• KIISE Transactions on Computing Practices
• /
• v.22 no.9
• /
• pp.455-460
• /
• 2016

Recently, with more severe types felonies such as robbery and sexual violence, the importance of crime prediction and prevention is emphasized. For accurate and prompt crime prediction and prevention, both a classification model of crime with high accuracy based on past criminal records and well-designed system interface are required. However previous studies on the analysis of crime factors have limitations in terms of accuracy due to the difficulty of data preprocessing. In addition, existing crime monitoring systems merely offer a vast amount of crime analysis results, thereby they fail to provide users with functions for more effective monitoring. In this paper, we propose a classification model for types of crime based on random-forest algorithms and system design factors for real-time crime prediction. From our experiments, we proved that our proposed classification model is superior to others that only use criminal records in terms of accuracy. Through the analysis of existing crime monitoring systems, we also designed and developed a system for real-time crime monitoring.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.99-105
• /
• 2023

In the 4th industrial revolution, the field of criminal justice is paying attention to Legaltech using artificial intelligence to provide efficient legal services. This paper attempted to create a crime prediction model that can apply Recurrent Neural Network(RNN) to increase the potential for using legal technology in the domestic criminal justice field. To this end, the crime process was divided into pre, during, and post stages based on the criminal facts described in the judgment, utilizing crime script analysis techniques. In addition, at each time point, the method and evidence of crime were classified into objects, actions, and environments based on the sentence composition elements and the 8 principles of investigation. The case summary analysis framework derived from this study can contribute to establishing situational crime prevention strategies because it is easy to identify typical patterns of specific crime methods. Furthermore, the results of this study can be used as a useful reference for research on generating crime situation prediction data based on RNN models in future follow-up studies.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.64-80
• /
• 2018

In Korea, citizens can only know general information about crime. Thus it is difficult to know how much they are exposed to crime. If the police can predict the crime risky area, it will be possible to cope with the crime efficiently even though insufficient police and enforcement resources. However, there is no prediction system in Korea and the related researches are very much poor. From these backgrounds, the final goal of this study is to develop an automated crime prediction system. However, for the first step, we build a big data set which consists of local real crime information and urban physical or non-physical data. Then, we developed a crime prediction model through machine learning method. Finally, we assumed several possible scenarios and calculated the probability of crime and visualized the results in a map so as to increase the people's understanding. Among the factors affecting the crime occurrence revealed in previous and case studies, data was processed in the form of a big data for machine learning: real crime information, weather information (temperature, rainfall, wind speed, humidity, sunshine, insolation, snowfall, cloud cover) and local information (average building coverage, average floor area ratio, average building height, number of buildings, average appraised land value, average area of residential building, average number of ground floor). Among the supervised machine learning algorithms, the decision tree model, the random forest model, and the SVM model, which are known to be powerful and accurate in various fields were utilized to construct crime prevention model. As a result, decision tree model with the lowest RMSE was selected as an optimal prediction model. Based on this model, several scenarios were set for theft and violence cases which are the most frequent in the case city J, and the probability of crime was estimated by $250{\times}250m$ grid. As a result, we could find that the high crime risky area is occurring in three patterns in case city J. The probability of crime was divided into three classes and visualized in map by $250{\times}250m$ grid. Finally, we could develop a crime prediction model using machine learning algorithm and visualized the crime risky areas in a map which can recalculate the model and visualize the result simultaneously as time and urban conditions change.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.5
• /
• pp.195-205
• /
• 2020

Recently, after the 4th industrial revolution era has arrived, technological advances started to develop and these changes have led to widespread use of data. Big data is often used for the safety of citizens, including the administration, safety and security of the country. In order to enhance the efficiency of maintaining such security, it is necessary to understand the installation status of CCTVs. By comparing the installation rate of CCTVs and crime rate in the area, we should analyze and improve the status of CCTV installation status, and crime rate in each area in order to increase the efficiency of security. Therefore, in this paper, big data analytic system based on public data is developed to collect data related to crime rate such as CCTV, female population, entertainment center, etc. and to reduce crime rate through efficient management and installation of CCTV.

• Journal of Cadastre & Land InformatiX
• /
• v.44 no.1
• /
• pp.139-150
• /
• 2014

Recently the violent crimes is the emerging social issue and the crime prevention is important policy both for maintenance of public order and the national welfare. To prevent these crimes with the geospatial data, we study the geospatial crime DB features, analytical method and linking method of current National Police Agency's crime system data. In this study, the Geospatial Information Open Platform(Vworld) was used to map the test site crime DB on the thematic map. We also researched the mesh-up thematic map and optimal location model of petrol car and CCTV.

