• 융합정보논문지
• /
• 제7권1호
• /
• pp.35-42
• /
• 2017

본 논문에서는 정보보안 담당자의 분석 업무 부하를 줄이고, 신속한 정보유출 감지를 위해 로그 데이터를 이용한 통합모니터링 관리시스템을 구현을 제안한다. 이를 위해 개별 보안시스템(MSSQL)에서 발생하는 대용량의 로그 데이터를 통합모니터링 관리시스템(ORACLE)으로 전송하는 이(異)기종 DBMS간의 전송 모듈을 개발하고, 전송된 로그 데이터를 일자별, 개인별로 수치화하는 방법에 대해 연구하고, 수치화된 데이터를 이용해 정보유출 징후감지 시 악의적인 사용자에 대한 검사와 조치 방법에 대해 연구했다.

• 경영정보학연구
• /
• 제4권1호
• /
• pp.47-67
• /
• 2002

1990년대 중반 이후 기업들은 인터넷상에서 사용자의 행동에 대한 관심이 높아짐에 따라, 인터넷상에서 사용자의 웹 사이트 클릭 정보가 남아 있는 웹 로그파일에 대한 관심 역시 높아지고 있다. 웹 로그파일에는 사용자 IP, 사용시간, 방문한 주소, 참조주소, 쿠키 파일 등 다양한 정보가 남기 때문에 이것을 이용하면 사용자의 웹 사이트 행위를 구체적으로 분석할 수 있다. 또한, 특정한 유형의 사용자와 관련된 웹 사이트를 찾아 효과적인 마케팅 전략을 수립할 수도 있다. 본 연구에서는 SPSS사의 데이터마이닝 도구인 클레멘타인을 이용하여 웹 마이닝을 할 수 있는 방법론을 소개하고, 실제 인터넷 허브 사이트의 로그화일을 대상으로 분석을 수행하였다.

• Communications for Statistical Applications and Methods
• /
• 제11권1호
• /
• pp.93-106
• /
• 2004

Recently, many data of various types is gained with development of computer in many fields. Especially, web log data generating in web site furnish beneficial information on an organization. The enterprise's destiny is swayed by according as how these information gaining from the web site utilize. In this paper, for the purpose of obtaining useful information, we present a tool is called WebBizi for web log analysis. This will be helpful to enterprise working the web site.

• Communications for Statistical Applications and Methods
• /
• 제19권4호
• /
• pp.559-569
• /
• 2012

Compositional data consist of compositions that are non-negative vectors of proportions with the unit-sum constraint. In disciplines such as petrology and archaeometry, it is fundamental to statistically analyze this type of data. Aitchison (1983) introduced a log-contrast principal component analysis that involves logratio transformed data, as a dimension-reduction technique to understand and interpret the structure of compositional data. However, the analysis is not usable when zero values are present in the data. In this paper, we introduce 4 possible methods to reduce the dimension of compositional data with zero values. Two real data sets are analyzed using the methods and the obtained results are compared.

• Water Engineering Research
• /
• 제2권1호
• /
• pp.1-10
• /
• 2001

The frequency analyses for the precipitation data in Korea were performed. We used daily maximum series, monthly maximum series, and annual series. For nonparametric frequency analyses, variable kernel estimators were used. Nonparametric methods do not require assumptions about the underlying populations from which the data are obtained. Therefore, they are better suited for multimodal distributions with the advantage of not requiring a distributional assumption. In order to compare their performance with parametric distributions, we considered several probability density functions. They are Gamma, Gumbel, Log-normal, Log-Pearson type III, Exponential, Generalized logistic, Generalized Pareto, and Wakeby distributions. The variable kernel estimates are comparable and are in the middle of the range of the parametric estimates. The variable kernel estimates show a very small probability in extrapolation beyond the largest observed data in the sample. However, the log-variable kernel estimates remedied these defects with the log-transformed data.

