Scribd
Upload
5 views24 pages

Crime Prediction

The document outlines a project that utilizes AI to analyze various crimes in India, employing a technology stack that includes Flask, SQLite, HTML, CSS, and JavaScript. It details the workflow from user authentication to crime prediction using a Random Forest algorithm, achieving a prediction accuracy of 93.20%. Additionally, it emphasizes the importance of crime rate prediction for law enforcement and provides insights into cybercrime prevention and safety measures.

Uploaded by

bca40519.22
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5 views24 pages

Crime Prediction

The document outlines a project that utilizes AI to analyze various crimes in India, employing a technology stack that includes Flask, SQLite, HTML, CSS, and JavaScript. It details the workflow from user authentication to crime prediction using a Random Forest algorithm, achieving a prediction accuracy of 93.20%. Additionally, it emphasizes the importance of crime rate prediction for law enforcement and provides insights into cybercrime prevention and safety measures.

Uploaded by

bca40519.22
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 24

A STUDY OF VARIOUS

CRIMES IN INDIA USING AI

TECHNOLOGY STACK: FLASK, SQLITE, HTML, CSS, JAVASCRIPT


WORK FLOW OF PROJECT
WHY FLASK?

• Lightweight and flexible web framework.


• Easy to integrate with HTML, CSS, JavaScript.
• Suitable for small to medium-scale applications.
• RESTful request handling.
• Simple routing and template engine (Jinja2).
WHY SQLITE?

• Lightweight and serverless.

• Zero-configuration database, perfect for small projects.

• Integrated directly into Python using sqlite3 module.

• Easy to create, query, and manage.

• Ideal for storing user credentials, face recognition metadata, etc.


LOGIN AUTHENTICATION PROCESS
LOGIN PAGE – HOW IT WORKS

• User enters email and password.


• Credentials are validated against SQLite database.
• If credentials match, access is granted to the dashboard.
• Secure session handling to maintain user authentication.
HOME PAGE – OVERVIEW

• Landing page post-login.


• Displays navigation options: Crime Prediction, Cyber Law
Info, Developer Info.
• Dynamic and responsive design.
• Personalized user greetings based on session.
DEVELOPERS PAGE – HOW IT WORKS

• Displays team member information.


• Each profile includes name, role, and image.
• Created using card-based layout in HTML/CSS.
• Responsive grid format with hover animations.
TECHNOLOGIES USED

• Frontend: HTML, CSS, JavaScript


• Backend: Flask (Python)
• Database: SQLite
SUMMARY & FLOW

1.User signs up with details → Data stored in SQLite.


2.User logs in with credentials → Redirected to Home.
3.Home page shows navigation → Crime Prediction, Cyber
Laws, Developers, Contact.
4.Data visualized with graphs, predictions shown with dynamic
charts.
5.Clean and responsive user interface with clear data flow.
INTRODUCTION

 Crime is an act that violates a law and is punishable by


the government.
 Crime prediction determine increase or decrease in
crime rate from preceding years.
 Machine Learning algorithms and data-driven methods
can be used to identify patterns in data.
INTRODUCTION TO MACHINE LEARNING

•
DATASET

• The dataset is prepared manually based on the publication available on the


National Crime Rate Bureau (NCRB) official website.

• The data provides statistics on the number of crimes committed in 19 Indian


metropolitan cities during the year 2014 to 2021.

• It includes statistics on 10 different categories of crime, including murder,


kidnapping, crime against women, crime against children, crime committed by
juveniles, crime against senior citizens, crime against SC, crime against ST,
economic offences and cyber crimes.
ALGORITHM – RANDOM FOREST
• Random Forest is an ensemble learning technique that combines multiple decision trees
to generate a more accurate prediction.

• It is a versatile and powerful algorithm used in a wide variety of applications.


