ONLINE NOTICE BOARD

MINI PROJECT REPORT

SUBMITTED BY

P.PranithaPriyanka
ROLL NO:20502012
B.VOC SOFTWARE DEVELOPMENT – IV Semester

Under the Guidance of

Dr. SHAHEDA AKTHAR
Department of Computer Science
GOVERNMENT COLLEGE FOR WOMEN (A), GUNTUR-522001
OCTOBER 2022
Name…:……………………………… Group:

Regd.No……………………… Class No. …………………………………

GUNTUR

DEPARTMENT OF COMPUTER
SCIENCE
This is certified to be the bonafide work of the student in the B.Voc
IV Sem (Software Development) Project Work entitled

_ during the academic year 2021-2022.

Project Guide Head of the Department

Date: ExternalExaminer
Declaration

I affirm that the mini project work titled “ONLINE NOTICE

BOARD” being submitted as project report in partial fulfillment of B.Voc
(Software Development)IV Semester is the original work carried out by me.
It has not formed the part of any other project work submitted of any degree
or diploma, either in this or any other University.

P. PRANITHAPRIYANKA

20502012
 ACKNOWLEDGEMENT

I express my gratitude to Dr. SHAHEDHA AKTHAR, Lecturer in Computer

Science, Government College for Women(A), Guntur for having provided me the
facilities to do the project successfully.
My heartful thanks to Dr.V.R JYOSHNA KUMARI, Principal,
Government college for women (A) , Guntur, for his patronage and giving us an
opportunity to undertake this Project.
I owe deep sense of gratitude to Dr. A.V. KAVITHA, Head
of Department of Computer Science for appreciating my goal. I express my
sincere thanks to her for her constant encouragement.
I would also like to thank K. DEEPTHI, Lecturer in Computer
Science department for her valuable guidance and support to meet the successful
completion of my project.
 I express my sincere thanks to all the faculty of Computer Science
Department for their encouragement and valuable guidance throughout this
project.
Last but not the least; I extend my sincere thanks to my family
members and my friends for their constant support throughout this project.

ONLINE NOTICE BOARD INDEX

Sr Name Page
1 Abstract 6
2 Objectives of the project and modules 7
3 Project Category and Tools 9
6 Software Requirement Specification (SRS) 10
5 Project Scheduling: PERT and GANTT Chart 16
6 ER AND DFD 16-20
7 Database Design 20
8 Security and Code Improvement 25
9 Future Scope 26
10 Source Code 27-63
11 Reference 66
 Abstract

In today’s modern colleges, there should be a platform where people can communicate and can
exchange information. Sometimes, there is a big gap between different departments of a college and
students don’t get information on time. There should be a centralized platform where students can check
information and notices. Online Notice Board is a service which provides this platform.
Teachers will be able to register on this website and they will get special privileges. They can
post notice and information and our website will sort this information by departments.
Students can view the information posted by teachers. There will be an admin panel to control
the teachers account. It will have the options to delete users, delete their posts, add new
users.etc.
It uses CORE PHP to manage the database. PHP is used to create new users, performing
CRUD operations, creating admin panel to manipulate registered users.etc

A lot of effort has been taken to keep the website simple and beautiful to maximize loading
speed and minimizing resp/
 Institute Vision and Mission
INSTITUTION VISION
To produce eminent and ethical Engineers and Managers for society by
imparting quality professional education with emphasis on human values and
holistic excellence.

INSTITUTION MISSION
o To incorporate benchmarked teaching and learning pedagogies in curriculum.

o To ensure all round development of students through judicious blend

of curricular, co- curricular and extra-curricular activities.
o To support cross-cultural exchange of knowledge between industry
and academy.

o To provide higher/continued education and researched opportunities to

the employees of the institution.

Department Vision and Mission

Department VISION

To be a renowned department for education in Artificial Intelligence and empowering

students into professional engineers with human values and holistic excellence.

