ISSN 2278-3091

Volume 10, No.4, July - August 2021

International Journal of Advanced Trends in Computer Science and Engineering
Available Online at http://www.warse.org/IJATCSE/static/pdf/file/ijatcse211042021.pdf
https://doi.org/10.30534/ijatcse/2021/211042021

Data Analytics on the COVID-19 Outbreak in South Asia

using Machine Learning Methods
Kajol Chandra Paul1*, Md. Ahsanul Hoque2, Shubhra Mostafa Dhiman3, Joynto Kumar Sen4
1*
Jatiya Kabi Kazi Nazrul Islam University, Bangladesh, Email: [email protected]
2
Jatiya Kabi Kazi Nazrul Islam University, Bangladesh, Email: [email protected]
3
Jatiya Kabi Kazi Nazrul Islam University, Bangladesh, Email: [email protected]
4
University of Dhaka, Bangladesh, Email: [email protected]

ABSTRACT neighboring countries, namely, Afghanistan, Bangladesh,

Bhutan, India, Maldives, Nepal, Pakistan, and Sri Lanka.
The transformation of COVID-19 spread from the first case Often, the first confirmed cases in those countries have been
reported in China’s Wuhan to a worldwide pandemic has found among the expatriates who returned from China, Italy,
been a tremendous topic of study among data analysts and or Iran during the period January to March of 2020 [3], [4].
scientists alike. In South Asia, this pandemic has brought By July 2nd of that year, at least one case of COVID-19 was
about a disaster in the lives and livelihoods of most of its reported in every country. To analyze and compare the
inhabitants. An exploratory analysis of the overall COVID- pandemic situation in SAARC countries, we cannot merely
19 data provided by the Johns Hopkins University Center for look at the sheer number of cases without considering the
Systems Science and Engineering (JHU CSSE) is presented respective country’s population. For example, India has the
in this paper. The number of confirmed, death, recovered, highest cumulative confirmed cases among all; still, it is
and active cases as recent as July 18, 2021, have been 2.2% of its population. Contrarily, 13.8% population of
explored with machine learning data analytics methods to Maldives has been infected with the virus, which ranks 7th
draw crucial conclusions about the pandemic. The analytics in terms of confirmed cases.
and predictive modelingare performed in the context of the
cases in the SAARC (South Asian Association of Regional The spread of the virus, number of deaths caused, number of
Cooperation) countries. The calculated correlation tests conducted, cases of recovery depend on some
coefficient demonstrates that the countries with higher GDP underlying factors such as the population density, testing
Per Capita have conducted more tests/1M population. To facilities, availability of hospital and ICU beds. Each of the
find and compare the severity of the pandemic, the countries countries has a different testing capacity and health care
are grouped based on the K-Means clustering algorithm. The facility leading to a varying number of confirmed and death
confirmed and death cases are modeled with the polynomial cases, which can essentially be related to its GDP Per
regression technique and the future evolution of the Capita, health care index (HCI), the number of vaccination,
pandemic is predicted with good accuracy. Based on the and population age groups. With data analytics, it is possible
predictive model, the total cases estimate around 42.91 to extract valuable information from real data and make a
million confirmed and 0.58 million deaths till August 17, forecast on the future course of the pandemic. Several data-
2021. analytics-based studies have been carried out on the
epidemiological outbreak of the coronavirus in China and
Key words: COVID-19, data analytics, K-Means clustering, some other countries [5]-[9]. Using K-Means clustering,
polynomial regression, predictive model, SAARC. countries or provinces of a country can be grouped to
determine and contrast the severity of infections between the
1. INTRODUCTION
group members [10], [11]. Mathematical models such as the
Not long after the first documented case at Hubei province SIR model have been used to forecast the spread of the
in China [1], the COVID-19 has been declared a global pandemic in countries like China [12], India [13], Sri Lanka
pandemic on 11thMarch 2020, by the World Health [14], and the European countries [15]. Machine learning
Organization (WHO) [2]. As of 18thJuly2021, the total algorithms such as the linear, polynomial, and logistic
global confirmed cases are around 191 million. The first regression techniques are also widely used to model the
reported case of infection among the SAARC countries was pandemic data and create a forecast on future cases [16]-
in Nepal, where the case was reported on 23rdJanuary 2020. [20]. In [21], fuzzy logic system has been used for the
SAARC is a regional organization comprising of 8 prediction of COVID-19 cases in South Africa and Egypt.