• 한국CDE학회논문집
• /
• 제17권2호
• /
• pp.97-110
• /
• 2012

High performance sensors and modern data logging technology with real-time telemetry facilitate system fault diagnosis in a very precise manner. Fault detection, isolation and identification in fault diagnosis systems are typical steps to analyze the root cause of failures. This systematic failure analysis provides not only useful clues to rectify the abnormal behaviors of a system, but also key information to redesign the current system for retrofit. The main barriers to effective failure analysis are: (i) the gathered data (event) logs are too large in general, and further (ii) they usually contain noise and redundant data that make precise analysis difficult. This paper therefore applies suitable pre-processing techniques to data reduction and feature extraction, and then converts the reduced data log into a new format of event sequence information. Finally the event sequence information is decoded to investigate the correlation between specific event patterns and various system faults. The efficiency of the developed pre-filtering procedure is examined with a terminal box data log of a marine diesel engine.

• Communications for Statistical Applications and Methods
• /
• 제8권3호
• /
• pp.831-840
• /
• 2001

In this study, We introduce the process of web usage mining, which has lately attracted considerable attention with the fast diffusion of world wide web, and explain the web log data, which Is the main subject of web usage mining. Also, we illustrate some real examples of analysis for web log data and look into practical application of web usage mining for eCRM.

• 정보과학회 논문지
• /
• 제45권3호
• /
• pp.234-241
• /
• 2018

데이터 분석 영역에 있어 게이머의 유형을 분류하거나 게이머의 특성을 분석하는 연구는 데이터 분석 연구자들이 많은 관심을 가지는 분야 중 하나이다. 과거부터 현재까지 게이머 유형화나 게이머 분석에 대해 많은 연구가 진행되어 왔다. 하지만, 대부분의 연구는 설문조사나 생체신호를 이용하고 있는데, 이는 많은 데이터를 얻기 힘들어 실용적이지 못한다. 또는 게임로그를 이용하더라도 단순히 통계적인 수치만을 추출하여 게이머를 유형화하고 분석하고 있어 게이머의 심리분석에 어려움이 있다. 하지만 기본적인 게임 로그로부터 게이머의 인지심리정보를 추출할 수 있다면, 게이머 분석을 보다 직관적이고 손쉽게 할 수 있다. 본 논문에서는 모바일 Role Playing Game(RPG) 게임인 크레이지 드래곤의 게임로그를 이용하여 게이머의 행동과 심리정보를 나타내는 8개의 인지심리속성을 추출하였다. 그 후, 이를 기반으로 게이머의 유형을 분류하였으며, 각 유형별 특징을 추출한 인지심리속성으로 분석하였다. 그 결과, 대부분의 게이머가 1~2가지 유형과 높은 연관성을 가지고 있는 것으로 확인되었다.

• 대한약학회:학술대회논문집
• /
• 대한약학회 2003년도 Proceedings of the Convention of the Pharmaceutical Society of Korea Vol.1
• /
• pp.117.2-118
• /
• 2003

Sample size calculations plays an important role in a bioequivalence trials and is determined by considering power under the alternative hypothesis. The regulatory guideline recommends that $2{\times}2$ crossover design is conducted and raw data is log-transformed for statistical analysis. In this paper, we discuss the sample size calculation in $2{\times}2$ crossover design with the log-transformed data.

• 산업경영시스템학회지
• /
• 제42권4호
• /
• pp.126-134
• /
• 2019

Nowadays, since there are so many big data available everywhere, those big data can be used to find useful information to improve design and operation by using various analysis methods such as data mining. Especially if we have event log data that has execution history data of an organization such as case_id, event_time, event (activity), performer, etc., then we can apply process mining to discover the main process model in the organization. Once we can find the main process from process mining, we can utilize it to improve current working environment. In this paper we developed a new method to find a final diagnosis of a patient, who needs several procedures (medical test and examination) to diagnose disease of the patient by using process mining approach. Some patients can be diagnosed by only one procedure, but there are certainly some patients who are very difficult to diagnose and need to take several procedures to find exact disease name. We used 2 million procedure log data and there are 397 thousands patients who took 2 and more procedures to find a final disease. These multi-procedure patients are not frequent case, but it is very critical to prevent wrong diagnosis. From those multi-procedure taken patients, 4 procedures were discovered to be a main process model in the hospital. Using this main process model, we can understand the sequence of procedures in the hospital and furthermore the relationship between diagnosis and corresponding procedures.