• The algorithm can be illustrated as follows:
1. Begin with a dataset of observations and their associated labels.
2. Randomly select ‘k’ features from the dataset.
3. For each of the ‘k’ features, choose the best split point.
4. Create a tree using the chosen split points.
5. Repeat steps 2-4 for each of the ‘k’ features.
6. Combine the trees to form a forest.
7. Use the forest to make predictions on new data.
8. Calculate the accuracy of the predictions.
PROPOSED SYSTEM

• Data Preprocessing: The data is prepared in the correct format for analysis. Some columns are
removed or transformed, and label encoding is used to convert the categorical data into numeric
for better prediction.

• Random Sampling: After feature selection, the data has been splitted into two parts: training data
(70%) and testing data (30%).

• Model Creation: The model algorithms are imported from sklearn. The dataset has been analyzed
using five different models: support vector machine, nearest neighbor, decision tree, random forest,
and neural network.

• Model Selection: Based on the defined goals and model performance, random forest model has
been selected.

• Model Deployment: The model has been deployed for prediction using flask web technology.
SYSTEM ARCHITECTURE
RESULTS & DISCUSSION
• The Random Forest Regression model demonstrates the best accuracy in
predicting test data among the five selected models.

• The model predicts the crime rate with an accuracy of 93.20% on the testing
data.

• The accuracy results obtained after testing are listed below:


Algorithm Mean Absolute Mean Squared R2 Score
Error Error
Support Vector Machine 10.3204 371.7907 0.17886

K-Nearest Neighbor 6.58181 140.8179 0.55349

Neural Networks MLPRegressor 12.4248 307.5506 0.24823

Decision Tree Regressor 2.89024 34.95932 0.88915

Random Forest Regressor 2.49143 21.43956 0.93201


CONCLUSION
• Crime rate prediction has become an important tool for law enforcement
agencies to help them focus their resources in high-crime areas.

• By focusing their resources in the right areas, police officers can help reduce
the overall crime rate in a community.

• As a result of machine learning technology, finding relationships and patterns


between various data has become easier.

• The model prediction of crime rate and data visualization helps in analysis of
data set and prediction of crimes.

• The model helped in understanding different crime datasets that can be used in
implementing the factors that can help in keeping society safe.
SUBMIT YOUR CYBER
QUERY
THIS INPUT FORM FOR CYBER QUERY
•FIELDS:
• Your Name: For personal
identification.
• Your Email: To respond or follow up
with the user.
• Your Query: A text area where users
describe their cyber issue or
question.

SUBMIT BUTTON
•ONCE CLICKED: IT LIKELY TRIGGERS A BACKEND FUNCTION TO
STORE OR SEND THE QUERY TO THE CYBER ANALYSIS TEAM.
CYBERCRIME PREVENTION
What is Cybercrime?

Cybercrime refers to illegal activities carried out using computers or the internet.
Common Cyber Threats

•Phishing Emails

•Malware and Ransomware

•Data Breaches

•Online Scams

General Prevention Tips

•Use Strong and Unique Passwords


•Keep Software Updated
•Always Log Out After Use
•Use HTTPS-Secured Websites
SOCIAL MEDIA SAFETY

•KEEP YOUR PROFILES PRIVATE


•THINK BEFORE SHARING PERSONAL INFO
•IGNORE FRIEND REQUESTS FROM STRANGERS
MOBILE SAFETY

•INSTALL APPS ONLY FROM TRUSTED SOURCES


•USE BIOMETRIC OR PIN SECURITY LOCKS
CYBER SAFETY FOR BUSINESSES

•TRAIN EMPLOYEES ON CYBER HYGIENE


•USE FIREWALLS AND ENCRYPTION METHODS
CYBER CRIME STATISTICS
Control Panel (Top Options):
• Home Button: Returns to the
homepage.
City List (Left Panel):
• Displays a list of cities with the
number of cyber crime cases next
to each.
Graph Display (Center Panel):
• Bar Chart Visualization:
Represents total cyber crime cases
per city.
USER INTERFACE DESIGN:

•Soft green and gray theme: Gives a clean and modern look.
•Shadow effects: Make dropdowns and boxes pop out nicely.
•Well-structured layout: Easy navigation and interaction.

•Color-coded bars make it easy to distinguish different cities.


•X-Axis: Cities
•Y-Axis: Total Cases
THANK YOU

You might also like