• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.513-515
• /
• 2022

본 연구는 범죄를 발생시키는데 관련된 여러가지 요인들을 기반으로 범죄 예측 모델을 생성하고 설명 가능 인공지능 기술을 적용하여 인천 광역시를 대상으로 범죄 발생에 영향을 미치는 요인들을 분석하였다. 범죄 예측 모델 생성을 위해 XG Boost 알고리즘을 적용하였으며, 설명 가능 인공지능 기술로는 Shapley Additive exPlanations (SHAP)을 사용하였다. 기존 관련 사례들을 참고하여 범죄 예측에 사용된 변수를 선정하였고 변수에 대한 데이터는 공공 데이터를 수집하였다. 실험 결과 성매매단속 현황과 청소년 실종 가출 신고 현황이 범죄 발생에 큰 영향을 미치는 주요 요인으로 나타났다. 제안하는 모델은 범죄 발생 지역, 요인들을 미리 예측하여 제시함으로써 범죄 예방에 사용되는 인력자원, 물적자원 등을 용이하게 쓸 수 있도록 활용할 수 있다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.4
• /
• pp.221-229
• /
• 2015

The urban crimes that threat individual's safety are parts of the serious social problems. However. the information of crime in Korea has only been provided by forms of hot spots around place of crime, or forms of crime statistics without positional information. Those could not provide enough information to users in identifying the vulnerable areas for substantive crimes. Therefore, this study suggested a methodology of extraction in criminal vulnerable areas by using the spatial information, the statistical information and the public sector information. The crime vulnerable areas were extracted through the grid-based spatial analysis and the overlapping analysis from each of the information. In fact, the extracted areas were able to provide detailed vulnerability information than the traditional hot spot-based crime information. Following the study, the extracted results in crime vulnerable areas have displayed highly coincide with Korea safety map, provided by national disaster management institute, which regards to be able to provide crime risk rating in terms of administrative business in future.

• Korean Security Journal
• /
• no.14
• /
• pp.261-283
• /
• 2007

In recent studies for explaining the causation of crime fear shows interest and effort in studies attempting microscopical individual level and macroscopical local level of sex, age, economic level, crime damage level and etc. However, in this study, it is considered that interest and analysis of individual on characteristics of these local level may has its difference depends on crime damage experience in the past, fragility precision of crime damage and interest on crime relating information and processed positive analysis on characteristics of individual and relation of crime fear on individual level before making an attempt of connecting microscopical level and macroscopical level. Therefore, the purpose of this study is on positive verification of how people feel about crime fear depends on individual's characteristic and also how much effect would they receive. As the result of this study, it is shown that first, population statistical characteristics that crime damage experience is statistically meaningful of its difference of each group are age, status of marriage, final education status and residential area and for the fragility precision of crime damage was sex and status of marriage and for the interest about the crime relating information has meaningful difference statistically of each group depends on sex, age, final education status, income of the house and location of residential area. Second, after processing correlation analysis on individual characteristic primary factor and crime fear, the result of 3 primary factor independent variable all shows statistically meaningful correlation with crime fear and especially fragility primary factor on crime damage showed the most high correlation with crime fear. Lastly, fragility of crime damage, interest on crime information and crime damage experience has effected as characteristics of individual and especially fragility of crime damage which the person thought to be the most fragility on crime damage out of these individual characteristic primary factor showed to have the most effecting primary factor.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.1
• /
• pp.12-25
• /
• 2009

The aim of this study is to analyze the periodical and spatial characteristics of urban crime and to find out the factors that affect the crime occurrence. For these, crime data of Masan City was examined and crime occurrence pattern is ploted on a map using crime density and criminal hotspot analysis. The spatial relationship of crime occurrence and factors affecting crime were also investigated using ESDA (Exploratory Spatial Data Analysis) and SAR (Spatial Auto-Regression) model. As a result, it was found that crimes had strong tendency of happening during a certain period of time and with spatial contiguity. Spatial contiguity of crimes was made clear through the spatial autocorrelation analysis on 5 major crimes. Especially, robbery revealed the highest spatial autocorrelation. However as a autocorrelation model, Spatial Error Model(SEM) had statistically the highest goodness of fit. Moreover, the model proved that old age population ratio, property tax, wholesale-retail shop number, and retail & wholesale number were statistically significant that affect crime occurrence of 5 most major crimes and theft crime. However population density affected negatively on assault crime. Lastly, the findings of this study are expected to provide meaningful ideas to make our cities safer with U-City strategies and services.

