ABSTRACT

Crime is an alarming aspect of our society, and its prevention is a vital task. Crime analysis is a well-organised way of detecting and examining patterns and trends in crime. It is of utmost importance to study reasons, consider different factors and determine the relationship among various crimes occurring and discover the best suitable methods to control crime. The primary objective of this project is to distinguish various crimes using clustering techniques based on the occurrences and regularity. Data mining is used for analysis, investigation and check patterns in crimes. In this project, a clustering approach is used to analyse the crime data; the stored data is clustered using the K-Means algorithm. After the classification and clustering, we can predict a crime based on its historical information. This proposed system can indicate regions which have a high probability of crime rate and distinguish areas which have a higher crime rate.

Existing System

It is only within the last few decades that the technology made spatial data mining a practical solution for broad audiences of Law enforcement officials which is affordable and available. Even today all our data is available in the form of paper-based format. We can digitise this great data record for creating a criminal record database. So the primary challenge in front of us is developing a better, efficient crime pattern detection tool to identify crime patterns effectively.

In countries like England, Cambridge Police Department have done a similar one named Series Finder for finding the patterns in a burglary. For achieving this, they used the modus operandi of an offender, and they extracted some crime patterns which were followed by the offender. The predicted result showed more than 80% accuracy. We are applying a similar concept in this study is to examine the use of clustering technology.

DIS-ADVANTAGES

• Increase in crime information that has to be stored and analysed.
• Analysis of data is difficult since data is incomplete and inconsistent.
• Limitation in getting crime data records from the Law Enforcement department..

Proposed System

The precision of the program depends on the correctness of the training set. Finding the patterns and trends in crime is a challenging factor. To identify a pattern, crime analysts takes much time, scanning through data to find whether a particular crime fits into a known pattern. If it does not fit into an existing pattern, then the data must be classified as a new pattern. After detecting a pattern, it can be used to predict, anticipate and prevent crime before this clustering algorithms have been used for crime analysis. For instance, one site it is revealed that suspect has black hair and from next site/witness, it is revealed that suspect is youth and from third one reveals that the offender has a tattoo on his left arm. Through the offender details, we can obtain a basic picture of various crime incidents. These days most of the work is manually done with the assistance of different reports which detectives obtain from data analysts and old crime logs.

SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10

HARDWARE REQUIREMENTS:

 Processor : Core I3
 RAM Capacity : 2 GB
 Hard Disk : 250 GB
 Monitor : 15″ Color
 Mouse : 2 or 3 Button Mouse
 Key Board : Windows 08/10