CONTENTS
❑ Abstract
❑ Existing System
❑ Drawbacks
❑ Proposed System
❑ Advantages
❑ Modules
❑ System Requirements
❑ Architecture
❑ UML Diagrams
❑ IMPLEMENTATION CODE
❑ Results
❑ Conclusion
❑ References
ABSTRACT
Machine learning (ML) based forecasting mechanisms have proved their significance to
anticipate in perioperative outcomes to improve the decision making on the future course of actions.
The ML models have long been used in many application domains which needed the identification
and prioritization of adverse factors for a threat. Several prediction methods are being popularly used
to handle forecasting problems. This study demonstrates the capability of ML models to forecast the
number of upcoming patients affected by COVID-19 which is presently considered as a potential
threat to mankind.
EXISTING SYSTEM
Machine Learning models that are used in existing system are decision
tree and random forest algorithms but however among them, model made of the
decision tree has the highest accuracy of 79.85%.
DRAWBACKS
∙ Less accuracy. i.e, it can predict only 79% of cases
∙ Time consumption to train large number of datasets is high.
PROPOSED SYSTEMS
This study attempts to develop a system for the future forecasting of the number of
cases affected by COVID-19 using machine learning methods. The dataset used for the
study contains information about the daily reports of the number of newly infected cases,
the number of recoveries, and the number of deaths due to COVID-19 worldwide. In this
project we are using supervised models like svm and linear regression. Which predicts the
cases upto 95%.
ADVANTAGES
1. Our proposed system will accurately detect the affected area from the original area.
2. This system will efficiently mark the affected area from original image.
MODULES
► Data collection
► Data pre-processing
► Data cleaning
► Splitting of data Test data
Train data
DATA COLLECTION:
► Data loading is the process of copying and loading data or data sets from a source file,
folder or application to a database or similar application
► In this project we are collecting the data in manual process
DATA PRE-PROCESSING:
Missing values were imputed to guarantee that all the algorithms would be able to
handle them.
For numerical data types, the missing entries are replaced by the median value of the
complete entries.
For categorical data, the missing entries were replaced by the mode value of the
complete entries.
DATA CLEANING:
► In this module the data is cleaned. After cleaning of the data, the data is grouped as per
requirement. This grouping of data is known as data clustering.
SPLITTING OF DATA:
After cleaning the data, data is normalized in training and testing the model.
Training set: -A data scientist uses a training set to train a model and define its optimal
parameters — parameters it has to learn from data.
Test set: - A test set is needed for an evaluation of the trained model and its capability
for generalization.
SYSTEM ARCHITECTURE
Training
Data Set Data Pre - Processing
Data Sets
Algorithm
Output Result Prediction
Prediction
ARCHITECHTURE DIAGRAM
Patient Details
Data Pre-processing Testing Data Set
Classification
Training Data
of DL model Model
Set
UML DIAGRAMS
DATA FLOW DIAGRAM
ACTIVITY DIAGRAM
User system
Login Train
Test
cases
cases
input
prediction
accuracy
Yes no
Covid-19
performance
Implementation code
%matplotlib inline
import os
import [Link] as plt import pandas as pd
import numpy as np import seaborn as sns import
random
from sklearn.model_selection import train_test_split
#data_1 = pd.read_csv("/content/drive/MyDrive/Covid- 19_ML/time_series_covid19_confirmed_US.csv")
/* confirmed cases*/
data_confirmed = pd.read_csv(r"C:\Users\Lenovo\Desktop\project\BACK END
from sklearn.linear_model import LinearRegression
/* recovered cases*/
y_pred_recovered =[Link](x_test_recovered )
#print(mean_squared_error(y_pred_recovered ,y_test_recovered ))
/*death rates*/
y_pred_deaths = y_pred_deaths[:10] pred = []
new1 = ['Death Data', 'Linear Regression',0.002] new2 = ['Death Data', 'SVM',0.033]
[Link][4] = new1
[Link][5] = new2 results
Results:
CONCLUSION
► This study discussed the spread of COVID-19 in different states of India and
proposed a model for predicting the number of confirmed, recovered, and
death cases.
► Linear regression and SVM were used to predict the possible number of cases
in the future. The predicted confirmed cases of India for the next 30 days.
► The predicted values and actual values are together in good agreement.
REFERRENCES
► S. Makridakis, E. Spiliotis, and V. Assimakopoulos, “Statistical and machine learning
forecasting methods: Concerns and ways forward,” PloS one, vol. 13, no. 3, 2018.
► G. Bontempi, S. B. Taieb, and Y.-A. Le Borgne, “Machine learning strategies for time
series forecasting,” in European business intelligence summer school. Springer, 2012,
pp. 62–77.
► P. Lapuerta, S. P. Azen, and L. LaBree, “Use of neural networks in predicting the risk of
coronary artery disease,” Computers and Biomedical Research, vol. 28, no. 1, pp.
38–52, 1995.
► K. M. Anderson, P. M. Odell, P. W. Wilson, and W. B. Kannel, “Cardiovascular disease
risk profiles,” American heart journal, vol. 121, no. 1, pp. 293–298, 1991.
THANK YOU