2784
Kajol Chandra Paul et al., International Journal of Advanced Trends in Computer Science and Engineering, 10(4), July – August 2021, 2784 – 2791

In this paper, we have presented a comprehensive and 3. DATA-DRIVEN DIAGNOSIS

exploratory data analysis including visualization and
forecast for the COVID-19 outbreak in SAARC countries. The diagnostic data analytics has been performed in terms of
The analytical work examines both diagnostic and predictive the reported cases, economic, and health factors. The
features. It includes visualization concerningbar charts, distribution of the COVID-19 confirmed, deaths, recovered,
scatter plots, bubble plots, and other types of graphs on the and active cases for the SAARC countries along with their
documented cases and other manipulated data. A statistical respective population are listed in Table 1. In this section,
correlation is performed on the number of tests and death we have sought to identify the hidden factors behind the
cases in terms of GDP Per Capita, HCI, the number of difference in the pandemic performance of the countries.
vaccinated people, population, and their age groups. Using
India constitutes 90.5% of the total confirmed cases. On the
K-Means clustering, the countries are segmented into groups
other hand, it shares only 74.2% of the total population of
of varying severity regarding confirmed, death, and active
SAARC. In comparison, Pakistan and Bangladesh share
cases. We have also presented a prediction model based on
11.9% and 8.9% of the SAARC population, while their share
polynomial regression for the number of infections and
of COVID-19 confirmed cases are 2.9% and 3.2%,
deaths till August 17, 2021. This way, we have calculated
respectively. The spread of Coronavirus has not been
the future size of the Coronavirus pandemic in South Asia
uniform or in proportion with the population distribution in
with a satisfactory level of evaluation metrics.
the region. For example, Nepal has approximately 10 million
fewer people than Afghanistan, but the confirmed cases in
2. MATERIAL AND METHODS
Nepal are nearly 5 times the cases in Afghanistan. It does
The Python programming language is used for the not indicate that Afghanistan did exceptionally well to stop
visualization, analysis, and modeling of the data. The the spread rather, the lower number of confirmed cases can
primary dataset employed in this research is collected from be attributed to the significantly lower number of testing
Johns Hopkins University Center for Systems Science and conducted in Afghanistan.
Engineering (JHU CSSE). The data is available on a public
There are several ways to calculate the case fatality rate
GitHub page: https://github.com/CSSEGISandData/COVID-
(CFR) of a pandemic. Generally, CFR is the proportion of
19. JHU CSSE collects the data from primary sources such
deaths among individuals diagnosed with a specific disease.
as the WHO, local and national health institutions, which are
In this approach of calculation, the outcomes of active cases
updated daily [22]. On their Github page, data of the
are not considered. Since the pandemic is ongoing, the final
confirmed, deaths, and recovered cases are time-series data
CFR will change after the active cases are resolved. As a
given in separate CSV files. However, for ease of our work,
solution, the CFR can be calculated by dividing the total
we have brought all the data into the same CSV file
deaths by the total closed cases (deaths + recovered) [16].
datasheet. The dataset has been processed and cleaned using
Hence, the formula to calculate the CFR are
libraries like NumPy and Pandas. Manipulating these data,
we have added more attributes to the dataset such as the
active cases, daily new cases, daily new deaths, and daily = (1)
new recovered cases. The secondary data source used here is
https://www.worldometers.info/coronavirus/#countries, from
where data such as the number of testing and the population = (2)
+
of the countries are collected.

Table 1: The country-wise distribution of COVID-19 cases in SAARC.

