• Tidak ada hasil yang ditemukan

Daffodil International University

N/A
N/A
Protected

Academic year: 2023

Membagikan "Daffodil International University "

Copied!
46
0
0

Teks penuh

This project entitled "CRIME ANALYSIS AND DATA USE FORECASTING", submitted by Jannatul Faria, ID No to the Department of Computer Science and Engineering, Daffodil International University, has been accepted as satisfactory in partial fulfillment of the requirements for the degree of B. .Sc. Department of Computer Science and Engineering Faculty of Information Science and Technology Daffodil International University. Syed Akhter Hossain, Head of CSE Department, for his kind help to complete our project and also to other faculty members and staff of CSE department of Daffodil International University.

We would like to thank all our coursemates at Daffodil International University who participated in this discussion while completing the coursework. Data mining framework, which is easy to implement, works with the geospatial plot of crime and criminal activities and helps to increase the efficiency of the police forces and other law enforcement agencies.

Motivation

We chose group algorithmic guidelines over the other algorithmic principle such as order as a result of misbehavior is vastly different in nature and misbehavior data square measure usually replete with uncertain violations. In this way, arrangement algorithm principle that can have certainty about the current and known completed violations will not give meaningful prognostic factors to future violations.

Objectives

Research is perpetuated by misuse of open supply of information preparation equipment that uses diagnostic devices to examine data. Among the modified offered open supply information processing suite such as KNIME, WEKA, R, ORANGE, high-speed excavator, WEKA is chosen. K implies that all this is done using a fast miner device that concerns open supply, connected science and information, preparing PC code written in Java with various flexible information processing decisions.

The monstrous amounts of error data are also put in light of the fact that the unpredictability of connections between this kind of information has made the human sciences a worthy field in which to apply and test information management strategies. The data and learning gained from the information management method can be a tremendously valuable instrument that can encourage and strengthen legal requirements.

Research Questions & Objectives

Expected Outcome

The faults that slope areas where the fault event is expected using our framework can be spoken to graphically using a heat contour shows level of movement, usually low action is shown by lighter shadows and high action is shown by darker shadows.

Report Layout

Background

  • Introduction
  • Related Works
  • Research Summary
  • Scope of the Problem
  • Challenges

Using nine known offense arrangements of thefts, Series Finder recovered the most violations in these detected examples and also recognized nine additional violations. Their basic aim was to model and build wrong actions; research into the use of error-based reasoning to improve order and grouping; build an intelligent recovery framework news identified with wrongdoing; image news identified with violations in a powerful and intuitive way; incorporate them into a usable and strong and reliable framework and evaluate the usability and performance of the framework and the study will contribute to a better understanding of the information identified with wrongdoing and exploitation in the Malaysian setting and furthermore the framework that is created with the perception highlights to address information about wrongdoing and the inevitable goal of combating the violations. This area outlines and looks at the study directed and discoveries that have modeled forecasts of wrongdoing for the underlying long stretches of the 21st century.

There are several elements that influence the type of misconduct, despite the fact that there is no specific or authoritative explanation as to why the rate of misconduct has fallen over the past few years or why it has started to increase drastically in the circumstances such as e.g. 1960s. Page 11 In any case, the two most essential drivers that have affected past delinquency rates and are required to be deeply persuasive about future rates are full-scale financial variables such as quality of the economy, buyer spending, unemployment rates, and specifically statistical factors. the amount of guys in the offense prone age gathering. The simple answer is that it has two essential foci for broadly ranked measurements of the frequency of misconduct: the information collected by the Uniform Crime Reporting Office and the aftermath of the ongoing National Crime Victimization Survey conducted by the Outsiders Association.

Despite the fact that there is some motivation to believe that the scale of irregularities and the level of irregularities have expanded over the last too many years of the twentieth century, it remains difficult to see whether the issue of irregularities has really worsened or is showing signs of improvement. Such reasons, and the resulting approval of levels of wrongdoing in the United States, most likely grew, at least to some degree, out of an apparent mix of the general issue of wrongdoing. Measurements from both free and law enforcement associations provide the end that illegal conduct expanded throughout the 1980s and largely leveled off in the mid-1990s.

In addition, the metrics accumulated towards the end of the 1980s and all the way ahead of schedule to the mid-1990s reflected not just an evolution in the propensity offense problem, but in addition an evolution in authoritative and managerial attention on the problem. Page 13 Experts are currently of the opinion that predictive crime is not yet a fully accepted and good crime prevention method. If perfected, it could arguably become one of the most useful tools for the safety of humanity as a whole.

Research Methodology

  • Introduction
  • Research Subject and Instrumentation
  • Data Collection Procedure
  • Statistical Analysis
  • Implementation Requirements
  • Introduction
  • Experimental Results
  • Descriptive Analysis
  • Implementation and Testing
  • Summary

Using the Naive Bayes calculation, we create a model by constructing misbehavior information identified with murder, vandalism, theft, theft, assault, sex abuse, fire-related crimes, armed burglary, fraud, fraud and so on. Test results show that Naive Bayes indicates more than 90% accuracy as it classifies each word as tokens and omits consecutive words such as "the and of" and so on, which increases accuracy. A word is naturally terminated if it occurs less often or more often.

