• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.05a
• /
• pp.619-622
• /
• 2002

IDS has been studied mainly in the field of the detection derision and collecting of audit data. The detection decision should decide whether successive behaviors are intrusions or not , the collecting of audit data needs ability that collects precisely data for intrusion decision. Artificial methods such as rule based system and neural network are recently introduced in order to solve this problem. However, these methods have simple host structures and defects that can't detect transformed intrusion patterns. So, we propose the method using data mining agent that can retrieve and estimate the patterns and retrieval of user's behavior in the distributed different hosts.

• 한국정보통신설비학회:학술대회논문집
• /
• 2004.08a
• /
• pp.298-301
• /
• 2004

KT는 무궁화 3호 위성을 이용한 양방향 위성 통신 사업을 추진하고 있으며, 지상망을 이용하기 어려운 지역에 정부/공공, 에너지 산업, 기업 단일망 등 다양한 산업 분야를 대상으로 초고속 네트워크를 제공하고 있다. 양방향 위성 통신 서비스는 36,000km 상공의 위성 중계기와 지상 간의 통신 지연을 극복하기 위한 첨단 기술로 운용되고 있으며, 중요 데이터에 대한 위성 통신 품질보증 기능을 제공한다. 본 논문에서는 위성망의 트래픽을 수집하고 데이터를 로깅하는 위성망 트래픽 수집 도구와 수집된 데이터를 마이닝을 통해 실시간 모니터링하고 통계 정보를 생성하는 위성망 패킷 데이터 분석 도구로 이루어진 위성망 패킷 데이터 분석 시스템에 대해 논한다. 위성망 패킷 데이터 분석 시스템은 데이터 송수신 정보를 모니터링 함으로써 실시간 위성 통신 상태를 점검하고, 전송 지연 및 실패 등의 위성 통신 오류 상태를 조기 진단하고 조치할 수 있는 위성망 품질 보증 서비스를 제공한다.

• Journal of Korea Game Society
• /
• v.15 no.4
• /
• pp.59-68
• /
• 2015

The progress in Information & Communication Technology enables data scientists to analyze big data for identifying peoples' daily lives and tacit preferences. A variety of industries already aware the potential usefulness of analyzing big data. However limited use of big data has been performed in game industry. In this research, we adopt data mining technique to analyze data gathered from a strategic simulation game. Decision Tree, Random Forest, Multi-class SVM, and Linear Regression techniques are used to find the most important variables to users' game levels. We provide practical guides for game design and usability based on the analyzed results.

• The Journal of Korean Association of Computer Education
• /
• v.11 no.1
• /
• pp.65-74
• /
• 2008

In this paper, we introduce an analysis system for answer dataset by using a data mining method. We analyze students' answer data collected from a test including multiple choice question items, and find associations between the items. Analysis of evaluation results based on our system will not only provide correct information on students' achievement levels but also provides a basis for modifying weaknesses of the evaluation procedures, question items, or teaching/learning procedures. Furthermore, it will enable us to improve the quality of question items for future use so that we can secure itemsets of high quality.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.17-20
• /
• 2011

축구 비디오를 분석하고 이를 팀 전략 수립에 활용하는 축구 비디오 분석관의 역할이 강조됨에 따라, 축구 비디오에서 주요 이벤트의 탐지와 같은 절차적 기능에서 부터 고수준의 해석 방법에 이르는 다양한 기능들이 요구된다. 본 논문에서는 축구 웹 캐스트에서 실시간으로 제공하는 텍스트 정보를 기반으로 메타데이터 키워드 매칭을 통하여 축구 경기의 다양한 속성들을 추출하고 텍스트 마이닝의 대표적 해석 기법인 연관규칙 마이닝을 사용함으로써 축구 경기의 전략 수립이 가능한 고수준의 해석 방법을 소개한다. 실제 2010년 월드컵의 스페인 경기를 중계한 웹 캐스트의 텍스트 정보를 대상으로 제안된 방법론의 타당성을 검증한다.

• 한국IT서비스학회:학술대회논문집
• /
• 2009.11a
• /
• pp.524-527
• /
• 2009

최근 감시, 상황판단, 정보전달에 있어서 비디오 영상의 사용이 점점 증가하고 있다. 그러나 비디오 영상에 나타나는 객체들의 비정상행위를 탐지하는 것은 사용자에게 의존한다. 따라서 사용자가 비정상 행위를 놓치기 쉽고, 상황에 대한 대처가 늦어진다는 문제가 발생한다. 이러한 점을 개선하기 위해 실시간 영상 마이닝 기법을 이용한 비정상행위 탐지법이 연구되었으나, 제약 조건이 심하고, 불필요하게 추적되는 데이터가 많아 효율이 떨어진다는 단점이 있다. 본 논문에서는 이러한 단점을 개선하여 3차원 환경에서의 객체의 추적에 대한 정확도를 높이고 일반적인 상황에서도 적용이 가능한 비디오 마이닝을 이용한 비정상 행위 탐지 기법을 제안한다.

• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.161-169
• /
• 2015

Realtime search words of typical portal sites appear every few seconds in descending order by search frequency in order to show issues increasing rapidly in interest. However, the characteristics of realtime search words reordering within too short a time cause problems that they go over the key issues of the day. This paper proposes a method for deriving a key issue through association analysis of realtime search words. The proposed method first makes scores of realtime search words depending on the ranking and the relative interest, and derives the top 10 search words through descriptive statistics for groups. Then, it extracts association rules depending on 'support' and 'confidence', and chooses the key issue based on the results as a graph visualizing them. The results of experiments show that the key issue through association rules is more meaningful than the first realtime search word.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.8 no.6
• /
• pp.544-550
• /
• 2015

The opinion mining technique which analogize significant information from SNS message is increasingly important because opinions communicated through SNS are increasing. This paper propose SEIAS(SNS Emotional Information Analysis Strategy) based on opinion mining that analogize emotional information from SNS setting a different weight according to position of antonym and adverb. Firstly, the proposed SEIAS constructs a emotion dictionary for opinion mining analysis, Secondly, it collects SNS data on real time, compare it with emotion dictionary and calculates opinion value of SNS data. Specially, it increases the precision of opinion analysis result compared to the existing SO-PMI because it sets up the different value according to the position of antonym and adverb when it calculates the opinion value of data.

• The KIPS Transactions:PartC
• /
• v.13C no.3 s.106
• /
• pp.295-302
• /
• 2006

An intrusion detection system writes a lot of alarms against attack behaviors in real time. These alarms contain not only actual attack alarms, but also false alarms that are mistakes made by the intrusion detection system. False alarms are the main reason that reduces the efficiency of the intrusion detection system, and we propose framework for false alarms analysis in the paper. Also, we apply an incremental data mining method for pattern analysis of false alarms increasing continuously. The framework consists of GUI, DB Manager, Alert Preprocessor, and False Alarm Analyzer. We analyze the false alarms increasingly through the experiment of the proposed framework and show that false alarms are reduced by applying the analyzed false alarm rules in the intrusion detection system.

• Korean Journal of Construction Engineering and Management
• /
• v.17 no.5
• /
• pp.89-96
• /
• 2016

Most data generated in construction projects is unstructured text data. Unstructured data analysis is very needed in order for effective analysis on large amounts of text-based documents, such as contracts, specifications, and RFI. This study analysed previously performed project's bid related documents (bidder inquiry) in overseas construction projects; as a results of the analysis frequent words in documents, association rules among the words, and various document topics were derived. This study suggests effective text analysis approach for massive documents with short time using text mining technique, and this approach is expected to extend the unstructured text data analysis in construction industry.