• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.481-483
• /
• 2004

NIDS(Network Intrusion Detection System)는 공격 탐지 과정에서 대량의 로그가 발생하게 되는데 일반적인 침입탐지 시스템에서 탐지되어 하루에 남는 로그만으로도 시스템에 막대한 양을 차지한다 이러한 문제점은 관리자에게 많은 부담을 줄뿐만 아니라 그렇게 남겨진 로그에는 오탐율(False Positive) 비율이 높기 때문에 관리자가 실제로 위협적인 침입을 식별하고, 침입 행위에 대한 빠른 대응을 어렵게 만든다. 그러므로 NIDS와 특정 호스트가 가지고 있는 보안상 취약한 부분을 비교하여 판단할 수 있는 침입탐지시스템을 선택, 운용하는 것은 관리측면이나 대응측면에서 매우 중요한 일이라고 할 수 있다. 본 논문에서는 NIDS와 해당 호스트 취약점 정보를 이용해 작성된 데이터베이스(HVIDB : Host Vulnerability Information Database)를 이용하여 호스트의 취약성에 관한 로그만을 최종 경고해줌으로써 오탐율의 양을 감소시키고 호스트 보안성의 향상과 관리자가 로그분석 등의 IDS 업무를 효과적으로 할 수 있는 모델을 제시한다.

• The Korean Journal of Applied Statistics
• /
• v.13 no.1
• /
• pp.197-206
• /
• 2000

For estimating missing cells in contingency table, we suggest an iterative method which extends IPF (Iterative Proportional Fitting) method. The suggested m~thod is not restricted by the number and the location of missing cells, and does not distort the given quasi-independency.

• Journal of the Korean Society for Library and Information Science
• /
• v.45 no.1
• /
• pp.377-393
• /
• 2011

This study aims to investigate trends of internet searching behavior of users of NAVER, a major Korean search portal. In particular, this study analyzed trends of query submission behaviors, behaviors related to typos, multimedia searching behaviors, and click behaviors. In conducting this study, query logs and click logs of unified search service were analyzed. The results of this study show that there were little changes in the topic and length of queries, the pattern of typos, and multimedia seeking behavior over a year's period. However, click counts of documents have gradually increased over time. The results of this study can be implemented to increase the portal's effective development of internet contents and searching algorithms.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.35 no.2
• /
• pp.137-145
• /
• 1990

Six commercial rice varieties were cultivated at different locations in 1987 and 1988. Rice samples harvested from 8 to 20 locations for a variety each year were used to measure or observe grain appearance, amylose content and alkali digestibility, cooked rice texture using rheometer, gelatinization and viscosity of rice flour using amylograph, and eating Quality of cooked rice by sensory evaluation. Relationship between Quality characteristics showing large locational variation were analized to approach the long-term objective, rice grain Quality standardization. Percent white-center and white-belly grain of the same variety showed great variation between locations, but did not affect on 1000-grain weight, amylose content and alkali digestibility, amylogram and rheogram characteristics, and eating Quality of cooked rice. Positive correlationship were obtained between maximum viscosity and break down, and maximum viscosity and alkali digestibility. Set back was correlated negatively with maximum viscosity, break down and alkali digestibility. Rice samples having significantly lower values of maximum viscosity and break down and higher set back value at the same time showed higher ADV and lower texture palatability index (TPI) and viscousness/hardness ratio (Vi/H), and lower sensory evaluation score of cooked rice compared with those of rices having typically higher values of maximum viscosity and break down and lower set back value. When TPI, Vi/H and overall sensory eating score of cooked rices measured were divided into three categories, high, medium and low using deviation from locational mean value of a variety, many of rice samples having high TPI or high Vi/H showed medium or high in overall sensory eating score of cooked rice.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.761-764
• /
• 2020

본 논문에서는 라이프로그 데이터를 기반으로 한 행동인식 결과로부터 일상생활의 활동유형을 분석하는 기술에 대해 제안한다. 실제 일상생활 중에 수집한 가속도 센서 데이터만을 이용하여 분석한 행동인식 결과를 정적-동적 행동으로 분류된 특징 벡터로 나타내었고, 이를 클러스터링하여 6개의 대표 활동유형으로 분류하였다. 50명의 사용자 데이터를 분석하여 정적-동적 활동의 비율에 따른 활동유형을 분류함으로써 실제 라이프로그 데이터로부터 일상생활 활동유형을 확인하였다.

