• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.15-20
• /
• 2018

In modern society, crime is one of the major social problems. Crime has a great impact not only on victims but also on those around them. It is important to predict crimes before they occur and to prevent crime. Various studies have been conducted to predict crime. One of the most important factors in predicting crime is frequency of crime occurrence. The frequency of crime is widely used as basic data for predicting crime. However, the frequency of crime occurrence is announced about 2 years after the statistical processing period. In this paper, we propose a frequency analysis of crime - related key words retrieved from the web as a way to indirectly grasp the frequency of crime occurrence. The relationship between the number of frequency of crime occurrence and frequency of actual crime occurrence was analyzed by correlation coefficient.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.9
• /
• pp.229-236
• /
• 2016

In the past, crime prediction methods utilized previous records to accurately predict crime occurrences. Yet these crime prediction models had difficulty in updating immense data. To enhance the crime prediction methods, some approaches used social network service (SNS) data in crime prediction studies, but the relationship between SNS data and crime records has not been studied thoroughly. Hence, in this paper, we analyze the relationship between SNS data and criminal occurrences in the perspective of crime prediction. Using Latent Dirichlet Allocation (LDA), we extract tweets that included any words regarding criminal occurrences and analyze the changes in tweet frequency according to the crime records. We then calculate the number of tweets including crime related words and investigate accordingly depending on crime occurrences. Our experimental results demonstrate that there is a difference in crime related tweet occurrences when criminal activity occurs. Moreover, our results show that SNS data analysis will be helpful in crime prediction model as there are certain patterns in tweet occurrences before and after the crime.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.5
• /
• pp.235-241
• /
• 2007

AThis research is rather on the crime occurrence of target area's space scope than on the approach to the cause of specific area's crime occurrence from the perspective of the environmental criminology emphasizing the crime prevention. By observing the composition of crime distribution, it is intended to search the strategies of crime prevention actually corresponded to the crime problems. For this, after segmenting the city into six sectors, targeting city crimes in Gwangju metropolitan city, in 2004, the basic materials about the crime frequency are analyzed through dividing the types on the base of the present state of crime occurrence, the types of crime, the locations of crime occurrence, the purposes of buildings, the types of intruders, the forms of intrusions. As a result of research. it is suggested that the activation method of community police activities is necessary for the prevention of community crime prevention.

• Korean Journal of Artificial Intelligence
• /
• v.10 no.1
• /
• pp.21-25
• /
• 2022

Korea has relatively less crime than other countries. However, the crime rate is steadily increasing. Many people think the crime rate is decreasing, but the crime arrest rate has increased. The goal is to check the relationship between CCTV and the crime rate as a way to lower the crime rate, and to identify the correlation between areas without CCTV and areas without CCTV. If you see a crime that can happen at any time, I think you should use a random forest algorithm. We also plan to use machine learning random forest algorithms to reduce the risk of overfitting, reduce the required training time, and verify high-level accuracy. The goal is to identify the relationship between CCTV and crime occurrence by creating a crime prevention algorithm using machine learning random forest techniques. Assuming that no crime occurs without CCTV, it compares the crime rate between the areas where the most crimes occur and the areas where there are no crimes, and predicts areas where there are many crimes. The impact of CCTV on crime prevention and arrest can be interpreted as a comprehensive effect in part, and the purpose isto identify areas and frequency of frequent crimes by comparing the time and time without CCTV.

• Korean Journal of Culture and Social Issue
• /
• v.9 no.1
• /
• pp.1-21
• /
• 2003

A survey of 220 male and 233 female residents of Seoul was carried out to investigate why women appeared to be more fearful of crime than men. As expected, female respondents reported higher levels of fear of crime and perceived physical vulnerability to crime. Incivility factors in the neighborhood and perceived possibility of criminal victimization were significant predictors of fear of crime for both male and female respondents. For women more psychological variables such as trait anxiety and age were other significant predictors of their fear of crime, whereas the distance to police station and frequency of watching crime-related TV programs were significant predictors for men's fear of crime.