Department MISSION

• Impart rigorous training to acquire knowledge through the state-of-the-art concepts

and technologies in Artificial Intelligence.
• Train students to be technically competent through innovation and leadership.
• Inculcate values of professional ethics, social concerns, life-long learning and
environment protection.
• Establish centers of excellence in leading areas of computing and artificial intelligence

KKR & KSR INSTITUTE OF TECHNOLOGY AND SCIENCES

(Autonomous)
Approved by A.I.C.T.E New Delhi || Permanently Affiliated to JNTUK, Kakinada) || Accredited with ‘A’
Grade by NAAC || NBA Accreditation status for 5 B.Tech Programmes (Civil, CSE, ECE, EEE &
Mech)
Vinjanampadu, Vatticherukuru Mandal, Guntur, Andhra Pradesh522017
DEPARTMENT OF CSE - ARTIFICIAL INTELLIGENCE
 Index
Description Page Number
UNIT –I INTRODUCTION
1.1 Introduction of the Project
1.2 Existing System
1.3 Problems of the Existing Systems
1.6 Proposed System
1.5 Benefits of the Proposed System

UNIT II - ANALYSIS
2.1 Requirements Analysis
2.1.1 Functional Requirements Analysis
2.1.2 User Requirements
2.1.3 Non Functional
Requirements
2.1.6 System
Requirements
2.2 Modules Description
2.3 Feasibility Study
2.3.1 Technical Feasibility
2.3.2 Operational Feasibility
2.3.3 Behavioral Feasibility
2.6 Process Model used
2.5 Hardware and Software Requirements
2.6 SRS Specification

UNIT-3 DESIGN PHASE

3.1 Design concepts
3.2 Design Constraints
3.3 Conceptual Design
3.6 Logical Design (Logical Tools/Logical
Diagrams)
3.5 Architectural Design
3.6 Algorithms Design
3.7 Database Design
3.8 Module design Specifications

UNIT IV- CODING & OUTPUT SCREENS

6.1 Sample Coding

6.2 Output Screens
6.3 Screen Reports

UNIT- 5 TESTING

5.1 Introduction to Testing

5.2 Types of Testing
5.3 Test cases and Test Reports

UNIT- 6 IMPLEMENTAION
6.1 Implementation Process
6.2 Implementation Steps
6.3 Implementation procedure
6.6 User Manual
UNIT- 7 CONCLUSION AND FUTURE
ENHANCEMENTS
7.1 Conclusion
7.2 Future Enhancements
UNIT- 8BIBLIOGRAPHY
8.1 Books Referred

8.2 Websites visited

INTRODUCTION:
Heart disease is a major health problem affecting people worldwide.
Machine learning algorithms have been used in healthcare to predict the
occurrence of heart disease, providing early detection and timely
intervention. In this project, the goal is to develop a machine learning
model that can accurately predict the likelihood of an individual having
heart disease.

The project will involve collecting and analyzing data on various factors
that are known to influence heart disease, such as age, gender, blood
pressure, cholesterol levels, smoking history, and family history. The
collected data will be preprocessed and cleaned to ensure that it is suitable
for use in the machine learning model.

Once the data is ready, the project will involve using various machine
learning algorithms such as logistic regression, decision trees, and random
forests to train and test the model. The performance of the model will be
evaluated using various metrics such as accuracy, precision, recall, and F1
score.

The ultimate goal of this project is to develop a robust machine learning

model that can accurately predict the likelihood of heart disease in
individuals. Such a model can help healthcare professionals in making
informed decisions about patient care and management.

Existing system of a graphical password

aunthentication:

There are already several existing systems for heart disease prediction using
machine learning. Here are some examples:

1. The Cleveland Clinic Foundation Heart Disease Dataset: This dataset is a popular
benchmark dataset used for heart disease prediction. It contains data on 303 patients
and 16 features including age, sex, blood pressure, serum cholesterol levels, and
electrocardiographic readings. Machine learning models can be trained on this
dataset to predict the likelihood of heart disease.

2. DeepHeart: This is a deep learning-based system for predicting cardiovascular

risk using wearable devices. It uses a combination of convolutional neural
networks and recurrent neural networks to analyze data from wearable devices such
as smartwatches and fitness trackers. The system can predict the onset of
cardiovascular disease up to one year in advance with an accuracy of up to 90%.
3. Cardiologs: This is a cloud-based platform that uses deep learning to analyze
electrocardiograms (ECGs) for the early detection of heart disease. The system
can analyze ECGs in real-time and detect abnormalities that may be indicative of
heart disease. It has been shown to be highly accurate in detecting atrial
fibrillation, a common heart condition.

4. Heart disease prediction using machine learning: This is a research paper that
proposes a machine learning-based system for heart disease prediction. The system
uses a combination of logistic regression and artificial neural networks to analyze
data from the Framingham Heart Study dataset. The system achieved an accuracy
of 85% in predicting the likelihood of heart disease.

These are just a few examples of existing systems for heart disease prediction using
machine learning. There are many other systems and research studies in this field,
and the technology is constantly evolving to improve the accuracy and effectiveness
of heart disease prediction.

