vector Machine (SVM) dan dibandingkan kinerja dari kedua teknik tersebut. Dari hasil perhitungan kinerja, prediksi new cases per million Covid-19 yang dilakukan dengan menggunakan SVM(RMSE = 9,053) memiliki kinerja yang lebih baik dibandingkan dengan menggunakan MLP (RMSE = 10,284). Nilai RMSE yang lebih kecil menunjukkan kinerja yang lebih baik.

show abstract

“…Rizvi, Umair, and Cheema analyzed 79 countries for their vulnerability to the impact of the COVID-19 pandemic. Based on socioeconomic, disease prevalence, and health system indicators considering COVID-19 confirmed cases and COVID-19 death cases as evaluation parameters, they divided countries into 4 clusters (Rizvi et al, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

Classification of the EU Countries According to the Vulnerability of their Economies to the Impact of COVID-19 Pandemic

Brzyska¹,

Szamrej-Baran²

2021

ERSJ

View full text Add to dashboard Cite

Purpose: The paper's objective is to identify the similarities of EU countries in terms of the entire sets of indicators. Hence, the multi-dimensional cluster analysis is applied to evaluate the economic vulnerability to the impact of the COVID-19 pandemic. Design/Methodology/Approach: A hierarchical and non-hierarchical cluster analysis method was used in the paper. At the first step, EU countries were clustered with Ward's method, and the following k-means method was applied for grouping countries. Findings: In the study, four clusters were identified. Southern European countries grouped in the 1st Cluster performed the highest level of vulnerability to the negative impact of the COVID-19 pandemic. Germany, the Netherlands, Ireland, and the Scandinavian countries appeared to be the least vulnerable EU economies to the impact of the COVID-19 pandemic and were grouped in the 4th Cluster. The countries of Central and Eastern Europe, most of which joined the EU in the 21st century, were characterized by moderate vulnerability and belonged to the 2nd and 3rd Cluster. Practical Implications: The results obtained can be used by policymakers to make better decisions to mitigate the negative impact of the pandemic on economies. Originality/Value: Most clustering of countries according to the impact of a COVID-19 pandemic examines how the virus spreads from a medical point of view. There is little literature on the economic impact of a coronavirus pandemic. This study will fulfill this gap.

show abstract

Clustering of Countries for COVID-19 Cases based on Disease Prevalence, Health Systems and Environmental Indicators

Cited by 5 publications

References 36 publications

COVID-19 Dataset Clustering based on K-Means and EM Algorithms

COVID-19 Dataset Clustering based on K-Means and EM Algorithms

Pemodelan Perkembangan New Cases Covid-19 di Indonesia Menggunakan Multi-Layer Perceptron dan Support Vector Machine

Classification of the EU Countries According to the Vulnerability of their Economies to the Impact of COVID-19 Pandemic

Contact Info

Product

Resources

About