Country Confirmed Deaths Recovered Active Population (mil.)

India 31144229 30308456 414108 421665 1394.12
Bangladesh 1103989 932008 17894 154087 166.39
Pakistan 991727 920066 22811 48850 225.34
Nepal 667109 632074 9550 25485 29.68
Sri Lanka 284932 256676 3779 24477 21.51
Afghanistan 137853 82586 5983 49284 39.83
Maldives 75879 73226 216 2437 0.55
Bhutan 2421 2042 2 377 0.78

Where FCFR stands for final case fatality rate. C, D, and R respectively. The recovery rates are calculated the same
represent confirmed, death, and recovered cases way. Figure 1 shows the calculated fatality and recovery
2785
Kajol Chandra Paul et al., International Journal of Advanced Trends in Computer Science and Engineering, 10(4), July – August 2021, 2784 – 2791

rates. Initially, the highest recovery rate is observed in India here is Sri Lanka, which ranks second on the GDP Per
which is 97.3% and the lowest recovery rate of 59.9% is Capita. Despite that, it carried out fewer tests than that of
seen in Afghanistan. On the other hand, Bhutan has the Maldives, Bhutan, and India. On the other hand, the number
lowest fatality rate overall (approximately 0.1%) whereas of tests is found to be moderately negatively associated with
Afghanistan tops the list. It is seen that Afghanistan’s final the test positivity rate as the correlation coefficient between
case fatality rate is a staggering 6.8%, which is significantly them is -0.50. This points to the fact that countries with
higher than the rest of the SAARC countries. It is to be higher positivity rates did not perform a sufficient amount of
noted, the initial fatality and recovery rates do not add up to tests. For example, Afghanistan with the highest positivity
100%, though the final rates do. Consequently, the final rate i.e., 20.4% conducted the lowest number of tests i.e.,
fatality and recovery rates can be interpreted 16986 tests/1M population, contributing to their lower
probabilistically. confirmed cases.

Figure 2: The number of tests conducted per 1M population

(indicated by the bubble size) depends strongly on the GDP Per
Capita.

Figure 1: Initial recovery and case fatality rates are calculated

without considering the active cases,whereas the final rates are
calculated based on the resolved cases.

The underlying factors of the confirmed cases, often

overlooked, are the number of tests conducted and the test
positivity rate. The testing capability of a country depends
on many aspects such as the number of testing labs, number
of kits and technicians available, accessibility to the testing
facility, etc. We have attempted to relate the number of tests
conducted by each country to its GDP Per Capita. On the
other hand, the factors such as age, vaccination, Figure 3: The number of deaths exhibits a positive linear
comorbidities, and HCI could have an impact on death cases. association with population age and vaccination, whereas HCI has
The HCI data [23] gives an estimation of the overall quality an unsubstantial negative linear correlation with death counts.
of the health care system in the country. In addition, the
fatality rate from COVID-19 increases substantially for the Similarly, the correlation coefficient found for the number of
population aged 65 and above [24]. The data for HCI, GDP deaths concerning HCI, the number of vaccinated people,
Per Capita [25], number of people vaccinated with at least a and population age are -0.04, 0.30, and 0.28 respectively.
There is an absence of a perfect linear relationship between
single dose [26], and 65+ population [27] are collected and
these factors. From Figure 3, it is evident that Maldives,
their relationship with the death cases are quantified based
despite having a small 65+ population size and high
on the Pearson correlation coefficient.
vaccination record has witnessed the highest count of nearly
The bubble plot in Figure 2 shows the tests/1M population 392 deaths/1M population. The reason could be its
conducted by each country. The correlation coefficient inadequate health care facilities as it belongs to the bottom
found between the number of tests and GDP Per Capita is three countries on HCI rating. On the contrary, India is
0.90, which suggests thatthe countries with higher GDP Per below Maldives and Nepal in deaths/1M population
Capita have conducted more tests. The notable exception although it has the largest age group of 65+ years. The fact
2786
Kajol Chandra Paul et al., International Journal of Advanced Trends in Computer Science and Engineering, 10(4), July – August 2021, 2784 – 2791