Benefits of the Proposed System :

There are several benefits of heart disease prediction using machine learning. Here
are a few of them:

Early detection: One of the primary benefits of heart disease prediction is early
detection. Machine learning algorithms can analyze large amounts of data to
identify patterns and predict the likelihood of heart disease in individuals. Early
detection allows healthcare professionals to take preventive measures and provide
timely treatment to prevent the progression of the disease.

Personalized treatment: Heart disease prediction using machine learning can help
healthcare professionals provide personalized treatment to individuals. By
analyzing data on various risk factors such as age, sex, blood pressure, cholesterol
levels, and family history, machine learning algorithms can identify the most
effective treatment options for each individual.

3. Improved patient outcomes: Early detection and personalized treatment can

lead to improved patient outcomes. By detecting heart disease early and providing
timely treatment, healthcare professionals can reduce the risk of complications and
improve the quality of life for patients.

4. Cost savings: Heart disease is a major healthcare cost, and early detection and
prevention can help reduce healthcare costs. By predicting the likelihood of heart
disease in individuals and providing preventive measures, healthcare professionals
can reduce the need for costly treatments and hospitalizations.

5. Public health benefits: Heart disease prediction using machine learning can
also have broader public health benefits. By identifying patterns and trends in
heart disease risk factors, healthcare professionals can develop effective public
health strategies to prevent heart disease at the population level.

Overall, heart disease prediction using machine learning can lead to improved
patient outcomes, cost savings, and public health benefits. It is a promising area of
research that has the potential to make a significant impact on healthcare.

Requirement analysis :
Requirement analysis is a critical step in the development of any machine learning
project, including heart disease prediction. Here are some key requirements to
consider when conducting requirement analysis for a heart disease prediction
system:

1. Data collection: The first requirement is to collect relevant data. The data should
include various risk factors for heart disease, such as age, sex, blood pressure,
cholesterol levels, smoking history, and family history. The data should be large
enough and diverse enough to train and test the machine learning model
effectively.

2. Data preprocessing: The collected data must be preprocessed to ensure that it

is suitable for use in the machine learning model. This includes tasks such as data
cleaning, data transformation, and feature engineering.

3. Machine learning algorithms: The heart disease prediction system should

use appropriate machine learning algorithms to analyze the data and predict the
likelihood of heart disease. The choice of algorithms will depend on the type of data
and the accuracy requirements of the system.

4. Performance metrics: The system should be evaluated using appropriate

performance metrics such as accuracy, precision, recall, and F1 score. The
performance metrics should be carefully selected to ensure that the system meets
the accuracy requirements.

5. User interface: The heart disease prediction system should have a user interface
that is easy to use and provides clear and concise information about the predicted
likelihood of heart disease. The user interface should also be secure and protect the
privacy of patient data.

6. Integration with healthcare systems: The heart disease prediction system

should be integrated with existing healthcare systems to ensure that healthcare
professionals can access and use the system effectively.

7. Compliance with regulations: The heart disease prediction system should

comply with relevant regulations and standards, such as HIPAA and GDPR, to
ensure that patient data is handled securely and confidentially.

By carefully considering these requirements, it is possible to develop a heart disease

prediction system that is accurate, effective, and secure.

Types of GPA:
There are several types of heart disease prediction that can be performed using
machine learning. Here are some examples:

1. Binary classification: Binary classification is a type of heart disease prediction

where the model predicts whether a patient is likely to have heart disease or not.
The model is trained on data that includes patients with and without heart disease,
and it learns to identify patterns that distinguish between the two groups.
2. Multi-class classification: Multi-class classification is a type of heart disease
prediction where the model predicts the type of heart disease a patient is likely to
have. The model is trained on data that includes patients with different types of
heart disease, and it learns to identify patterns that distinguish between the
different types.
3. Risk assessment: Risk assessment is a type of heart disease prediction where the
model predicts the risk of developing heart disease in the future. The model is
trained on data that includes patients with and without heart disease, as well as
patients who are at risk of developing heart disease in the future. The model learns
to identify patterns that are indicative of increased risk of heart disease.

4. Time-series prediction: Time-series prediction is a type of heart disease

prediction that uses historical data to predict future outcomes. For example, a
model could be trained to predict the likelihood of a heart attack based on a
patient's medical history, lifestyle factors, and other risk factors.

5. Survival analysis: Survival analysis is a type of heart disease prediction that is

used to predict the likelihood of an event occurring within a certain timeframe.
For
example, a model could be trained to predict the likelihood of death due to heart
disease within the next five years based on a patient's medical history and other risk
factors.

