Description
Crime Detection and Classification using Fuzzy Logic Techniques
Abstract:
The objective of this project is to tackle a vital issue in society – Crimes. Analyzing and examining of crimes happening in the world will give us a Broad view in understanding the crime regions and can be used to take necessary precautions to mitigate the crime rates. Identifying Crime patterns will allow us to tackle problems with unique approaches in specific crime category regions and improve more security measures in society. Current studies show the reason for an increase in crime rates is more in areas that are economically backward. In few decades? property crime will be a target. The following approach involves predicting crimes classifying, pattern detection, and visualization with effective tools and technologies. The use of past crime data trends helps us to correlate factors that might help to understand the future scope of crimes. Crime Detection and Classification using Fuzzy Logic Techniques
Overview:
San Francisco was infamous for housing some of the world’s most notorious criminals on the inescapable island of Alcatraz. Today, the city is known more for its tech scene than its criminal past. From Sunset to SOMA, and Marina to Excelsior, this project analysis 12 years of crime reports from across all of San Francisco’s neighborhoods to create a model that predicts the category of crime that occurred, given time and location.
Scope of the project:
- Crime is a social phenomenon as old as societies themselves, and although there will never be a free from crime society – just because it would need everyone in that society to think and act in the same way – societies always look for a way to minimize it and prevent it.
- Violent crime nearly quadrupled between 1960 and its peak in 1991. Property crime more than doubled over the same period. Since the 1990s, however, crime in the United States has declined steadily.
- We will explore a dataset of nearly 12 years of crime reports from across all of San Francisco’s neighborhoods, and we will create a model that predicts the category of crime that occurred, given the time and location.
System Analysis:
Existing System:
In this system they are proposed logistic regression and K-means classifiers. Researches have been done to study the relation between criminal activities and socio-economic variables like unemployment income level race level of education
Disadvantages:
- It supports only for small and medium-level data?s only.
- It gives the less accuracy
- In existing system, they are use traditional ML algorithms like logistic regression
Proposed System:
Crime is a social phenomenon as old as societies themselves, and although there will never be a free from crime society – just because it would need everyone in that society to think and act in the same way – societies always look for a way to minimize it and prevent it. In the modern United States history, crime rates increased after World War II, peaking from the 1970s to the early 1990s. Violent crime nearly quadrupled between 1960 and its peak in 1991. Property crime more than doubled over the same period. Since the 1990s, however, crime in the United States has declined steadily. Until recently crime prevention was studied based on strict behavioral and social methods, but the recent developments in Data Analysis have allowed a more quantitative approach in the subject. We will explore a dataset of nearly 12 years of crime reports from across all of San Francisco’s neighborhoods, and we will create a model that predicts the category of crime that occurred, given the time and location.
Advantages:
- it should give the best accuracy value
- It accepts large level data?s
we are using the latest techniques like fuzzy logic and logistic regression
Hardware and Software Requirements:
Hardware:
- Windows 7,8,10 64 bit
- RAM 4GB
Software:
- Python 2.7
- Anaconda Navigator
Customer Reviews
There are no reviews yet.