• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.13-20
• /
• 2022

This study is to develop a named entity recognition model specialized in criminal investigation domains using deep learning techniques. Through this study, we propose a system that can contribute to analysis of crime for prevention and investigation using data analysis techniques in the future by automatically extracting and categorizing crime-related information from text-based data such as criminal judgments and investigation documents. For this study, the criminal investigation domain text was collected and the required entity name was newly defined from the perspective of criminal analysis. In addition, the proposed model applying KoELECTRA, a pre-trained language model that has recently shown high performance in natural language processing, shows performance of micro average(referred to as micro avg) F1-score 98% and macro average(referred to as macro avg) F1-score 95% in 9 main categories of crime domain NER experiment data, and micro avg F1-score 98% and macro avg F1-score 62% in 56 sub categories. The proposed model is analyzed from the perspective of future improvement and utilization.

• Korean Security Journal
• /
• no.37
• /
• pp.83-108
• /
• 2013

Since the end of the Cold War and rapid globalization and technical developments, terrorist groups actively involved in criminal activities. Also criminal entrepreneurs became a major financial revenue for these terrorists groups. This newly patternized activities among terrorist groups is now called as Crime-Terror Nexus" indicating the changing nature of terrorism, which means two traditionally separate phenomena, crime and terrorism, became more similar. This new pattern of terrorism is considered to create synergy for the criminal organizations and terrorist groups, scholars believe that it would become a significant threat to the security of world community in the near future. Although the phenomenon of this crime-terror nexus is significant and imminent threats, there is lack of studies investigation this new evolution of terrorism with empirical data. Moreover there is literally no studies exploring factors relevant to the Crime-Terror Nexus. Therefore, this current study aims to conduct explorative investigation of factors affecting the "Crime-Terror Nexus" with a world terrorism data, MAROB(the Minorities at Risk Organizational Behavior), which is developed by START and Minority at Risk project and contains information terrorist groups in Middle-East and Africa region. Considering the significance of this new terrorism patterns and the challenging nature of conducting empirical studies on this topic, this study has great contribution on the development in the field of criminal justice as well as terrorism.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.8
• /
• pp.49-55
• /
• 2016

In this study, we proposed the social map system prototype for intelligent crime prevention. For developing the social map system prototype, functional requirements were derived through the analysis of related cases and preceding studies. Derived requirements are providing a variety of map-based safety information, using crowdsourcing data such as SNS, connecting to intelligent CCTV. To satisfy these requirements, the prototype is developed with four main menus: the integrated search menu including social media data, the safety map menu providing a variety of safety and danger information, the community map menu to collect safety and danger information from users, and the CCTV menu providing the link to intelligent CCTV. The social map for intelligent crime prevention in this study is expected to greatly enhance the safety of local community with the provision of prompt response to risk information, safe route, etc. through actual service and user participation.

• Electronics and Telecommunications Trends
• /
• v.35 no.2
• /
• pp.17-27
• /
• 2020

Predicting where and when a crime may occur in an area of interest is one of many strategies of predictive policing. Multidimensional analysis, including CCTV, can overcome the limitations of hotspot prediction, especially of violent crimes. In order to identify the precursors of a crime, it is necessary to analyze dynamic data such as attributes and activities of people, social information, environmental information, traffic flows, and weather. These parameters can be recognized by CCTV. In addition, it provides accurate analysis of the circumstances of a crime in a dynamic situation, calculates the risk, and predicts the probability of a crime occurring in the near future. Additionally, it provides ways to gather historical criminal datasets, including sensitive personal information.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.5
• /
• pp.147-156
• /
• 2013

Each field of modern society, industrialization and the development of science and technology are rapidly changing. However, as a side effect of rapid social change has caused various problems. Crime of the side effects of rapid social change is a big problem. In this paper, a model for predicting crime and Markov chains applied to the crime, predictive modeling is proposed. Markov chain modeling of the existing one with the overall status of the case determined the probability of predicting the future, but this paper predict the events to increase the probability of occurrence probability of the prediction and the recent state of the entire state was divided by the probability of the prediction. And the whole state and the probability of the prediction and the recent state by applying the average of the prediction probability and the probability of the prediction model were implemented. Data was applied to the incidence of crime. As a result, the entire state applies only when the probability of the prediction than the entire state and the last state is calculated by dividing the probability value. And that means when applied to predict the probability, close to the crime was concluded that prediction.

• Journal of Integrative Natural Science
• /
• v.17 no.3
• /
• pp.75-86
• /
• 2024

Surveys are an important data collection method for national statistics in Korea. As of July 22, 2024, based on data provided by the MDIS of Statistics Korea, approximately 92% of national statistics are compiled using the survey method, and about 85% of these rely primarily on face-to-face interviews for data collection. However, with the increase in single-person households, the nonresponse rate of surveys has been rising each year. This study examined the behaviors of respondents across different survey modes used in the 2020 Korean Crime Victim Survey, whose raw data about survey response modes is available for public use on the MDIS website in Statistics Korea. The results show that, overall, the younger the age group, the higher the proportion of self-administered responses, with this proportion being higher for female than male except over 60 years old. Notably, the 20s age group has a significantly higher percentage of self-administered (TAPI) responses for both male and female. Furthermore, the response using tablets generally has a higher proportion compared to the response using paper across all age groups except for females in their teens, regardless of whether the survey is interviewer-administered or self-administered.

• Journal of the Korean association of regional geographers
• /
• v.21 no.4
• /
• pp.739-750
• /
• 2015

This study aims to investigate the possibility of crime prevention through CCTV by analyzing the appropriateness of the CCTV location, whether it is installed in the hotspot of crime-prone areas, and exploring the crime prevention effect and transition effect. The real crime and CCTV locations of case city were converted into the spatial data by using GIS. The data was analyzed by hotspot analysis and weighted displacement quotient (WDQ). The results demonstrated that there was no significant effect in the installation of CCTV on crime prevention. This indicates that CCTV should be installed and managed in a more scientific way reflecting local crime situations. In terms of CCTV, the methods of spatial analysis such as GIS, which can evaluate the installation effect, and the methods of economic analysis like cost-benefit analysis should be developed. In addition, these methods should be distributed to local governments across the nation for the appropriate installation of CCTV and operation. This study intended to find a design guideline of the optimum CCTV installation. In this regard, this study is meaningful in that it will contribute to the creation of a safe city.

• International journal of advanced smart convergence
• /
• v.13 no.3
• /
• pp.150-155
• /
• 2024

Genomic data plays a transformative role in medicine, biology, and forensic science, offering insights that drive advancements in clinical diagnosis, personalized medicine, and crime scene investigation. Despite its potential, the integration and analysis of diverse genomic datasets remain challenging due to compatibility issues and the specialized nature of existing tools. This paper presents the GenomeSync system, designed to overcome these limitations by utilizing the Hadoop framework for large-scale data handling and integration. GenomeSync enhances data accessibility and analysis through SQL-based search capabilities and machine learning techniques, facilitating the identification of genetic traits and the resolution of forensic cases. By pre-processing DNA profiles from crime scenes, the system calculates similarity scores to identify and aggregate related genomic data, enabling accurate prediction models and personalized treatment recommendations. GenomeSync offers greater flexibility and scalability, supporting complex analytical needs across industries. Its robust cloud-based infrastructure ensures data integrity and high performance, positioning GenomeSync as a crucial tool for reliable, data-driven decision-making in the genomic era.

• 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.