These are just a few examples of the types of heart disease prediction that can be
performed using machine learning. The specific type of prediction that is used will
depend on the goals of the project and the data that is available.

3. LITERATURE REVIEW ON HEART DISEASE PREDICTION:

Heart disease prediction using machine learning has been the focus of several
research studies in recent years. Here is a brief literature review of some of the key
studies in this area:

1. "Prediction of Heart Disease Using Machine Learning Algorithms: A

Systematic Review" (Sharma et al., 2020)

This systematic review evaluated the performance of various machine learning

algorithms in predicting heart disease. The authors analyzed 30 studies and found
that several algorithms, including artificial neural networks and support vector
machines, had high accuracy in predicting heart disease.

2. "Comparison of Machine Learning Algorithms for Prediction of Early

Stage Cardiovascular Disease" (Mellor et al., 2020)

This study compared the performance of several machine learning algorithms in

predicting early-stage cardiovascular disease. The authors found that a deep
learning algorithm had the highest accuracy, followed by a random forest
algorithm.

3. "Predicting Cardiovascular Disease Risk Factors Using Machine

Learning Techniques: A Systematic Review" (Abbasi et al., 2019)

This systematic review evaluated the use of machine learning techniques in

predicting cardiovascular disease risk factors. The authors analyzed 29 studies and
found that machine learning algorithms had high accuracy in predicting risk factors
such as hypertension and diabetes.

4. "Predicting Cardiovascular Disease Events Using Machine Learning

Techniques: A Systematic Review and Meta-Analysis" (Wang et al., 2020)
This systematic review and meta-analysis evaluated the performance of machine
learning algorithms in predicting cardiovascular disease events. The authors
analyzed 62 studies and found that machine learning algorithms had higher
accuracy than traditional risk prediction models.

Overall, these studies demonstrate that machine learning algorithms have high
accuracy in predicting heart disease and cardiovascular disease risk factors.
However, further research is needed to develop and validate these algorithms in
larger and more diverse populations.

TECHNIQUE :

The introduced technique is based on graphical images. In previous techniques user

selects a set of images but these images were predefined but in the introduced
technique user will upload images from personal directory of computer. Sequence
of images is key factor of introduced authentication technique. In this technique
user will upload images at the time of registration for the sake of password and for
login, user will have to select the images which were uploaded at the time of
registration. Figure 1 shows that how this system will run.

3.2:Features of Introduced Technique

Features, also known as predictors or variables, are the inputs used in a

heart disease prediction model. The features used in heart disease
prediction models can vary depending on the type of model and the
specific research question. However, here are some common features that
have been used in heart disease prediction models:

1. Age

2. Gender

3. Family history of heart disease

4. Blood pressure

5. Cholesterol levels
 6. Diabetes status

7. Smoking status

8. Body mass index (BMI)

9. Physical activity level

10. Electrocardiogram (ECG) results

11. Echocardiogram results

12. Cardiac stress test results

13. History of angina or chest pain

14. History of heart attack or stroke

15. Medication use (e.g. blood thinners, statins)

These features can be collected from medical records, patient interviews,

physical exams, and laboratory tests. Machine learning algorithms are then
used to identify patterns in the data that are associated with the outcome of
interest (e.g. presence of heart disease or risk of developing heart disease).
By using these features, heart disease prediction models can help healthcare
providers identify patients who are at risk of heart disease and provide
targeted interventions to prevent or manage the disease.
3.1.1 Registration Phase:

The registration phase of a heart disease prediction project involves collecting and
organizing the data that will be used to develop the prediction model. Here are some
steps involved in the registration phase:

1. Define the research question: The first step is to define the research question or
hypothesis. For example, the research question may be to predict the likelihood of
heart disease in a specific population or to identify risk factors for heart disease.
2. Identify the study population: The next step is to identify the population that
will be included in the study. This may include patients from a specific clinic,
hospital, or geographic region.

3. Obtain ethical approval: Depending on the jurisdiction, the study may

require ethical approval from an institutional review board (IRB) or ethics
committee.

4. Collect data: Data can be collected from various sources such as medical
records, laboratory results, imaging studies, and patient interviews. It is important
to ensure that data is collected in a standardized and consistent manner.

5. Preprocess data: Before the data can be used to develop a prediction model, it
may need to be cleaned, organized, and transformed. This may include
removing missing values, scaling variables, and encoding categorical variables.

6. Split data: The dataset is then split into a training set and a testing set. The
training set is used to develop the prediction model, while the testing set is used
to evaluate the performance of the model.

