• International Journal of Advanced Culture Technology
• /
• v.10 no.4
• /
• pp.499-510
• /
• 2022

This study examines the reporting factors of crime against business in Korea and proposes a corresponding predictive model using machine learning. While many previous studies focused on the individual factors of theft victims, there is a lack of evidence on the reporting factors of crime against a business that serves the public good as opposed to those that protect private property. Therefore, we proposed a crime prevention model for the willingness factor of theft reporting in businesses. This study used data collected through the 2015 Commercial Crime Damage Survey conducted by the Korea Institute for Criminal Policy. It analyzed data from 834 businesses that had experienced theft during a 2016 crime investigation. The data showed a problem with unbalanced classes. To solve this problem, we jointly applied the Synthetic Minority Over Sampling Technique and the Tomek link techniques to the training data. Two prediction models were implemented. One was a statistical model using logistic regression and elastic net. The other involved a support vector machine model, tree-based machine learning models (e.g., random forest, extreme gradient boosting), and a stacking model. As a result, the features of theft price, invasion, and remedy, which are known to have significant effects on reporting theft offences, can be predicted as determinants of such offences in companies. Finally, we verified and compared the proposed predictive models using several popular metrics. Based on our evaluation of the importance of the features used in each model, we suggest a more accurate criterion for predicting var.

• Architectural research
• /
• v.24 no.1
• /
• pp.1-11
• /
• 2022

As the occurrence of a crime is dependent on different factors, their correlations are beyond the ordinary cognitive range. Owing to this limitation, systems face difficulty in correlating various factors, thereby requiring the assistance of artificial intelligence (AI) to overcome such limitations. Therefore, AI has become indispensable for crime prediction. Crimes can cause severe and irrevocable damage to a society. Recently, big data has been introduced for developing highly accurate models for crime prediction. Prediction of night crimes should be given significant consideration, because crimes primarily occur during nights, when the spatiotemporal characteristics become vulnerable to crimes. Many environmental factors that influence crime rate are applied for crime prediction, and their influence on crime rate may differ based on temporal characteristics and the nature of crime. This study aims to identify the environmental factors that influence sex and theft crimes occurring at night and proposes an artificial neural network (ANN) model to predict sex and theft crimes at night in random areas. The crime data of A district in Seoul for 12 years (2004-2015) was used, and environmental factors that influence sex and theft crimes were derived through multiple regression analysis. Two types of crime prediction models were developed: Type A using all environmental factors as input data; Type B with only the significant factors (obtained from regression analysis) as input data. The Type B model exhibited a greater accuracy than Type A, by 3.26 and 9.47 % higher for theft and sex crimes, respectively.

• Korean Security Journal
• /
• no.8
• /
• pp.361-377
• /
• 2004

This study is to examine the relations between the big five critical crime that consist of homicide, robbery, rape, theft, violence and the private security services. To achieve this objective, this research selected the subject of study, specially, 2002 status of the private security such as the number of companies and employees classified by areas along with the big five crime mentioned above classified by area. The research data is secondary data that is from '2003 Crime Analysis' of the Supreme Public Prosecutors' Office and 'The private Security Related Data' of the National Police Agency. The selected data were analyzed according to the variables by using SPSS 10.0 statistics software program. Each hypothesis was verified around the level of significance ${\alpha}$=.05 by using the statistical techniques, such as Descriptive Statistics, Correlation, Regression, etc. The following was the result of the study, First, the total number of the big five crime affects the number of the companies at significant level. Second, the number of the security companies can be explained by the each total number of the big five crime in the order of theft, robbery, violence, rape and murder. Third, the total number of the big five crime affects the number of the security employees at significant level. Forth the number of the security employees can be explained by the each total number of the big five crime in the order of theft, robbery, violence, rape and murder.

• Korean Security Journal
• /
• no.34
• /
• pp.313-336
• /
• 2013

The purpose of this study is to derive an optimal regression model for occurrences of major crimes on a security company's stock price through identifying precedence of the occurrences of major crimes on the security company's stock price, relationship between the occurrences of major crimes and the security company's stock price. Followings are the results of this study. First, the occurrences of murder crime, robbery crime, rape crime, theft crime move along the security company's monthly stock price simultaneously, and the occurrence of violence crime precedes 6 months to the security company's monthly stock price depending on the results of cross-correlation analysis of precedence of occurrences of major crimes, such as murder crime, robbery crime, rape crime, theft crime, violence crime on the security company's monthly stock price. Second, the explanation of the occurrences of robbery crime, rape crime, theft crime on the security company's monthly stock price is 61.7%($R^2$ = .617) excluding murder crime, violence crime depending on the results of multiple regression analysis(stepwise method) by putting the occurrences of major crimes, such as murder crime, robbery crime, rape crime, theft crime, violence crime into the security company's monthly stock price.