• 한국IT서비스학회:학술대회논문집
• /
• 2009.11a
• /
• pp.306-309
• /
• 2009

본 논문에서는 업무맞춤메뉴를 설계하여 기존의 연구지원포털에 구현하였고 사용로그를 분석하여 맞춤메뉴 사용비율과 설정유형의 2가지 측면에서 효과를 평가하였다. 사용비율은 연구지원포털의 트리구조메뉴 대비 업무맞춤메뉴의 사용횟수를 비교한 것인데 트리구조메뉴의 메뉴항목수 대비 업무맞춤메뉴의 항목수는 10%에 불과하지만 업무맞춤 메뉴를 사용한 비율은 43%로서 업무맞춤메뉴의 사용비율이 상대적으로 대단히 높은 것으로 나타났다. 설정유형으로는 (1) 사용자별로 사용빈도가 높은 메뉴를 종합하여 모아둔 유형, (2) 담당업무에 자주 사용하는 메뉴를 종합해서 모아둔 유형, (3) 동일업무를 자주 반복하다 보면 메뉴사용순서가 자연스럽게 정해지므로 사용순서 기반으로 메뉴를 설정한 유형의 3종류를 식별할 수 있었다. 이것은 사용자들이 자신의 필요성에 맞추어 적절하게 맞춤메뉴를 설정사용하고 있다는 것을 보여주는 것으로 해석된다. 분석결과로부터 사용편의성 측면에서 업무맞춤메뉴의 도입효과가 뛰어나고 사용자들의 자발적인 설정사용을 확인할 수 있었다. 또한 사용빈도가 낮은 메뉴항목까지 맞춤메뉴화 할 필요는 없으므로 트리구조메뉴와 병행하여 맞춤메뉴를 도입하는 것이 바람직하다는 점도 알게 되었다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1131-1141
• /
• 2015

In this paper, we proposed a new approach of machine learning based method for detecting game-bots from normal players in MMORPG by inspecting the player's action log data especially in-game money increasing/decreasing event log data. DBSCAN (Density Based Spatial Clustering of Applications with Noise), an one of density based clustering algorithms, is used to extract the attributes of spatial characteristics of each players such as a number of clusters, a ratio of core points, member points and noise points. Most of all, even game-bot developers know principles of this detection system, they cannot avoid the system because moving a wide area to hunt the monster is very inefficient and unproductive. As the result, game-bots show definite differences from normal players in spatial characteristics such as very low ratio, less than 5%, of noise points while normal player's ratio of noise points is high. In experiments on real action log data of MMORPG, our game-bot detection system shows a good performance with high game-bot detection accuracy.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.257-269
• /
• 2012

Global crisis expedites the change in the environment of industry and puts small size enterprises in danger of mass bankruptcy. Because of this, domestic small size enterprises is an urgent need of restructuring. Based on the small business data registered in the Credit Guarantee Fund, we estimated the survival probability in the context of the survival analysis. We also analyzed the survival time which are distinguished depending on the types of business in the small business. Financial variables were also conducted using COX regression analysis of small businesses by types of business. In terms of types of business wholesale and retail trade industry and services were relatively high in the survival probability than light, heavy, and the construction industries. Especially the construction industry showed the lowest survival probability. In addition, we found that construction industry, the bigger BIS (bank of international settlements capital ratio) and current ratio are, the smaller default-rate is. But the bigger borrowing bond is, the bigger default-rate is. In the light industry, the bigger BIS and ROA (return on assets) are, the smaller a default-rate is. In the wholesale and retail trade industry, the bigger bis and current ratio are, the smaller a default-rate is. In the heavy industry, the bigger BIS, ROA, current ratio are, the smaller default-rate is. Finally, in the services industry, the bigger current ratio is, the smaller a default-rate is.

• Journal of Korean Library and Information Science Society
• /
• v.42 no.1
• /
• pp.325-338
• /
• 2011

This study aims to investigate characteristics of most clicked documents of Naver's universal search service. In particular, this study analyzed characteristics of most clicked documents such as click ratio, collection distribution, and yearly distribution. Also, clicked documents were evaluated in terms of relevance, credibility, and currency. In conducting this study, query logs and click logs of unified search service were analyzed. The results of this study show that most clicks occurred in blog collection and average click concentration rate reached almost 50%. Also, the relevance and currency of most clicked documents were quite high, but credibility of these documents were on average level. The results of this study can be implemented to the portal's effective development of searching algorithm and interface.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.499-501
• /
• 2004

웹 로그, 바이오정보학 둥 여러 분야에서 다양한 형태의 결측치가 발생하여 학습 데이터를 희소하게 만든다. 결측치는 주로 전처리 과정에서 조건부 평균이나 나무 모형과 같은 기본적인 Imputation 방법을 이용하여 추정된 값에 의해 대체되기도 하고 일부는 제거되기도 한다. 특히, 결측치 비율이 매우 크게 되면 기존의 결측치 대체 방법의 정확도는 떨어진다. 또한 데이터의 결측치 비율이 증가할수록 사용 가능한 Imputation 방법들의 수는 극히 제한된다. 이러한 문제점을 해결하기 위하여 본 논문에서는 Vapnik의 Support Vector Regression을 데이터 전처리 과정에 알맞게 변형한 Support Vector Regression을 제안하여 이러한 문제점들을 해결하였다. 제안 방법을 통하여 결측치의 비율이 상당히 큰 희소 데이터의 전처리도 가능하게 되었다. UCI machine learning repository로부터 얻어진 데이터를 이용하여 제안 방법의 성능을 확인하였다.