that it has a comparatively higher HCI and better vaccination moderately affected as in the case of India, Nepal, and Sri
record has contributed to a relatively lower death count. Lanka. Finally, cluster 2 is the set of countries comprising
Afghanistan, Bangladesh, Pakistan, and Bhutan. These
4. K-MEANS CLUSTERING METHOD countries are less affected with a low number of confirmed
and active cases.
An important way to compare the severity of the COVID-19
pandemic in different countries could be K-Means clustering
based on various case criteria. The SAARC countries have
been clustered based on the number of confirmed, death, and
active cases per 1M population. The K-Means clustering is
an unsupervised machine learning algorithm that divides the
data into K clusters. There are several methods to find the
optimal number of clusters such as the Elbow method,
Silhouette method, and Gap statistic [11]. In this study, we
have performed the K-Means clustering for a range of
clusters K in iteration and calculated the optimal K value
with the Elbow method. Figure 4 depicts the within-cluster
sum of squares (WCSS) values for different cluster numbers.
WCSS measures the sum of squared distances of each
sample to their nearest cluster center.
(a)

Figure 4: Elbow method plot of WCSS/inertia values to find the

optimal number of clusters. This operation is performed based on (b)
the data of confirmed and death cases.
Figure 5: SAARC nations grouped according to (a) confirmed-
The value of K at the ‘elbow’ point is 3, as the inertia starts deaths and (b) confirmed-active cases using K-Means clustering.
to decrease linearly from that point. Hence, the optimal
value of K is 3 which means the data points can be grouped 5. PREDICTIVE MODELING OF THE PANDEMIC
into 3 clusters. Consequently, the SAARC nations are
segmented into 3 groups according to the number of To model the pandemic data, we have used regression
confirmed and death cases. Furthermore, the Elbow method analysis, which is a supervised machine learning method.
performed based on the data of confirmed and active cases The regression method attempts to model a continuous
determines the optimal value of K as 3. The graphical output variable based on one or several input variables [28].
representation of the K-Means clustering is shown in Figure It finds the relationship between the independent and
5. In Figure 5(a), cluster 0 represents the countries with a dependent variables and builds a predictive model that can
high number of deaths but a low number of confirmed cases. forecast future outcomes. There are different types of
India, Nepal, and Sri Lanka belong to this cluster. Maldives, regression analysis techniques such as linear, polynomial,
which belongs to cluster 1 is the worst affected nation with a logistic growth model, and others. Linear regression is a
very high number of confirmed and death cases. Eventually, simple algorithm and it cannot perform well when the data is
cluster 2 comprising of the rest of SAARC countries has a complex and shows a curvilinear pattern. Therefore,
very low number of confirmed and death cases. Likewise, applying linear regression to model the non-linear dataset
cluster 0 in Figure 5(b) depicts the worst affected country does not yield accurate results.
which is Maldives. The countries belonging to cluster 1 are
2787
Kajol Chandra Paul et al., International Journal of Advanced Trends in Computer Science and Engineering, 10(4), July – August 2021, 2784 – 2791