7. Store data: The data should be stored in a secure and organized manner to
ensure data privacy and facilitate analysis.

By completing the registration phase, researchers can ensure that the data used in
the heart disease prediction project is reliable and of high quality. This phase
lays the groundwork for developing an accurate and effective heart disease
prediction model.

3.1.2 Login Phase :

A login page for a heart disease prediction project would typically be used to
authenticate users and grant access to the system. Here are some key components
that may be included in a login page for a heart disease prediction system:

1. Username and password fields: Users would enter their unique username and
password to access the system. These credentials would be verified against a
database of registered users to ensure that only authorized users are able to
access the system.
2. Forgot password link: A "forgot password" link would allow users who have
forgotten their password to reset it using their registered email address or
phone number.

3. Remember me checkbox: A "remember me" checkbox may be included to

allow users to save their login credentials for future use.

4. Login button: The login button would submit the user's credentials to the
system for authentication.

5. Sign-up button: A "sign-up" button may be included to allow new users

to register for the system.

6. Error messages: Error messages would be displayed if the user enters an

incorrect username or password, or if there are issues with the authentication
process.

7. Security features: To ensure the security of the system, features such as

CAPTCHA, two-factor authentication, and SSL encryption may be
implemented.

Overall, the login page of a heart disease prediction system would play a crucial
role in ensuring that only authorized users are able to access sensitive patient data
and that the system remains secure.

in incorrect sequence, then he will be unable to login or access the system. To resist
the shoulder surfing, images will be shown in random order. During each time of
login order of images will be different from the previous login. Figure 3 show the
login phase of our system, after successful login system will redirect to dashboard
of the user.

in incorrect sequence, then he will be unable to login or access the system. To resist
the shoulder surfing, images will be shown in random order. During each time of
login order of images will be different from the previous login.

Sample coding:
rile Edi‹ seie c‹ion view sa Run ierminal H eip Hean a se ass Predict on. py ns vis•ai s udi° c°d• ] g Q] 0,° a x
cted M d - ded for sa fe code browsing. Trust thfs window to enable aii features. M daAge Learn More X
g Heart oisease Prediction.ipynb x @ @

c: Users › Taiathoti vamri › ppDa a › Locai › Temp › Tempt Heart oisease Prediction master.zip › Heart oisease Predictio n master › 9 H ean aide are Predictio n ipynb › •• Heart Disease Predict ion › •• import libraries › "• import numpy as np
—I- d —I- M kdorn ”= outi ne , , sei ct r: m i

Heart Disease Prediction

In this machine learning oroject, I have collected the dataset from Kaggle (h ltDs ,‘/\‘ \‘/\\ kaggle cont,‘t oniif/heai t disease uri) and I will be using Machine Learning to make oredictions on
whether a person is suffering from Heart Disease or not.

Import libraries
Let's first import all the necessary lioraries. I'll use numpy and pa nd a s to start with. For visualization, I will use pyplot subpackage of matplot I ib, use rcParams to add styling to the plots
and ra in bow for colors. For implementing Machine Learning models and processing of data. I will use the s klearn library.

For processing the data, I'll import a few libraries. la split the available dataset for testing and training, I'll use the t nai n_t est_s plit method. Io scale the features, I am using Standards c aie r.

CI Search

For processing the data, I'll import a few libraries. Io split the available dataset for testing and training, I'll use the erai n_test_s plit method. Io scale the features, I am using standa rdscaie r.

Next, I'll import all the Machine Learning algorithms I will be using.

1. K Neighoors Classifier
2. Suoport Vector Classifier
3. Decision Tree Classifier
4. Random Forest Classifier

Now that we have all the libraries we wilI need, I can import the dataset and take a look at it. +he dataset is stored in the file data s et . csv. I'll use the pandas nead_c s v method to read the
dataset.

ENG
CI Search
 ) ri e Ed ‹ se e c‹ on view sa Run ierminal H eip Hcan aise ass P r•dici on ipynb vis•ai siudi° c°a• ] g Q] 0,° a x

’ ' Restricted Mode s intended for sa fe code browsing. Trust thfs window to enable aii M daAge Learn Mo re X
features.
@ @
B Heart Disease Predietla n pynb X

c Use s › Ta a hot vamri › ppDa a › ocai › Temp › Tempt Heart oisease Prediction master.zip › Heart oisease Predictio n master › 9 H ean aide are Predictio n ipynb › •• Heart Di ea e Predict ion › •• import libraries › "• import numpy as np
@ —I- code —I- Ma kdor n — out ne % set ect r:em e

Import dataset
Now that we have all the libraries we will need, I can import the dataset and take a look at it. The dataset is stored in the file data set . csv. I'll use the pandas nead_c s v method to read
the p dataset.

