DESIGN AND IMPLEMENTATION OF A COMPUTERISED SYSTEM FOR  DETECTING CRIMINAL TENDENCIES USING MACHINE LEARNING

DESIGN AND IMPLEMENTATION OF A COMPUTERISED SYSTEM FOR  DETECTING CRIMINAL TENDENCIES USING MACHINE LEARNING

ABSTRACT

Crime is a serious problem in the society today and to solve it. Crimes have a negative effect on any society both socially and economically. Law enforcement bodies face numerous challenges while trying to prevent crimes. There are several issues that contribute to the weakness of the present system of dealing with crime which includes loss and poor management of criminal records, inefficiency and redundancy in the overall process. The developed system will be able to help the police force to keep an eye out for potential criminals. Artificial Neural Network was used in analyzing and designing the proposed system.  The system was implemented using MATLAB to predict the chances of any criminal tendencies.

CHAPTER ONE

1.1 BACKGROUND OF THE STUDY

A crime can be defined as any action or omission that violates a law, which results in a punishment. Usually what constitutes as a crime depends on the government bodies and laws that are in existence in those places. Crimes are a significant threat to the humankind. There are many crimes that happen at regular interval of time. Perhaps it is increasing and spreading at a fast and vast rate. Crimes happen from small village, town to big cities. Crimes are of a different types – robbery, murder, rape, assault, battery, false imprisonment, kidnapping, homicide. Since crimes are increasing there is a need to solve the cases in a much faster way. The crime activities have been increased at a faster rate and it is the responsibility of police department to control and reduce the crime activities. Crime prediction and criminal identification are the major problems to the police department as there are tremendous amount of crime data that exist. There is a need of technology through which the case solving could be faster. Studies on these planned crimes observed that there are patterns of those kinds of crimes happening on specific geographical areas. Persons who intended to do crimes choose seclude places for committing the crime where the police and other law enforcement patrols are less. Because of this reason there is a higher probability of predicting the crimes which going to happen in the future.

However, earlier days the data about crimes are based on the police reports, newspapers, reports and articles. Those all were in hand written hard copy format, but nowadays police and other law enforcement authorities are maintaining a soft copy of these data along with the hard copy. Those soft data generations in these days are very high. These data are just not a bulk of data but valuable information that can be used to predict upcoming crimes and solve exiting. Criminals are human beings, since they are trying to repeatedly do the same thing. They will use same locales and high crime risk areas repeatedly. This is called “Modus Operandi” (MO). Series of crime have some common attributes which can be used to characterize the modus operandi of the criminal.

Machine learning agents work with data and employ different techniques to find patterns in data making it very useful for predictive analysis. Law enforcement agencies use different patrolling strategies based on the information they get to keep an area secure. A machine learning agent can learn and analyze the pattern of occurrence of a crime based on the reports of previous criminal activities and can find hotspots based on time, type or any other factor. This technique is known as classification and it allows predicting nominal class labels. Classification has been used on many different domains such as financial market, business intelligence, healthcare, weather forecasting etc.

 

1.2      STATEMENT OF THE PROBLEM

Various problems are encountered in detecting criminal tendencies which specifically involves use of data analytics and relevant technologies to prevent crime from transpiring. Some of the problems encountered are:

1. There is no computerized system known in Nigeria for recording crime.
2. Criminals who often commit crime are not known even if they get arrested often and so the police do not track them and control the chances of them committing the same crime again.

1.3       AIM AND OBJECTIVES OF THE STUDY

The aim of this project work is to design and implement a computerized system to detect criminal tendencies. This project identifies a machine learning approach to detect the criminal tendencies by using past data related to the crimes. Identify the geographical ‘hotspots’ where a crime can happen frequently.

The objectives are as follows:

1. To develop a system that will analyze and detect criminal tendencies and predict crime.
2. To develop a system capable of helping the police track down common criminals.

1.4       SIGNIFICANCE OF THE STUDY

The adoption of computer technology in the operations of various sectors such as education, health, management, security etc. in the society today, has greatly increased the efficiency of all processes carried out by these sectors. If the developed system is implemented, and effectively utilized it would reduce the problems of loss of records of information of crimes, reduce redundancy in the overall processes, and would enable a quick retrieval of information of criminal activities. The beneficiaries of this project are security agencies as they will be able to get the information about criminal acts on time and also the general public they will be able to leave the crime scene on time.

 

1.5       SCOPE OF THE STUDY

The scope of this study is limited to using a machine learning algorithm to predict criminal tendencies. The study involves methods for the prediction using the crime recorded, making use of the dataset from its database if provided by the government.

 

1.6       DEFINITION OF RELATED TERMS

Crime: Crime can be defined as any action or omission that violates a law

Knowledge-based:  Information system that store wealth of one’s knowledge

Data mining: It is a broad term that encompasses both data management and statistical techniques. Data management refers to how data are prepared for the application of data mining techniques. These techniques are used to explore variables that predict student progression relating to their success or general academic performance.

Multilayer Perceptron (MLP): They are layered feed forward networks typically trained with static back-propagation. They take input to add some weighting to it which is defined when it has been trained, then apply that to give an output.

Machine Learning: It is a meld of statistics and AI which became more cost-effective than AI as its cost of running a machine learning algorithm is cheaper. It combines AI heuristics with advanced statistical analysis. It allows the computer to learn about the data it is studying.

Regression: It is used to predict numerical rather than categorical labels. It works by essentially fitting a regression curve through the data points as if they were plotted on a graph. A.I:  This stands for Artificial intelligence which is a branch of Computer Science.

ANNs: This stands for Artificial Neural Networks Systems which are non-linear mapping structures based on the function of the human brain.

Modus Operandi (MO): A particular way or pattern of doing something.

 

 

DESIGN AND IMPLEMENTATION OF A COMPUTERISED SYSTEM FOR  DETECTING CRIMINAL TENDENCIES USING MACHINE LEARNING

Sharing is caring!