5.1Polynomial regression SStotal indicates the total variation in Y values i.e., the sum of
the squared differences between the observed output values
In this paper, we have performed the data modeling based on and their mean. The value of R2 ranges from 0 to 1. When
polynomial regression, where a polynomial equation of nth SSline is very small, R2 is close to 1, which means the
degree is used to model the non-linear dataset. The generic regression line perfectly fits the actual data points. For
nth degree polynomial equation is expressed as practical use, the modified version of R2 which is called the
adjusted R2 is a better metric. While R2 does not account for
the additional input variables that are statistically
= + + + +⋯⋯ (3) insignificant, adjusted R2 adjusts the statistical model based
Where a, b, c, d, ….n are called the parameters of on the number of observations and variables. Thus, it is
polynomial regression analysis. In our model, the number of more useful to evaluate the predictive power of the model
days is the independent variable X, which we count from the with adjusted R2. At times, the model tries to fit every data
starting date of our dataset (i.e., 22.01.2020) and the number points exactly, especially for higher degrees of the
polynomial function. The situation is known by the name
of confirmed/death cases is the dependent variable or
overfitting, where the model picks up too much noise and
predictor Y. The degree of a polynomial is determined by the makes fatal errors when predicting unknown data. An
highest exponent of the independent variable. Some of the effective way to solve the problem is to utilize cross-
common polynomial functions are validation (CV), where the training dataset is divided into k-
folds. At each iteration, the model is trained on k-1 folds,
1. Zero polynomial keeping the remaining fold for testing. The performance is
= (4)
function measured as the mean of the values in each iteration, which
2. First-degree is indicated by the cross-validation metric or CV score.
= + (5)
polynomial (Linear)
3. Quadratic polynomial 5.3 Experiment
= + + (6)
function
With the regression process algorithm described in [16], the
4. Cubic polynomial modeling experiment is performed in Python’s sklearn
= + + + (7)
function machine learning library.The entire dataset is divided into
two subsets of training and testing data. As we want to make
the prediction modeling with polynomial regression, the
The first-degree polynomial is a straight line, known as a
input data points i.e., days are converted into polynomial
linear function where b is the slope and a is the Y-intercept features of different degrees. The model is fit on the training
of the line. In a similar fashion, the mathematical expression data and prediction is done on the testing data. The
for higher-order polynomial regression can be found from performance of the model changes slightly with the size of
Eq. (3). The higher order of the polynomial does not the training and testing data. Eventually, the accuracy of the
necessarily signify a better level of fitting i.e., the closeness predictions is evaluated in terms of the MAE, adjusted R2,
between the observed sample values and the predicted and CV score.The CV score is computed for 5 splits and
values. The best possible fitted regression line can be of any their mean is taken. Table 2 illustrates the values of the
order. evaluation metrics based on the testing size and degree of
the polynomial function used to model the total deaths in
5.2 Evaluation metrics SAARC.

Generally, the statistical measures used for evaluation of the Table 2: Evaluation metrics for the polynomial regression model of
regression model are: Sum of Squared Error (SSE), Mean the total deaths in SAARC
Polynomial model of Polynomial model of
Squared Error (MSE), or Root Mean Squared Error (RMSE). degree 6 degree 13
Evaluation
The finest regression line minimizes these values most. metrics 10% test 20% test 10% test 20% test
However, these metrics penalize for the big error, and size size size size
consequently, Mean Absolute Error (MAE) could be used. Adjusted R2 0.9923 0.9914 0.9881 0.9863
Besides that, another metrics called R-squared (R2) or the
coefficient of determination is also used. It is an indication MAE 9035.24 8976.31 11650.72 12294.90
of the goodness of fit for the data points to the regression CV score 0.9900 0.9885 0.9869 0.9864
model. The formula used for the calculation of R2 is [17]
It is seen that the adjusted R2decreases slightly if the testing
= 1− (8) size is increased to 20%. In that case, there is less training
data to train the model.It is also seen that a higher degree of
Where SSline indicates the sum of squared error between the the polynomial function does not necessarily yield better
observed output values and the fitted regression line and values of the evaluation metrics. Figure 6and Figure 7
illustrate the predictive modeling of the cumulative
2788
Kajol Chandra Paul et al., International Journal of Advanced Trends in Computer Science and Engineering, 10(4), July – August 2021, 2784 – 2791

confirmed and death cases in SAARC. In the figures, the

solid green curve represents actual data, while the blue line
represents the model that has been fit on the actual data
points. The blue prediction curve is extended for the next 30
days from July 18, 2021 (depicted by the dashed vertical
line).

Figure 7:Predictive modeling of total deaths in SAARC exhibits a

better coefficient of determination.

