• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.23-34
• /
• 2019

Recently, the crime that utilizes the digital platform is continuously increasing. About 140,000 cases occurred in 2015 and about 150,000 cases occurred in 2016. Therefore, it is considered that there is a limit handling those online crimes by old-fashioned investigation techniques. Investigators' manual online search and cognitive investigation methods those are broadly used today are not enough to proactively cope with rapid changing civil crimes. In addition, the characteristics of the content that is posted to unspecified users of social media makes investigations more difficult. This study suggests the site-based collection and the Open API among the content web collection methods considering the characteristics of the online media where the infringement crimes occur. Since illegal content is published and deleted quickly, and new words and alterations are generated quickly and variously, it is difficult to recognize them quickly by dictionary-based morphological analysis registered manually. In order to solve this problem, we propose a tokenizing method in the existing dictionary-based morphological analysis through WPM (Word Piece Model), which is a data preprocessing method for quick recognizing and responding to illegal contents posting online infringement crimes. In the analysis of data, the optimal precision is verified through the Vote-based ensemble method by utilizing a classification learning model based on supervised learning for the investigation of illegal contents. This study utilizes a sorting algorithm model centering on illegal multilevel business cases to proactively recognize crimes invading the public economy, and presents an empirical study to effectively deal with social data collection and content investigation.

• The Journal of the Korea Contents Association
• /
• v.16 no.10
• /
• pp.175-187
• /
• 2016

Protection of personal information has significant meaning in current information age. Information of crime victim is one of top in value in that divulgence of the information to perpetrators may threat safety of the victim or cause psychological demage as $2^{nd}$ harm if disclosed to public. Legal system protects the information with scattered statutes including Criminal Procedure Act. Existing studies have been limited to discussion of the single statute without integrated approach. Bearing necessity of the approach in mind, as issues of protection system this research proffers too broad subject of eligible inspection of case document, inactive practice of identity management cards and omission of personal information, and inappropriate punishment on the disclosure or divulgence. After reviewing systems of foreign jurisdictions to get useful implications, this paper suggests several measures with two separate aspect of legal provisions and protection practice.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.391-396
• /
• 2019

Researches for image processing have been actively progress due to the development of various hardware. For example, in order to prevent various types of crime by a vehicle, there is a method of detecting the location of a criminal vehicle using the existing CCTV in real time. However, certain types of systems and high-performance system requirements make it difficult to apply to existing equipment. In this paper proposes a search algorithm that construct a file database of Korean standard license plate information so that specific vehicles can be quickly searched using existing equipment. In order to evaluate the performance of the file database and the search algorithm proposed in this paper, we set up the search targets at various locations and the results showed that the search algorithm could always check the information by searching the vehicle within a certain time.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.477-481
• /
• 2018

본 논문은 범죄 수사 기록 문서로부터 추출한 정보를 트리플로 구성하여 특정 분야의 온톨로지를 구축하고, 더 나아가 온톨로지 기반의 검색 서비스를 구현하는 일련의 과정을 설명한다. 특히 비정형 데이터로 부터 얻어낸 정보를 통해 온톨로지를 구축하고, 이를 토대로 실제 사용할 수 있는 레벨의 서비스를 구현하는 것이 특징이다. 서비스의 성능을 확인하기 위하여 사건 검색에 대한 정확도 측정 방법 중 하나인 Top-K 방식의 정확도 측정 실험을 수행하였으며, 실험 결과 완전 일치 실험에서는 약 93.52%, 유사 필드 활용 실험에서는 약 88.91%의 결과를 얻어낼 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.144-146
• /
• 2017

사회적 약자로 여겨지는 여성과 아동을 대상으로 한 범죄들이 연신 화제가 되면서 이들의 안전을 위한 어플리케이션들의 출시가 늘고 있다. 2017년 현재 시중에 출시되어 있는 어플리케이션들은 '특정버튼 세 번 누르기', '해당 어플리케이션 실행시키기'와 같은 평범한 액션으로 사용자가 보호자에게 도움을 요청 할 수 있다. 하지만 본 프로젝트에서는 '낙하'라는 보다 더 간단한 액션으로 사용자가 빠른 도움 요청을 할 수 있는 시스템을 개발하였다. 블루투스 통신 모듈과 아두이노, 센서, 배터리를 사용하여 낙하를 감지할 수 있는 디바이스를 제작하였고 이와 통신할 수 있는 어플리케이션을 개발하여 디바이스의 낙하가 감지되면 문자 전송과 통화 연결기능을 수행할 수 있도록 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.319-321
• /
• 2019

최근 여성 1인 가구를 대상으로 주거침입 관련 범죄가 꾸준히 발생하고 있다. 이러한 범죄를 예방하기 위한 한 방법으로는 특정 구역, 위치를 감시하기 위한 목적으로 CCTV(Closed-circuit television)를 설치하는 방법이 있다. 하지만 일반적인 가정용 CCTV의 경우 사용자 커스터마이징이 제한되어 있다. 따라서 본 논문에서는 저비용의 커스터마이징이 가능한 양방향 통신 기반 침입자탐지 시스템을 제안한다.

• Proceedings of KOSOMES biannual meeting
• /
• 2008.05a
• /
• pp.33-42
• /
• 2008

The crimes and the vandalism committed by mental patients such as the burning of Syungremoon and Daegu's subway have become a social insecure factors. In the paper, the criminal status of mental patients is analyzed and the range of probabilities at sea investigated. The countermeasures to these crimes are proposed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.425-426
• /
• 2022

Many CCTVs are installed around the area for the purpose of preventing crime. In this case, it is necessary to sound an alarm when a specific situation occurs because many people cannot be watching CCTV. It is necessary to analyze the video data to determine what kind of behavior it is. In this study, we propose a scene change detection technique through histogram operation, paying attention to the change of the histogram due to a sudden movement.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.394-396
• /
• 2022

After COVID-19, hybrid stores operated as unmanned stores at specific times have spread, and theft crimes against these stores have also increased. In this paper, we propose an intelligent crime prevention system that fully utilizes existing shop devices to identify and respond to crimes occurring during the late night hours of unmanned shops in real time.

• Convergence Security Journal
• /
• v.15 no.5
• /
• pp.71-76
• /
• 2015

Financial Intelligence Unit Law doesn't include investigation on important cases that could influence the security and existence of the nation that are the core jobs of national intelligence agency. So the agency has a difficulty to investigate the international crime of North Korea and other security incidents. It is also difficult to catch an international crime organization working in Korea. It also produces problems such as difficulty in investigating the illegal leak of strategic materials and investigating people related to illegal funding to international terrorism. So it is urgently needed to revise Financial Intelligence Law as soon as possible. Foreign intelligence agencies use the information of financial intelligence unit in many different ways. National Security Agency of China and Australian Security Intelligence Organization freely use the information of financial intelligence unit based on their own laws and systems. Central Intelligence Agency and Federal Bureau of Investigation of USA and Secret Intelligence Service and Security Service of Britain request financial intelligence units to supply them with the information of financial intelligence unit. But the national intelligence agency of Korea isn't able to approach to FIU and can't share the FIU information with foreign intelligence agencies. To solve the problem, they should revise Financial Intelligence Unit Law so that national intelligence agency can receive or request information from Korean Financial Intelligence Unit.