• Journal of Korean Academy of Nursing
• /
• v.47 no.1
• /
• pp.39-48
• /
• 2017

Purpose: The purpose of this study was to verify the relationships among social support, resilience and post traumatic stress disorder (PTSD), and especially to identify factors influencing PTSD in police crime scene investigators. Methods: A cross-sectional design was used, with a convenience sample of 226 police crime scene investigators from 7 Metropolitan Police Agencies. Data were collected through self-report questionnaires during July and August, 2015. Data were analyzed using t-test, ${\chi}^2$-test, Fisher's exact test, and binary logistic regression analysis with SPSS/WIN 21.0 program. Results: The mean score for PTSD in police crime scene investigators was 13.69 .11 points. Of the crime scene investigators 181 (80.1%) were in the low-risk group and 45 (19.9%) in high-risk group. Social support (t=5.68, p<.001) and resilience (t=5.47, p<.001) were higher in the low-risk group compared to the high-risk group. Logistic regression analysis showed that resilience (OR=4.74, 95% CI: 1.57~14.35), and social support (OR=2.13, 95% CI: 1.23~3.69) are effect factors for PTSD low group. Conclusion: For effective improvement of PTSD in police crime scene investigators, intervention programs including social support and strategies to increase should be established.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1113-1122
• /
• 2020

Recently, as violent crimes of crime without reason (Korea : Do not ask), women and the elderly are getting serious. In the existing system, many CCTVs are installed, but it is difficult to prevent crime due to only follow-up measures after a crime occurs. This device prevents crime through this device for incidents in shaded areas and closed spaces such as apartments and buildings. To do this, we research this technology to develop products and software. It sends an alarm signal using communication technology to a specific place where you want to receive an event of an alarm or a CCTV device operated using image analysis big data technology and convergence sensor technology for a specific target of the behavior expected to be a crime or movement. Develop the device. This development device researches and develops this device and supplies low-cost devices to consumers, which is used as a device that predicts the occurrence of crime in advance, processes it as an alarm signal in real time, and transmits it, and constitutes a standalone device and a server. Will provide the device to be connected.

• Korean Security Journal
• /
• no.48
• /
• pp.147-176
• /
• 2016

Korean Peninsula is surrounded by ocean on three sides. Because of this geographical quality over 97% of export and import volumes are exchange by sea. Foreign ship and international passenger vessels carries foreign tourist and globalization and internationalization increases this trends. Leisure population grows with national income increase and interest of ocean. And accidents and incidents rates are also increases. Korea Coast Guard's jurisdiction area is 4.5 times bigger than our country. The length of coastline is 14,963km including islands. One patrol vessel is responsible for 24,068km and one coast guard substation is responsible for 94km. Efficient patrol activities can not be provided. This research focus on this problem. Analyze the status and trends of maritime crime and suggest efficient patrol activities. To deal with increasing maritime crime rate this study suggest to use geographical profile method which developed early 1900s in USA. This geographical profile analyse the spatial characteristic and mapping this result. With this result potential crime zone can be predicted. One of the result is hot spot management which gives data about habitual crime zone. In Korea National Police Agency adopt this method in 2008 and apply on patrol and crime prevention activity by analysis of different criteria. Korea National Police Agency analyse the crime rate with crime type, crime zone and potential crime zone, and hourly, regionally criteria. Korea Coast Guard need to adopt this method and apply on maritime to make maritime crime map, which shows type of crime with regional, periodical result. With this geographical profiling we can set a Criminal Point which shows the place where the crime often occurs. The Criminal Points are set with the data of numerous rates such as homicide, robbery, burglary, missing, collision which happened in ocean. Set this crime as the major crime and manage the data more thoroughly. I expect to enhance the reinforcement of marine crime using this Criminal Points. Because this points will give us efficient way to prevent the maritime crime by placing the patrol vessel where they needed most.

• International Journal of Advanced Culture Technology
• /
• v.9 no.2
• /
• pp.32-38
• /
• 2021

The purpose of this study is to examine the spatial characteristics of violent and burglary crimes in South Korea. Violent crimes and burglary crimes depend on a spatial setting with good conditions for their criminal purposes. This study defines population density, racial heterogeneity, types of houses, and density of commercial facilities as variables of place affecting crime in cities and counties. The study collects data from 229 cities in Korea to analyze the effect of spatial characteristics on crime. We conduct additional analyses to meet the statistical requisites of the spatial econometrics model using the open-source software R and GeoDa 1.12.1.129. From the analytical result, population density, racial heterogeneity, apartments, and commercial areas relate to crime occurrence. We suggest the implication of the theoretical and practical contributions to the relationship between place and crime.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.361-366
• /
• 2018

Previous studies on fear of crime used survey and interview to measure fear of crime. However, though these methods can measure fear of crime in past events, they cannot measure real time fear of crime. In this paper, we use EEG to measure fear of crime in real time. We measure and analyze the EEG of subjects watching the video and confirm the difference between three groups classified according to the degree of fear of crime. As a result, about two times more beta waves are shown when a group of subjects with a high degree of fear of crime watches the images of fear of crime and 1.5 times more beta waves are shown among the other groups. Although watching videos related to the crime increased the beta waves, the police video showed little increase in beta waves because the subjects can sense safety in the video even if it is related to crime.