Assuming the current pattern sustains, the projection is made

according to the best evaluation metrics achievable. We have
performed similar modeling for the total confirmed and
death cases in each of the countries of SAARC.The
Figure 6: The total confirmed cases in SAARC are modeled with a predicted cases as well as the performance metrics of the
fourth degree polynomial regression function. respective model are summarized in Table 3. In the next
section, the important findings are presented along with a
discussion on the merits and limits of the study.

Table 3: Predicted confirmed and death cases as of August 17, 2021.

Cumulative confirmed cases Cumulative deaths
Country
Adjusted Predicted Adjusted Predicted
MAE CV score MAE CV score
R2 cases R2 cases
India 0.9496 1681648.91 0.9539 38734943 0.9909 8413.28 0.9879 511467
Bangladesh 0.9956 16113.68 0.9945 1384232 0.9962 215.60 0.9964 21947
Pakistan 0.9926 21954.70 0.9925 1135729 0.9922 515.88 0.9925 27177
Nepal 0.9767 23113.02 0.9716 935114 0.9841 225.40 0.9759 12072
Sri Lanka 0.9829 7095.99 0.9846 382869 0.9922 51.38 0.9932 5011
Afghanistan 0.9832 2961.61 0.9857 252467 0.9878 118.35 0.9854 10867
Maldives 0.9848 1665.23 0.9788 89159 0.9742 5.56 0.9731 266
Bhutan 0.9920 42.68 0.9902 2750 0.9131 0.10 0.9039 3
Total cases 42917263 588810
SAARC 0.9713 1270958.53 0.9726 50512821 0.9923 9035.24 0.9900 580622

6. RESULTS AND DISCUSSION populated country in the region, Maldives has witnessed
infections encompassing 13.8% of its population.
Data analytics and modeling is a great tool to comprehend  Usually, the countries that rank higher up in GDP Per
the spread of COVID-19 and its impact. The documented Capita have conducted more tests except for Sri Lanka.
cases are diagnosed to unmask the underlying factors and the Afghanistan has conducted very few tests despite
having a test positivity rate of over 20%, which effected
pattern of the pandemic is modeled with polynomial
its relatively low number of confirmed cases.
regression to predict the future course. The characteristics of
 The final case fatality rate calculated after considering
the Coronavirus spread in South Asia and the related resolved cases is found to be 6.8% in Afghanistan,
findings are encapsulated through the following points. which is the highest in South Asia. There is no
definitive correlation between the number of deaths and
 Infections from COVID-19 spread all over South Asia
in a non-uniform pattern. Despite being the least
2789
Kajol Chandra Paul et al., International Journal of Advanced Trends in Computer Science and Engineering, 10(4), July – August 2021, 2784 – 2791

