# Analysis of COVID-19 Pandemic in India

India and China both are most populated countries in the world. China has already controlled this pandemic according to the information which is provided by China. India is still fighting against COVID-19 and trying the best possible way to control this pandemic, so India is successful too in this case. Remember Indian population is 1.33 billion right now. According to the current situation India has 8 patients per million and worldwide it is 245 per million.
You can check patients per million of 10 key countries as given bellow in the right side and China status in the left side. During the analysis on China I’ve noticed that the confirmed cases curve of China has been constant since mid of February as you can see in the graph.

Countries Patients/Million
USA 1751
Spain 3625
Italy 2638
France 2095
Germany 1530
UK 1305
China 57
Iran 873
Turkey 724
Belgium 2639

Analysis is divided in 5 sections:

• Analysis on all data state-wise;
• Last 10 days trend state-wise;
• Comparison of total and last 10 days COVID-19 patients;
• Currents status of India and forecast model and future aspect;
• List of functions which I used during the analysis and explanation.

## 1. Analysis on all data state-wise

In this case I did analysis on data from 30-01-2020 (first case in India) to 13-04-2020. Check the preview of my table below which I’ve prepared for the analysis, the size of the table is 75×39 (75 rows and 39 columns).

### a. Daily registered cases statewise

The figure below shows a surface plot of total daily cases vs. days and states of India. To plot this graph you can use MATLAB inbuilt function.

surf(states,date,data) % states will be in categorical format
%to convert string in category you can use categorical

As you see in the above graph till mid of March variation is almost flat, but you can see after mid March there are drastic changes.

The above graph is a 2D plot of daily cases of all the states with the respect to date.

plot(date,data,'LineWidth',2) % sample code date is x axis and data is y axis , width of line is 2

### b. Total registered confirmed cases state-wise

The graph which you see below is sum of confirmed cases registered everyday.

The peak which you see in the above graph represents peak cases in Maharashtra. You can find case variations according to the colorbar in the left side. Blue color shows lower cases and yellow color shows higher COVID-19 cases. Same you can use to surf a command to plot this graph.

SumAll=cumsum(data); %cumulative sum top to bottom according my table
surf(states,date,SumAll) % surfaceplot

The above graph is a 2D plot of sum of confirmed cases everyday of all the states.

### c. Most COVID-19 infected states based on daily registered cases

As you see in the above graph there are 10 states which are the most infected in India. The above graph is plotted on data from Jan 30 2020 to April 13 2020. I’ve used inbuilt function of MATLAB isoutlier to detect the states.

idx=isoutlier(TotalCases); % here TotalCases is sum of all confirmed cases of every state and output idx is index of outliers.

### d. Most COVID-19 infected states based on total registered confirmed cases state-wise

The above bar graph shows most infected 10 states from the beginning to the present time (means April 13, 2020). When you see the same analysis for the last 10 days in the next section, you will find that some states did improvement from the top 10 infected states.

## 2. Last 10 days trend state-wise

Let’s analyze the last 10 days data and find out a trend.

### a. Daily registered cases state-wise of the last 10 days

As you see in the above graph two peaks belong to Delhi and Maharashtra.

## 3. Comparison of total and the last 10 days COVID-19 patients

In the above figure Maharashtra has total 2344 cases as of 13 April 2020, similarly in the below figure for the last 10 days total confirmed cases are 1844. It shows that for the first 64 days (30-01-20202 to 3-04-2020) total cases were 2344-1844= 500 only, and in the last 10 days total cases have increased upto 1844 .

One thing is remarkable in the analysis of both the figures. In the above figure, Kerala was also in the most infected states, but if you see the last 10 days figure below, Kerala is not in the graph any longer. It means Kerala is performing better since the last 10 days. It is a good sign and shows that the detection of cases are decreasing in Kerala. Again if you check the above graph you will not find J&K (Jammu & Kashmir) but as per the below figure below it has been demonstrating bad performance in last 10 days.

## 4. Currents status of India, forecast model and future aspect

In this section we show graphs of confirmed cases, active cases, death cases and recovered cases. Additionally, a predictive model for forecasting COVID-19 patients in India (Note:- forecasting is based on the present data and the algorithm which I used, forecasting can be changed according to the situation and conditions, like you saw in the case of Kerala above). We all pray to get rid of COVID-19 pandemic in the whole world as soon a possible.
Today the lockdown has been extended till 3rd May 2020 by honorable Indian Prime Minister Modi Ji as per demands of States’ Chef Ministers and people of India. It is a great sign that we are together and united to fight against COVID-19.

### a. Current Status of India till April 13, 2020

As per 13th April
Confirmed cases 10453
Active cases 8902
Deceased cases 358

## b. Forecast for the next 15 days

There are different ways to create forecastive models, like deep learning or machine learning, or you can use system identification in MATLAB if you consider the pandemic as a time dependent system. In my case I’ve used non-linear least squares to create a predictive model. As the graph below demonstrates there may be total 69971 confirmed cases by the date of April 27, 2220.
It’s not good to compare but still I want to say that if you compare India with other countries since the first case till now, then India has fewer cases than other countries. And this happened due to the proper actions taken by the Government. So we wish the curve will be flatten and the confirmed cases will be constant with the respect to time as of China graph.

## List of functions which I used during analysis and explanation

readtable  - read data as a table from file
plot - for 2-D plot
categorical- this function is used to convert text data in category to apply MATLAB operators
bar - for bar plot
text - to show text on graphs
hold on and  hold off -  plot multiple figures in a same figure window
xlabel, ylabel, zlabel - labeling of axis
legend - to identify curves in figure
title - for title of figure
axis tight -  to make axis within range only
surf - for surface plot
yticks- to assign - customize values on yaxis
isoutlier - it is used to find most infected COVID-10 states
fit- it is used to fit a predective model ( in this case NonlinearLeastSquares is used) instead of this you can use cftool app

## Click below to understand through recorded webinar

In this video I used machine learning model to create a forecastive model for COVID-19 patients

Click here for next post on Forecast COVID-19 Patients using Machine Learning

Note:- Keep in mind that the COVID-19 analysis in this article is for educational purposes only not for publications. The goal is to inspire faculties, researchers and students, how deep learning and machine learning can make a big impact for such kind of analysis.

## 13 thoughts on “Analysis of COVID-19 Pandemic in India”

1. Like!! I blog quite often and I genuinely thank you for your information. The article has truly peaked my interest.

2. Hi would you mind stating which blog platform you’re working with?I’m planning to start my own blog in the near future but I’mhaving a difficult time selecting between BlogEngine/Wordpress/B2evolution and Drupal.The reason I ask is because your design and style seems different then most blogs and I’m lookingfor something completely unique. P.S My apologiesfor getting off-topic but I had to ask!

3. Your style is unique compared to other folks I have read stuff from. Thank you for posting when you have the opportunity, Guess I’ll just book mark this web site.

4. Great Post. Thanks.

5. Wonderful post on covid-19

6. Nice post. I used to be checking constantly this weblog
and I am impressed! Extremely helpful information specially the ultimate section 🙂 I take care
of such information a lot. I was looking for this certain information for a long
time. Thank you and best of luck.

7. Hello There. I found your weblog using msn. That is a very smartly
written article. I’ll be sure to bookmark it and come back to read extra of your helpful information. Thanks for the post.

I will definitely return.

8. Very good information. Lucky me I discovered your site by accident (stumbleupon).
I’ve book-marked it for later!

9. I am genuinely grateful to the holder of this web site who has shared this great post at
here.