• Proceedings of KOSOMES biannual meeting
• /
• 2002.10a
• /
• pp.149-160
• /
• 2002

The relatively rapid rising trends of crime rates in marine situations leads to social concerns in Korea. This study reviews some theoretical backgrounds of the economics of crime and apply econometric models to Korean marine crimes. We find that there is a negative relationship between marine crime rates and unemployment rates and positive relationship between price level and marine crime in Korea. And also we find that unemployment elasticities are higher in the 1980s' and price elasticities are higher in th 90's in comparison with the results of the other periods. This findings are incompatible with the previous theoretical researches in advanced countries. This findings show that in rapidly growing economy, marine crime occurrence is proportional to marine economic activity frequency. This result may reflect that marine crimes are different from land crimes.

• Journal of the Korean Institute of Educational Facilities
• /
• v.23 no.1
• /
• pp.23-32
• /
• 2016

This research aims to securement of crime prevention for school violence and invasion from outside etc. For crime prevention efficiency secure, It has purpose for school current state comprehension and prevention essential elements deduction autonomously etc. Furthermore, school facility crime dangerousness evaluation checklist is looked for autonomous monitoring tools. This checklist made from analysis of frequency, importance and check availability of 6 native and foreign existing CPTED evaluation's 360 indexes. Then, 81 indexes was derived from analysis, and that indexs verified through focus group interview. Finally, total 47 articles checklist emerged with general details, external school, internal school, and school administrative managements. Through this checklist, school can select essential elements of the preferential crime prevention autonomously, and so it is expected to prompt improvement of crime dangerousness elements, school violence and reduction of crime rate.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.8 no.2
• /
• pp.61-69
• /
• 2002

The relatively rapid rising trend of crime rates in marine situations leads to social concerns in Korea. This study reviews some theoretical backgrounds of the economics of crime and applies econometric models to Korean marine crimes. This research finds that there is a negative relationship between marine crime rates and unemployment rates and a positive relationship between the price level and marine crimes in Korea. The other finding results are that unemployment elasticities are higher in the 1980s and price elasticities are higher in th 1990s in comparison with the results of the other periods. This findings are incompatible with the previous theoretical researches in advanced countries. These findings show that In rapidly growing economy, marine crime occurrence is proportional to marine economic activity frequency. This result may reflect that marine crimes are different from land crimes.

• Journal of the Korea Convergence Society
• /
• v.11 no.11
• /
• pp.75-80
• /
• 2020

Since the Fourth Industrial Revolution, important technologies such as big data analysis, robotics, Internet of Things, and the artificial intelligence have been used in various fields. Generally speaking it is understood that the big-data technology consists of gathering stage for enormous data, analyzing and processing stage and distributing stage. Until now crime records which is one of useful big-sized data are utilized to obtain investigation information after occurring crimes. If crime records are utilized to predict crimes it is believed that crime occurring frequency can be lowered by processing big-sized crime records in big-data framework. In this research the design is proposed that the smart system can provide the users of smart devices crime occurrence probability by processing crime records in big-data analysis. Specifically it is meant that the proposed system will guide safer routes by displaying crime occurrence probabilities on the digital map in a smart device. In the experiment result for a smart application dealing with small local area it is showed that its usefulness is quite good in crime prevention.

• Journal of Satellite, Information and Communications
• /
• v.9 no.4
• /
• pp.57-62
• /
• 2014

In this paper, we proposed and implemented a crime pattern analysis algorithm using big data. The proposed algorithm uses crime-related big data collected and published in the supreme prosecutors' office. The algorithm analyzed crime patterns in Seoul city from 2011 to 2013 using the spatial statistics analysis like the standard deviational ellipse and spatial density analysis. Using crime frequency, We calculated the crime probability and danger factors of crime areas, time, date, and places. Through a result we analyzed spatial statistics. As the result of the proposed algorithm, we could grasp differences in crime patterns of Seoul city, and we calculated degree of risk through analysis of crime pattern and danger factor.