HCI, though a weak positive correlation is found with models set forth a forecast for the future confirmed and
vaccination and 65+ age population data. death cases.
 As per confirmed, death, and active cases,the SAARC REFERENCES
countries can be grouped into 3 clusters using the K-
Means clustering algorithm. Maldives belongs to the 1. J. Bryner, 1st known case of coronavirus traced back to
severely affected cluster while India, Nepal, and Sri November in China, Available at:
Lanka belong to the cluster which is moderately https://www.Livescience.com/first-case-coronavirus-
affected. The rest of the countries can be categorized as found.html, accessed May 2021.
less affected. 2. Timeline: WHO's COVID-19 response, Available at:
 The polynomial regression model performed on the https://www.who.int/emergencies/diseases/novel-
confirmed cases and deaths exhibit good accuracy coronavirus-2019/interactive-timeline, accessed May
overall. The adjusted R2 value is over 0.9700 for all the 2021.
instances of the model, except for Bhutan’s death cases
and India’s confirmed cases. This can be interpreted as 3. N. Banka, Explained: How SAARC countries are
97% of the total variations in the Y values are described fighting COVID-19, Available at: https://indianexpress.
by the fitted regression line. com/article/explained/explained-how-saarc-countries-
 Bhutan has two cases of fatality from COVID-19, which are-fighting-covid-19-6331509/, accessed June 2021.
occurred on January 8, and July 15 of 2021. This creates 4. Reported Cases and Deaths by Country or Territory,
two abrupt steps in the curve and it becomes relatively Available at:
imprecise to model these abrupt changes with https://www.worldometers.info/coronavirus/, accessed
polynomial regression. We observe many outlier data June 2021.
points on the modeling curve in the case of India and 5. S. K. Dey, M. M. Rahman,U. R.Siddiqi, andA.
Nepal, which have resulted in a relatively lower Howlader.Analyzing the epidemiological outbreak of
adjusted R-squared value. The outlier data points often COVID 19: A visual exploratory data analysis
come from dumping previous-day data into the next day approach,Journal of Medical Virology, vol. 92, no. 6,
due to delays in data collection. pp. 632–638, 2020.
 If we sum up the predicted death cases for the individual
country models, we get a number close to the total 6. H. Nishiura, S-m. Jung, N.M. Linton, R.Kinoshita, Y.
predicted cases inthe SAARC model. The difference is Yang, K. Hayashi, T. Kobayashi, B. Yuan, and A. R.
only 1.4%. However, the difference of confirmed cases Akhmetzhanov. The extent of transmission of novel
Coronavirus in Wuhan, China,Journal of Clinical
between individual country models and the SAARC
Medicine, vol. 9, no. 2, pp. 330, 2020.
model is 17.7%. The relatively lower adjusted R2 scores
have introduced this disagreement in the confirmed 7. N.AL-Rousan, and H.AL-Najjar.Data analysis of
cases. coronavirus COVID-19 epidemic in South Korea
based on recovered and death cases,Journal of
This study has enabled it to gather deep insights into the Medical Virology, vol. 92, pp. 1603–1608, 2020.
pandemic situation in South Asian nations. It can guide the
8. T. Chakraborty, andI. Ghosh.Real-time forecasts and
research and shape the decision-making process in tackling
risk assessment of novel coronavirus (COVID-19)
the virus.According to the predictive model, the total
cases: A data-driven analysis,Chaos, Solitons&
estimated confirmed cases till August 17, 2021, are 42.91
Fractals, vol. 135, 109850, 2020.
million while total fatalities are 0.58 million.
9. S. K. Dey, M. M. Rahman, U. R. Siddiqi, and A.
7. CONCLUSION Howlader. Exploring epidemiological behavior of
novel coronavirus (COVID-19) outbreak in
The spread of the Coronavirus in the South Asianregion may Bangladesh,SN Comprehensive Clinical Medicine, vol.
appear one-dimensional because of the sheer number of 2, pp. 1724–1732, 2020.
confirmed and death cases in India. However, the data
analytics conducted in this study has shown diversified 10. S. K.Saini, V.Dhull, S.Singh, and A. Sharma.Visual
dynamics on the COVID-19 outbreak in SAARC countries. Exploratory Data Analysis of COVID-19
Be it the death rate, recovery rate, test positivity rate, or the Pandemic,5th IEEE International Conference on
number of testings done, each country has performed Recent Advances and Innovations in Engineering
differently which can be correlated to their population, GDP (ICRAIE),Jaipur, 2020, pp. 1-6.
Per Capita, vaccination number, and HCI. Countries such as 11. D.Abdullah, S.Susilo, A. S.Ahmar, R.Rusli, andR.
Maldives are severely affected, according to the K-Means Hidayat. The application of K-means clustering for
clustering. It is shown here that the number of confirmed or province clustering in Indonesia of the risk of the
death cases can be modeled by polynomial regression COVID-19 pandemic based on COVID-19 data.
techniques with good accuracy. The proposed regression

2790
Kajol Chandra Paul et al., International Journal of Advanced Trends in Computer Science and Engineering, 10(4), July – August 2021, 2784 – 2791

Quality & Quantity, 2021. 24. M. O’Driscoll, G. R. D.Santos, L. Wang, D. A. T.