The dataset is now loaded into the variable dataset. I'll just take a glimpse of the data using the des ri be( ) and in-Fa( ) methods before I actually start processing and visualizing it.

Data columns (total 16 coI unins):

chO1

oTdpeak 3e3 non —null ftoat6a

ENG
CI Search

Taking a look at the correlation matrix above, it's easy to see that a few features have negative correlation with the target value while some have positive. Next, I'll take a look at the
histograms for each variable.

[‹matplotli b. axes. subplots .Axessubplot object at axlal789b8sa›,

ENG
CI Search
 se rs To “r t 'la psi › A* r la › ’ cv › e r › e r 1 H° '“ a s°ase Pr°u c cn ma e r zip He a a °a se Pr°I ie i n ir as te r › - ° r+ ois°ass Pr°uie n r rL ^• • He rt u ed s° e‹ r ar ^• •
r de Ma rkdor n — Out ne

dtype s fToats6(i), nt66(13)

memopy us a ge 33 . 2 KB

Looks like the dataset has a total of 303 rows and there are no missing values. There are a total of 1* -fieat ures along with one target value which we wish to find.

The scale of each feature column is different and quite varied as well. While the maximum for age reaches 77, the maximum of c noL (serum cholestoral) is 566.

Understanding the data

Now, we can use visualizations to better understand our data and then look at any orocessing we mig ht want to do.

bit . yt1 c ks ( nP . arange d at a set . s h ape 1 '' , dataset . cod

umn s ) bit . xt1 c ks ( nP . arange d at a set . s h ape 1 '' ,
dataset . cod umn s )

0 • §g L “'¥ • @’ -
art Dise ase P redic ti on i py nb- Visual St udio Code

He ar- ol la s-e Pr°. ie i -n ir as te r › - °. ois ass Pr°. ie n r fi ^• • He rt u ed s°. enIr'lar ^• • i

co for •e^ ' ' t•e-q ' ”

’
 c Users › Taiath oti va mci › up poa a › Lo Lai › Mem p › Tern p1 Hearn a sea se Pred ct on master.zip › Hear oisea se Predictio n mas ter › 9 H ean aide are Predictio n ipynb › •• Heart aidea e P rediciion › •• im port iibr ari es › "• impo rt nu mpy as np
—F code —F uarkdo n -= outline select r:ernei

@ Data Processing

After exploring the dataset, I observed that I need to convert some categorical variables into dummy variables and scale all the values before training the Machine Learning models. First, I'll use
the get_dummi es method to create dummy columns for categorical variables.

d ata set = pd . get dummy es(dat as et column s = [ ' sex ' 'cp' ' lbs ' , ' neste c g ' , ' exa n g ' , ' s TOpe ' , ' ca ' , ' thaI ' )

Now, I will use the standards caLer from skleann to scale my dataset.

dataset[columns to scale] = staodards<aler.Tit transform(dataset[columns to scale])

The data is not ready for our Machine Learning application.

Machine Learning
I'll now import tra i n_test_s omit to split our dataset into training and testing datasets. Then, I'll import all Machine Learning models I'll be using to train and test the data.

ENG
Ct Search

v,vuw uod i,mi<,dw›o ww‹odebow•»g.To«=i,w,dow o ,asea«e«e• use c a,voe

—{- Code —|- Ma rkdow n Out line Sel ect Kern el

I'll now import tra i n_tes t_s plit to split our dataset into training and testing datasets. Then, I'll import all Machine Learning models I'll be using to train and test the
data.

K Neighbors Classifier

The classification score varies based on different values of neighbors that we choose. Ihus, I'll plot a score graph for different values of K (neighbors) and check when do I achieve the best score.

knn score s . append(knn etassif ter. sco re (x test , y test ))

I have the scores for different neighbor values in the array knn_s cores. I'll now plot it and see for which value of K did I get the best scores.

pit . xta bed ( ’ r1u trb er a“ fJe ghb ar s ( K ) ’

ENG
Ct Search
FRONT END:
Output screens:
 Tlulium Test: Nax. Healt Rate

HEART DISEASE ANALYSIS & HOME FEATURES PREDICT

PREDICTION

Get In Touch
 Heart Disease Predictor

HEART DISEASE ANALYSIS & PREDICTION

INTRODUCTION TO TESTING:

Heart disease prediction testing refers to the process of evaluating the performance
of a heart disease prediction model. The purpose of testing is to determine the
accuracy, reliability, and effectiveness of the model in predicting the presence or
risk of heart disease.