• Journal of Convergence for Information Technology
• /
• v.8 no.1
• /
• pp.161-171
• /
• 2018

This study set out to identify crime vulnerable areas with the GIS spatial analysis technique for the prediction of crimes. Crime vulnerable areas were extracted from the statistics of crimes with the GIS hotspot analysis technique and the inverse distance weighted(IDW) method applied to different crimes according to places and use districts. The scope of surveillance and weight were calculated for each of CPTED surveillance elements including CCTV, streetlamp, patrol division, and police substation. Maps of crime vulnerable areas were overlapped one after another to make a CPTED-based one expressed in four grades(safety, attention, warning, and risk).

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.283-288
• /
• 2021

The purpose of this paper is to provide basic data for related studies by comparing and analyzing crimes committed by security guards through criminal statistical analysis, and to contribute to the sound development of the private security industry by strengthening the professional ethics of security guards and reducing guard crimes. The purpose. As a results of a comparative analysis of the number of crimes by security guards and the crime rate are as follows. Although the total number of crimes committed in Korea and the number of crimes committed by security guards decreased every year, the crime rate of security guards was higher than the average crime rate. felonious crimes, violent crimes, customs crimes, and special economic crimes were consistently high. As a countermeasure against the results, first, interest in security guard crimes as perpetrators rather than as victims, second, reinforcement of professional ethics education through new training and job training, third, academic development and systematic It appeared as a specification of the definition and current status of security guards for the study.

• Communications for Statistical Applications and Methods
• /
• v.1 no.1
• /
• pp.141-148
• /
• 1994

범죄형태에 관한 연구를 하기 위하여 재소자들에 관한 자료를 이용하는 경우가 많다. 그러나 이들 자료를 범죄자 전체의 모집단을 대표하는 표본이 될 수 없으므로 추정치에 편기가 존재하여 그대로 사용할수 없다. 단순 교대재생과정에 기초를 두고 재소자들의 특성을 고려하여 모형을 세우면, 편기가 제거된 범죄횟수, 재소기간등에 관한 추정치를 얻을 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1638-1641
• /
• 2015

최근 다양한 공공 데이터가 속속 개방되고 있지만, 지역 내의 범죄 데이터는 통계 데이터 이외에는 공개되지 않고 있다. 이처럼 공공 데이터의 확보가 어려운 경우에는 해당 지역 내의 범죄 관련 모든 온라인 뉴스 기사를 주기적으로 수집하고 범죄 현황에 관한 정보를 자동으로 추출하여 맵(map)에 시각화 하여 보여주는 프레임워크의 개발이 필요하다. 본 논문에서는 프레임워크 개발에 필요한 주요 알고리즘들과 효과적인 시각화 방안을 제안한다. 또한 이미 공개된 군산시의 범죄 발생 통계 자료를 비교하여 제안 시스템의 효용성을 평가한다.

• The Journal of the Korea Contents Association
• /
• v.17 no.10
• /
• pp.65-71
• /
• 2017

It is true that there is a possibility of distortion in the statistical surveys or actual surveys depending on which investigator, what purpose, and how research method. Even statistical results are more likely to be 'lying', and statistics on crime or delinquent are sometimes referred to as 'whopper'. There are many reasons for not trusting statistics on crime or delinquent, but one of the main causes is the existence of a hidden crime or an unreported crime. In order to overcome these hidden crime problems, victim surveys or self-report surveys are being used. However, this method also has the problem of underreporting or overreporting depending on the type of crime. Because investigations into crime, delinquency, and deviant behavior are very sensitive, the subjects have a psychological burden. A randomized response model has been developed and used in the field of statistics as a way to induce a true answer to the sensitive content which is burdensome to reveal the experiences of the survey subjects. This technique is a very useful way to solve the problems of victim surveys or self-report surveys. Nevertheless, there are very few cases in the field of criminology in Korea. Therefore, in order to examine the applicability of the randomized response model in the field of criminology, this study used the randomized response model to actually measure the content of prostitution for college students and the effectiveness of the randomized response model was confirmed.

• 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.