https://doi.org/10.1007/s11135-021-01176-w. Cummings, A. S.Azman, J.Paireau, A.Fontanet,
S.Cauchemez, and H. Salje. Age-specific mortality and
12. C.Anastassopoulou,L. Russo,A.Tsakris,and C. Siettos.
immunity patterns of SARS-CoV-2, Nature, vol. 590,
Data-based analysis, modeling and forecasting of the
pp. 140-145, 2021.
COVID-19 outbreak,PLOS ONE, vol. 15, no. 3,
e0230405, 2020. 25. SAARC - South Asian Association for Regional
Cooperation, Available at: https://countryeconomy.com/
13. M. K.Kakkar, M.Sood, B.Sharma, andJ. Bhatti.
countries/groups/southasian-association-
Mathematical modeling and forecasting the spread
regionalcooperation, accessed June 2021.
of Covid-19 using Python. IJSTR, vol. 9, no. 3, 2020.
26. E.Mathieu, H.Ritchie, E.Ortiz-Ospina, M.Roser,
14. S.Dharmaratne, S.Sudaraka, I.Abeyagunawardena,
J.Hasell,C.Appel, C.Giattino, and L.Rodés-Guirao. A
K.Manchanayake, M.Kothalawala, andW. Gunathunga.
global database of COVID-19 vaccinations,Nature
Estimation of the basic reproduction number (R0)
Human Behaviour. 2021.
for the novel coronavirus disease in Sri Lanka,
https://doi.org/10.1038/s41562-021-01122-8.
Virology Journal, vol. 17, 144, 2020.
27. Population ages 65 and above, total, Available at:
15. K.Linka, M.Peirlinck, and E. Kuhl.The reproduction
https://data.worldbank.org/indicator/SP.POP.65UP.TO?
number of COVID-19 and its correlation with public
end=2019&start=2019&view=bar, accessed June 2021.
health interventions,Computational mechanics, vol.
66, pp. 1035–1050, 2020. 28. A. Jain. Understanding Regression using COVID-19
Dataset - Detailed Analysis, Available at:
16. M. R. H.Mondal, S.Bharati, P.Podder, and P. Podder.
https://towardsdatascience.com/ understanding-
Data analytics for novel coronavirus
regression-using-covid-19-dataset-detailed-analysis-
disease,Informatics in Medicine Unlocked, vol. 20,
be7e319e3a50, accessed June 2021.
100374, 2020.
17. R. S. Yadav. Data analysis of COVID-2019 epidemic
using machine learning methods: a case study of
India,International Journal of Information Technology,
vol. 12, pp. 1321–1330, 2020.
18. H. Singh, and S. Bawa.Predicting COVID-19 statistics
using machine learning regression model: Li-MuLi-
Poly,Multimedia Systems, pp. 1-8,
2021.https://doi.org/10.1007/s00530-021-00798-2.
19. N. Druss. Covid-19 Data Analysis Using Linear
Regression, Available at: https://digitalcommons.
kennesaw.edu/cgi/viewcontent.cgi?article=1091&conte
xt=cday, accessed June 2021.
20. M. Batista.Estimation of the final size of the
coronavirus epidemic by the logistic model, medRxiv,
2020.Available at: https://doi.org/10.1101/2020.02.
16.20023606.
21. I. J. Eyoh, E. N. Udo, I. J. Umoeka, and J. E. Eyoh.
Prediction of COVID-19 time series – case studies of
South Africa and Egypt using Interval Type-2 Fuzzy
Logic system, Internation Journal of Advanced Trends
in Computer Science and Engineering, vol. 10, no. 2,
pp. 627-635, 2021.
22. CSSEGISandData/COVID-19, Available at:
https://github.com/CSSEGISandData/COVID-19,
accessed July 2021.
23. Asia: Health Care Index by Country 2021 Mid-Year,
Avaiable at: https://www.numbeo.com/health-
care/rankings_by_country.jsp?title=2021-
mid&region=142, accessed June 2021.

2791