There are several types of testing that can be conducted to evaluate a heart disease
prediction model, including:

1. Internal validation: Internal validation involves testing the model on the

same dataset that was used to develop the model. This type of testing can
provide an estimate of the model's performance on new data.

2. External validation: External validation involves testing the model on a new

dataset that was not used to develop the model. This type of testing can provide
an estimate of the model's performance in a real-world setting.

3. Cross-validation: Cross-validation involves splitting the data into multiple

subsets and testing the model on each subset. This type of testing can help assess
the robustness and generalizability of the model.

4. Receiver Operating Characteristic (ROC) curve analysis: ROC curve analysis is

a graphical method for evaluating the performance of a binary classification model,
such as a heart disease prediction model. It involves plotting the true positive rate
against the false positive rate at different thresholds, and calculating the area under
the curve (AUC) as a measure of performance.

5. Confusion matrix analysis: Confusion matrix analysis involves calculating the

number of true positives, true negatives, false positives, and false negatives
predicted by the model. This type of analysis can provide insights into the
sensitivity, specificity, positive predictive value, and negative predictive value
of the model.

Overall, heart disease prediction testing is an important step in the development and
validation of a heart disease prediction model. It helps ensure that the model is
accurate, reliable, and effective in predicting the presence or risk of heart disease,
and can ultimately help improve patient outcomes.

TYPES OF TESTING :

There are several types of testing that can be used to evaluate the performance of a
heart disease prediction model:

1. Internal validation: This involves testing the model on the same dataset that
was used to develop the model. Internal validation can provide an estimate of the
model's performance on new data. Techniques such as bootstrapping and k-fold
cross-validation can be used for internal validation.

2. External validation: This involves testing the model on a new dataset that was
not used to develop the model. External validation can provide an estimate of the
model's performance in a real-world setting.

3. Hold-out validation: This involves randomly splitting the dataset into a

training set and a testing set, and training the model on the training set before
testing it on the testing set. Hold-out validation can be used for both internal and
external validation.
4. Leave-one-out cross-validation: This involves leaving one observation out of the
dataset and training the model on the remaining observations before testing it on the
left-out observation. This process is repeated for all observations in the dataset.

5. Receiver Operating Characteristic (ROC) curve analysis: This is a graphical

method for evaluating the performance of a binary classification model, such as a
heart disease prediction model. ROC curve analysis involves plotting the true
positive rate against the false positive rate at different thresholds and calculating the
area under the curve (AUC) as a measure of performance.

6. Confusion matrix analysis: This involves calculating the number of true

positives, true negatives, false positives, and false negatives predicted by the
model. This type of analysis can provide insights into the sensitivity, specificity,
positive predictive value, and negative predictive value of the model.

7. Calibration curve analysis: This involves comparing the predicted probabilities

of the model to the actual probabilities of the outcome. Calibration curve analysis
can help determine if the model is well-calibrated and provides accurate probability
estimates.

Overall, a combination of internal and external validation techniques should be used

to ensure that the heart disease prediction model is accurate, reliable, and effective
in predicting the presence or risk of heart disease.

TEST CASES AND TEST REPORTS :

To create test cases and test reports for a graphical authentication password project,
you will need to consider the following:

Understand the project requirements: Before you can start creating test cases,
you need to understand the requirements of the graphical authentication
password project. This will help you to determine the expected behavior of the
system and what needs to be tested.
Identify the use cases: Once you have a good understanding of the project
requirements, you can start to identify the use cases that need to be tested.
These are the scenarios that a user might encounter when using the system.
 ⮚ Create test cases: For each use case, you should create a set of test cases that
cover all possible scenarios. These test cases should include inputs,
expected outputs, and any conditions that need to be met for the test to be
considered successful.
⮚ Prioritize the test cases: You may not be able to test every scenario, so it's
important to prioritize the test cases based on their importance and potential
impact on the system.
⮚ Conduct the tests: Once you have created the test cases, you can start
conducting the tests. Make sure to record the results of each test, including
any issues that were encountered.
⮚ Create a test report: Once all the tests have been completed, you can create a
test report that summarizes the results. This report should include a summary
of the test cases, the results of each test, and any issues that were encountered.

Example test case:

Test Case 1: Login using correct graphical password Inputs: User enters the
correct graphical password Expected Output: User should be logged into the
system.