Thus, using this idea in the wrongdoing article, we can get more subtle elements identified with wrongdoing, such as the names of the unfortunate victims and wrongdoers, wrongdoing area, date, time and so on [20]. In the information gathering step, we are collecting information from various sites like news sites, online magazines, internet based life, RSS feeds etc. Unlike an SQL database, it doesn't have to figure out what we're dropping ahead of time, tell it its size, and so on.

Apriori can be used to determine joining rules that contain standard and common patterns in the database. Here, with respect to each area, we take the characteristics of that area, its climatic features, the suggestibility of the zone, its proximity to criminal gatherings, an important occasion, and so on. After obtaining a general misconduct design for a place, when another case arises and is likely to pursue a similar misconduct design, we can say that the region has a possibility for a misconduct.

They can stay away from malfeasance events by providing security/viewing in malfeasance prone territories, installing criminal warnings/CCTV etc. That way, in the event that there is an instance in which wrongdoing has occurred, we recognize that in the event that design occurs again in a location, there is a likelihood of a wrongful event occurring in that location. The fundamental advantage of using the choice tree is that it is easy to understand and translate.

In case the first condition is met, we check the next case and if there is a good chance that the main condition itself is not met, there is no compelling reason to check the rest. In this way, by thinking about the plausible areas, we can counteract abuses by deploying preventive tools such as night vigils, arranging thief alerts, arranging CCTV cameras, and so on.

FIG: 3.1: Crime Analysis Steps
FIG: 3.1: Crime Analysis Steps

Summary, Conclusion, Recommendation and Implication for Future Research

  • Summary of the Study
  • Conclusions
  • Recommendations
  • Implication for Further Study

Page 30 pattern over years and can be used to structure more successful protection strategies for the future as the forecast shows. Examples of offenses cannot be static, as examples change are likely to change after some time. Thus, the framework consequently takes into account the modification of errors by assessing the error designs.

By examining delinquency information, we must recognize new delinquency factors that lead individuals to commit delinquency. In order to show signs of improvement in prediction results, we need to detect more features of the speckle malformation as compared to the change of some features. From our findings and aggregated results, it is anything but difficult to discern the pattern of wrongdoing over the years and can be used to structure more successful defense strategies for the future as predicted.

To show signs of improvement in prediction results, we need to detect more features of speckle malformation such as. In addition, we need to think about the different crime data sets from the new urban communities along with their statistical data sets. It is an extremely accurate tool for profiling the attributes or points of interest of perpetrators or guilty parties.

To do this, we must break the foundation of criminality and their data to collect the most extreme related information. The moment misdeeds like murder happen in a particular place, then from the reports like FIR, we get the subtle elements of the criminal and. After getting these subtle elements, we can think about the guilty parties with these practices.

APPENDIX

Purvis, 'Crime information extraction from online newspaper articles', in Proceedings of the Second Australasian Web Conference - Volume 155, Auckland, New Zealand, 2014, p. Databases (ECMLPKDD. 10] Sutapat Thirprungsri Rutgers University .USA, 2011 Cluster analysis of anomaly detection in accounting data: An audit approach 1.

Faculty of Mathematics and Computer Science .University of Kufa/Iraq, 2011 A Proposed Framework for Analysis of Crime Datasets Using Decision Tree and Simple K-means Mining Algorithms. 15] Aravindan Mahendiran, Michael Shuffett, Sathappan Muthiah, Rimy Malla, Gaoqiang Zhang, 2011 Forecasting Crime Incidents using Cluster Analysis and Bayesian Belief Networks.

Gambar

FIG: 3.1: Crime Analysis Steps
FIG: 3.2: Boston Police Department Crime Dataset in xls format
FIG: 3.3: Attribute Sets
FIG: 3.5: Procedure in Data Model Take crime dataset
+6

Referensi

Dokumen terkait

ii ©Daffodil International University APPROVAL This Project titled “Online Pharmacy Management System”, submitted by Name: Hasan Habibur Rahman and Mohammad Abul Kalam Azad, ID

©Daffodil International University i APPROVAL This Project titled “Design and Development of an online Learning Management System”, submitted by Mehedi Hasan Danee and Abdullah Al

i APPROVAL This Project/internship titled “MUSHROOM CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK: A TRANSFER LEARNING APPROACH” submitted by Julfikar Habib, ID No: 181-15-11182,

©Daffodil International University ii APPROVAL This internship titled “INTERNSHIP ON CISCO CERTIFIED NETWORK ASSOCIATE CCNA”, submitted by Anirudha Sarkar, ID No: 182-15-11579 to the

APPROVAL The project report „Web Design and Development of Online University Result Management System‟ submitted by Sanjida Akter, ID: 161-15-7154 The Department of Computer Science

APPROVAL This Project titled Design and development of security equipment market Secured BD, submitted by Al-Amin to the Department of Computer Science and Engineering, Daffodil

i ©Daffodil International University APPROVAL This Project/internship titled “WEB APPLICATION DESIGN & DEVELOPMENT FOR THE PURPOSE OF SOCIAL SUPPOERT”, submitted by MUSHFIQUR

APPROVAL This project titled “​MEDICATE: ​A Mobile Application to Automate Patient-Doctor-Hospital Relationships​”, submitted by Farhana Binta Shaheed ID 162-15-734 and Faisal Kabir ID