• Journal of forensic and investigative science
• /
• v.2 no.1
• /
• pp.23-31
• /
• 2007

Apartments are built in small countries to accommodate densely populated cities and maximize urbanization. Many apartment complexes have been built in recent reconstruction or redevelopment projects. An increase in crime has resulted due to residents living in a narrow space. Larceny is the most commonly reported crime in apartment complexes. Apartments can be classified as stairway, hallway, or plane surface. This study compares and analyzes the frequency of theft by apartment type to assist in creating a safer residential space. In America and England, scholars studied to make a safer residential space, and have applied the theory of 'the Defensible Space' and 'Crime Prevention Through Environmental Design(CPTED)' since 1970s. Korean apartment design now reflects CPTED in new apartment construction. In this study, 12 apartment complexes were selected in Changwon city to conduct analysis of theft in selected complexes. The study will cover housing invasion theft, motorcycle and car theft and snatching. The most frequency larceny is motorcycle and car theft, the second is housing invasion theft, and the least frequent is snatching. More residents' motorcycles and cars are damaged in a hallway style apartment. More frequently inhabitants have their possessions snatched on a stairway form. 1) When we build new apartment complexes, we must plan to improve territoriality and enhance a natural surveillance by reinforcing dwellers' relationship. Through planning we can prevention the larceny in apartments.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.1
• /
• pp.31-39
• /
• 2017

The goal of this study was to efficiently analyze the relationships of the number of thefts with related factors, considering the spatial patterns of theft crimes. Theft crime data for a 5-year period (2009-2013) were collected from Haeundae Police Station. A logarithmic transformation was performed to ensure an effective statistical analysis and the number of theft crimes was used as the dependent variable. Related factors were selected through a literature review and divided into social, environmental, and defensive factors. Seven factors, were selected as independent variables: the numbers of foreigners, aged persons, single households, companies, entertainment venues, community security centers, and CCTV (Closed-Circuit Television) systems. OLS (Ordinary Least Squares) and GWR (Geographically Weighted Regression) were used to analyze the relationship between the dependent variable and independent variables. In the GWR results, each independent variable had regression coefficients that differed by location over the study area. The GWR model calculated local values for, and could explain the relationships between, variables more efficiently than the OLS model. Additionally, the adjusted R square value of the GWR model was 10% higher than that of the OLS model, and the GWR model produced a AICc (Corrected Akaike Information Criterion) value that was lower by 230, as well as lower Moran's I values. From these results, it was concluded that the GWR model was more robust in explaining the relationship between the number of thefts and the factors related to theft crime.

• Journal of the Korean housing association
• /
• v.19 no.2
• /
• pp.73-82
• /
• 2008

The purpose of this paper is to analyze the correlation analysis between the experienced crime victimization rate and the evaluation indicator of residents' safety of outdoor spaces from crime in multi-family housing. Additionally this paper intend to analyze the correlation analysis between the residents' satisfaction about safety and the evaluation indicator of residents' safety of outdoor spaces. For that purpose, 9 Multi-Family Housing located in the metropolitan area were selected to perform a survey against 349 residents during May 26-29, 2006. The SPSS program was used and the level of satisfaction ranged from 1 to 5. Scale of 5 being most satisfied while 1 being most dissatisfied. The results of this study are the followings; 1) Most occurred crime were auto theft and damages, poster matter theft, housebreaking. 2) The crime rate is higher in outdoor than in indoor. 3) This study proved the correlation between the residents' satisfaction about housing safety and most indicators except the number of households etc. 4) By the results of the correlation coefficient it makes clear that the number of apartment building, the visibility of Green Space, the location of pedestrian etc. have relation with the residents' satisfaction about housing safety.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.1
• /
• pp.31-37
• /
• 2015

The recent long-term economic recession and business depression are constantly increasing the occurence of the five major crimes(murder, robbery, rape, theft, violence). When looking into the previously-analyzed characteristics of how the five major crimes are committed, this study understands that the crimes mostly occur in these crime-ridden areas of poor public order and security and, in order to decrease the crime rates of the crime-prone areas, any relevant fields have been emphasizing the application of CPTED. In the light of that, referring to CPTED surveillance factors and the current crime rate data, the study presented ways to help the relevant fields draw up a crime-prone area grade map. In particular, the security center among monitoring elements was visualized by dividing it into point patrol and directed patrol and by dividing it into 3 steps monitoring levels with CCTV and street lights. In addition, we checked the crime rate by zoning through crime statistics occurred in the research areas and established a crime status map. We estimated the weight through AHP analysis on the built monitoring elements and the zoning of the occurred areas, as a result of making a map vulnerable to crime by monitoring steps by overlapping each element, we were able to confirm that 60% of theft, 52% of violence and 33% of rape in the 1st grade area were reduced compared to the 1st step in monitoring Step 3.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.86-88
• /
• 2013

Theft is secretly steal things of others. And theft tell the person who secretly stealing, bandits, stealing one's things. In modern society, theft is one of the crimes that occur frequently in the elevator. In this paper, theft crime is extracted using a ${\chi}^2$ histogram of scene change detection method. Extracted images are submitted as evidence for the action on the merits the court.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.1
• /
• pp.57-81
• /
• 2019

An ontology is a complex structure dictionary that defines the relationship between terms and terms related to specific knowledge in a particular field. There have been attempts to construct various ontologies in Korea and abroad, but there has not been a case in which a large scale crime investigation record is constructed as an ontology and a service is implemented through the ontology. Therefore, this paper describes the process of constructing an ontology based on information extracted from instrusion theft field of unstructured data, a crime investigation document, and implementing an ontology-based search service and a crime spot recommendation service. In order to understand the performance of the search service, we have tested Top-K accuracy measurement, which is one of the accuracy measurement methods for event search, and obtained a maximum accuracy of 93.52% for the experimental data set. In addition, we have obtained a suitable clue field combination for the entire experimental data set, and we can calibrate the field location information in the database with the performance of F1-measure 76.19% Respectively.