Test Case 2: Login using incorrect graphical password Inputs: User enters an
incorrect graphical password Expected Output: User should not be logged into the
system and an error message should be displayed.

Test Case 3: Create a new graphical password Inputs: User creates a new graphical
password.

TEST REPORTS:

Test Case 1: Passed

Test Case 2: Failed - Error message not displayed

Test Case 3: Passed

Test Case 6: Passed

Test Case 5: Passed

Overall Result:

6/5 tests passed. Issue identified in Test Case 2 where error message was not
displayed.

IMPLEMENTATION:

System implementation is the stage of the project that the theoretical design is
turned into a working system. If the implementation stage is not properly planned
and controlled, it can cause error. Thus it can be considered to be the most crucial
stage in achieving a successful new system and in giving the user confidence that
the new system will work and be effective.

Normally this stage involves setting up a coordinating committee, which

will act as a sounding board for ideas; complaints and problem. The first task is
implementation planning; i.e., deciding on the methods and time scale to be
adopted. Apart from planning two major task of preparing for implementation are,
education takes place much earlier in the project; at the implementation stage the
emphasis must be on training in new skills to give staff confidence they can use the
system. Once staff has been trained, the system can be tested.

IMPLEMENTATION:

Implementing a heart disease prediction system involves several steps. Here is a

high-level overview of the implementation process:

1. Data Collection: The first step is to collect data on patients with and without
heart disease. The data should include a range of clinical and demographic
variables, such as age, gender, blood pressure, cholesterol levels, and family
history of heart disease. This data can be collected from medical records or through
surveys.

2. Data Preprocessing: The collected data needs to be preprocessed to remove

missing values, outliers, and other data errors. This step involves cleaning and
transforming the data so that it can be used for machine learning algorithms.
3. Feature Selection: The next step is to select the most relevant features from
the preprocessed data. This involves using statistical methods or domain
expertise to identify the features that are most strongly associated with heart
disease.

4. Model Development: The selected features are used to train a machine

learning model to predict the presence or risk of heart disease. The model can be
a classification algorithm, such as logistic regression or a decision tree, or a
neural network-based algorithm.

5. Model Evaluation: Once the model has been developed, it needs to be

evaluated using validation techniques such as hold-out validation or k-fold cross-
validation. This step helps to ensure that the model is accurate and reliable in
predicting heart disease.

6. Deployment: Once the model has been developed and validated, it can be
deployed as a web application or integrated into an electronic health record
system. The system should be easy to use and provide accurate predictions of heart
disease risk or presence.

7. Maintenance: Finally, the system should be maintained and updated regularly

to ensure that it continues to provide accurate and reliable predictions as new data
becomes available.

Overall, implementing a heart disease prediction system requires careful planning,

data collection, and model development, as well as ongoing maintenance and
updates to ensure that the system remains effective.

CONCLUSION:

Heart disease prediction is an important application of machine learning in

healthcare. It can help identify individuals who are at high risk of developing
heart disease and enable early intervention to prevent or manage the
disease. The development and implementation of a heart disease prediction
system involves several steps, including data collection, preprocessing,
feature selection, model development, evaluation, deployment, and
maintenance.

A range of machine learning techniques can be used for heart disease

prediction, including logistic regression, decision trees, random forests, and
The performance of the model should be evaluated using validation techniques
such as internal and external validation, hold-out validation, ROC curve analysis,
confusion matrix analysis, and calibration curve analysis.

Overall, heart disease prediction is an important area of research and has the
potential to significantly improve the detection and management of heart disease,
which is one of the leading causes of death worldwide.

Reference websites:

1. Cleveland Clinic Heart Disease Risk Calculator:

https://my.clevelandclinic.org/health/articles/16760-heart-disease-risk-calculator
2. National Heart, Lung, and Blood Institute (NHLBI):
https://www.nhlbi.nih.gov/health-topics/education-and-awareness/heart-truth
3. American Heart Association: https://www.heart.org/en/health-
topics/cardiovascular-disease
4. Mayo Clinic: https://www.mayoclinic.org/diseases-conditions/heart-
disease/symptoms-causes/syc-20353118
5. Centers for Disease Control and Prevention
(CDC): https://www.cdc.gov/heartdisease/index.htm
6. European Society of Cardiology: https://www.escardio.org/
7. World Heart Federation: https://www.world-heart-federation.org/
8. Harvard Health Publishing: https://www.health.harvard.edu/topics/heart-health
9. Heart Research Institute: https://www.hri.org.au/
10. MedlinePlus: https://medlineplus.gov/heartdiseases.html