• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.17-18
• /
• 2015

To improve urban safety there is an increasing social need for environmental design against crime, which is defined as the creation of inconvenient environments or situations for criminal offenders. By using a cluster analysis, we aimed to clarify crime occurrence patterns from the perspective of land-use. Osaka Prefecture was chosen as the study area because it has the highest crime rate in Japan. The results revealed that there are six patterns of crime occurrence, and that cities of medium-level of mixed land-use have the lowest crime rates.

• Architectural research
• /
• v.14 no.2
• /
• pp.45-56
• /
• 2012

The high rate of urban crime is a main issue that needs to be dealt with in this high-tech society. With the rapid increase of urban crime, research has mainly focused on topics either on a global or a local scale, such as cities or communities and houses or buildings, without reliable observational data. This study makes the best use of the nationwide surveys carried out by Korean government agencies for the analysis of urban crime patterns and factors in major Korean cities. The aims of this research are threefold: understanding the relationship between urban crime patterns and socio-economic differences in cities, determining the effect of residence types on the urban crime patterns; and uncovering potential influential factors of a crime victim's individual characteristics. The statistical methods used for the analysis of social statistical data are as follows: simple regression, logistic regression, one-way ANOVA and post-hoc test. This research found that the patterns of urban crime rate in cities have a certain tendency toward the cities' socio-economic and geographical differences. The residence type is an influential factor showing a close relation to the crime rate. Personal issues, such as the types of occupation, education, marriage, etc., are directly relevant to victims of crime.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1058-1080
• /
• 2021

Crime is not a completely random event but rather shows a pattern in space and time. Capturing the dynamic nature of crime patterns is a challenging task. Crime prediction models that rely only on neighborhood influence and demographic features might not be able to capture the dynamics of crime patterns, as demographic data collection does not occur frequently and is static. This work proposes a novel approach for crime count and hotspot prediction to capture the dynamic nature of crime patterns using taxi data along with historical crime and demographic data. The proposed approach predicts crime events in spatial units and classifies each of them into a hotspot category based on the number of crime events. Four models are proposed, which consider different covariates to select a set of independent variables. The experimental results show that the proposed combined subset model (CSM), in which static and dynamic aspects of crime are combined by employing the taxi dataset, is more accurate than the other models presented in this study.

• Journal of Satellite, Information and Communications
• /
• v.10 no.2
• /
• pp.40-45
• /
• 2015

In this paper, we proposed and implemented a crime prediction algorithm based upon crime influential factors. To collect the crime-related big data, we used a data which had been collected and was published in the supreme prosecutors' office. The algorithm analyzed various crime patterns in Seoul from 2011 to 2013 using the spatial statistics analysis. Also, for the crime prediction algorithm, we adopted a Bayesian network. The Bayesian network consist of various spatial, populational and social characteristics. In addition, for the more precise prediction, we also considered date, time, and weather factors. As the result of the proposed algorithm, we could figure out the different crime patterns in Seoul, and confirmed the prediction accuracy of the proposed algorithm.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.272-287
• /
• 2021

This article presents a multi-dimensional spatial pattern analysis of crime events in San Francisco. Our analysis includes the impact of spatial resolution on hotspot identification, temporal effects in crime spatial patterns, and relationships between various crime categories. In this work, crime prediction is viewed as a classification problem. When predictions for a particular category are made, a binary classification-based model is framed, and when all categories are considered for analysis, a multiclass model is formulated. The proposed crime-prediction model (HotBlock) utilizes spatiotemporal analysis for predicting crime in a fixed spatial region over a period of time. It is robust under variation of model parameters. HotBlock's results are compared with baseline real-world crime datasets. It is found that the proposed model outperforms the standard DeepCrime model in most cases.

• 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.

• Spatial Information Research
• /
• v.8 no.2
• /
• pp.213-232
• /
• 2000

It is important to scrutinize spatial patterns in crime analysis since crime data has geographical attribute in itself. We focus on the development of ¨Crime Analysis GIS¨ prototype which can discover spatial patterns in crime data by integrating mapping functions of GIS and spatial analysis techniques. The structure of this system involves integration of DBMS and GIS, and the major functions of the system include (i) exploring spatial distribution of point data, (ii) mapping hot-spot, (iii) clustering analysis of crime occurrence, and (iv) analyzing aggregated areal data. The process of design and implementation of this system is based on object-oriented methodologies. A web-based extension of the prototype using 3-tier architecture is currently under development.

• Journal of the Korean Geographical Society
• /
• v.36 no.3
• /
• pp.329-341
• /
• 2001

The purpose of this study focused on the distribution of crimes in Cheongju City. This study emphasized the characteristics of place and spatial pattern of crime in Central Business District(CBD). The crime core areas were delineated and explained through land-use based on fieldwork and GIS analysis For this aim. the police crime data of Cheongju Dongbu(east). Seobu(west) for 1998 were collected In which 3.909 indictable or similar offenses were reported. In this study, Included climes are murder. rape, robbery. arson, theft, burglary, assault and vandalism. Because theme crimes are related with site-specific crime. As a result. land-use patterns are often related to specific type of offenses. The climes in Cheongju City were concentrated in the CBD Most crimes were assaults and thefts Crime areas can be classified by the age of the offender Around Chungang and Pungmul Market in the CBD. the offender＇s ages were 30-50 dominantly Assaults and thefts were concentrated in Songan-gil(street). which is a place teen-ages and youngsters meet frequently The result of the buffering analysis with roads, explained 40% of crime within a 30m buffer area( including both sides) of a principal road The rest of the climes mainly occurred in the vicinity of narrow streets and alleys.

• Journal of Satellite, Information and Communications
• /
• v.11 no.1
• /
• pp.55-57
• /
• 2016

In this paper, we present an algorithm to determine the abnormal behavior through a CCTV-based behavioral recognition and a pattern of hand using ConvexHull. In the existing way that using CCTV for crime prevention, facial recognition is mainly used. Facial recognition is the way that compares the faces that are seen on the screen and faces of criminals for determining how dangerous targets are, however, this way is hard to predict future criminal behavior. Therefore, to predict more various situations, abnormal behaviours are determined with targets' incline of arms, legs and bodys and patterns of hand movements. it can forecast crimes when an acting has been getting within common normality out, comparing whose acting patterns with the crime patterns.

• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.1 s.39
• /
• pp.3-7
• /
• 2007

To deal with the modern intellectual criminal acts, various efforts have been tried. Especially, it is not difficult to watch the recent activities to analyze the criminal characteristics spatially using computing and GIS technology. In this study, the spatial features and patterns of crime are investigated. Based on the real criminal record in Seoul Korea, the crime is reconstituted with four major categories such as assault, larceny, robbery, and rape. Then the variables are derived based on the theory of criminology. The kernal density analysis is performed to investigate the criminal distribution, and the correlation between the main criminal causes and the criminal outbreak is examined by buffering analysis. In addition, the land price and land usages are correlated with social-economic factors of criminal patterns to produce the final crime map.