• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.66-71
• /
• 2010

BPMS, ERP, SCM 등 프로세스 인식 정보시스템들이 널리 쓰이게 되면서 프로세스 마이닝에 대한 연구가 활발하게 이루어지고 있다. 프로세스 마이닝은 프로세스가 실행되는 동안 저장된 이벤트 로그로부터 정보를 추출하는 기법이다. 추출된 로그정보는 비즈니스 프로세스의 분석 및 재설계에 사용될 프로세스 모델을 생성하게 된다. 프로세스 마이닝 기법은 프로세스의 자동화 및 기업의 업무정보들을 관리하는 프로세스 기반 정보시스템의 정확성 및 효율성을 위한 중요한 부분을 차지하지만 현재까지의 연구는 생성된 이벤트 로그로부터 프로세스 모델을 재설계하는 프로세스 발견 기법 (Process Discovery Technique)을 적용한 부분에서만 활발히 진행되었다. 프로세스 마이닝은 프로세스 발견 기법 외에도 프로세스 적합성검사 기법 (Process Conformance Checking Technique) 및 프로세스 확장 기법 (Process Extension Technique)이 존재한다. 이들은 많은 프로세스 발견 기법에 대한 연구들이 진행되고 나서야 최근 프로세스 마이닝의 이슈로 떠오르고 있다. 본 논문에서는 프로세스 적합성 검사를 위해 수집된 이벤트 로그와 기존에 나와 있는 여러 가지 프로세스 발견 알고리즘을 통해 생성된 프로세스를 수치적으로 비교할 수 있는 두 가지 애트리뷰트를 제시하였다.

• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.354-357
• /
• 2015

최근 정보기술의 발달로 기업의 비즈니스 모델이 아날로그에서 디지털로 전환되고 있다. 기업에서는 다양한 서비스 제공을 위해 고객의 개인정보를 수집하고 있으며, 이러한 정보는 보안 위협의 대상이 되고 있다. 대다수 기업에서는 다양한 분야의 보안 솔루션이 구축 운용되고 있으나, 솔루션 개발사들의 서로 다른 보안 로그들로 인해 통합 분석에 어려움을 겪고 있으며 이로 인해 보안 모니터링 업무 효율이 낮아지는 문제점을 안고 있다. 본 연구에서는 시간적 연관성을 기반으로 통합 보안 로그를 분석 하고 시나리오화 하여 좀 더 빠르고 정확한 개인정보 유출의 이상징후를 탐지할 수 있는 방안을 제안한다.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.22 no.4
• /
• pp.5-19
• /
• 2011

The purpose of this study is to identify possible needs for system improvements and reflect them on the operation and development of the system as a result of the usability assessment of an information site in science and technology. For this study, a variety of data collection techniques, including search logs, interviews, and think-alouds, were used. The search log data was processed to quantify four evaluation aspects, which were the effectiveness, efficiency, satisfaction, and errors. The verbal data collected by think-alouds and post-interviews were used to identify possible needs of enhancement in a qualitative analysis. The comparison of the usability before and after the system enhancement revealed an increase of 15 points for effectiveness, 35 seconds decrease in efficiency, 5 points increase in satisfaction, and 1.1 errors decreased, implying an overall improvement of the usability of the current system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.859-868
• /
• 2018

Previous research related to recovering deleted data in database has been mainly based on transaction logs or detecting and recovering data using original source files by physical collection method. However there was a limit to apply if the transaction log does not exist in the server or it is not possible to collect the original source file because a database server owner does not permit stopping the database server because of their business loss or infringement at the scene. Therefore it is necessary to examine various collection methods and check the recoverability of the deleted data in order to handling the constraints of evidence collection situation. In this paper we have checked an experiment that the recoverability of deleted data in the original database source according to logical and physical collection methods on digital forensic investigation of Microsoft SQL Server database.

• The Korean Journal of Applied Statistics
• /
• v.32 no.3
• /
• pp.391-404
• /
• 2019

Customers' fixed characteristics have often been used to predict customer behavior. It has recently become possible to track customer web logs as customer activities move from offline to online. It has become possible to collect large amounts of web log data; however, the researchers only focused on organizing the log data or describing the technical characteristics. In this study, we predict the decision-making time until each customer makes the first reservation, using Airbnb customer data provided by the Kaggle website. This data set includes basic customer information such as gender, age, and web logs. We use various methodologies to find the optimal model and compare prediction errors for cases with web log data and without it. We consider six models such as Lasso, SVM, Random Forest, and XGBoost to explore the effectiveness of the web log data. As a result, we choose Random Forest as our optimal model with a misclassification rate of about 20%. In addition, we confirm that using web log data in our study doubles the prediction accuracy in predicting customer behavior compared to not using it.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.546-548
• /
• 2019

In recent days, vehicle safety technologies for supporting safe vehicle driving attract public attention. This paper proposes multi-log platform based vehicle safety system (MLPVSS) that analyzes multi-log data (i.e., log-data on human, object, and place) and supports vehicle safety. The MLPVSS gathers sensor data and image data on the human, object, and place, and then generates multi-log data that are context-aware data on the human, object, and place. The MLPVSS can detect, predict, and response vehicle dangers. The MLPVSS can contribute to reduce car accidents.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.6
• /
• pp.63-76
• /
• 2014

Recently the desired information has been recommended to many people in a number of ways using the smartphone. Though there are many applications for that purpose, but most applications does not consider the user's current situation. In order to automatically recommend the information considering the user's situation, it is necessary to predict the future behavior of the user from the records of the past behavior of the user. Therefore, in this paper, we propose a method that predicts the user's future behavior through association analysis based on the user's current behavior which is identified by applying the user's current situation data collected via a smartphone to the Bayesian network built from the user's life log. From the experiments and analysis for five students and five virtual workers, the usefulness of the proposed method is confirmed.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.383-391
• /
• 2010

A Lifelog management system provides users with services to store, manage, and search their life logs. This paper proposes a fully-automatic collecting method of real world social contacts and lifelog search engine using collected social contact information as keyword. Wireless short-distance network devices in mobile phones are used to detect social contacts of their users. Human-Bluetooth relationship matrix is built based on the frequency of a human-being and a Bluetooth device being observed at the same time. Results show that with 20% of social contact information out of full social contact information of the observation times used for calculation, 90% of human-Bluetooth relationship can be correctly acquired. A lifelog search-engine that takes human names as keyword is suggested which compares two vectors, a row of Human-Bluetooth matrix and a vector of Bluetooth list scanned while a lifelog was created, using vector information retrieval model. This search engine returns more lifelog than existing text-matching search engine and ranks the result unlike existing search-engine.

• Cartoon and Animation Studies
• /
• s.36
• /
• pp.553-572
• /
• 2014

In this paper, for the evaluation of the ease of a particular Web site (www.appbelt.net), insert the log tracking code for Google Analytics in a page of the Web site to collect behavioral data of visitor and has studied the improvement measures for the problems of the Web site, after the evaluation of the overall quality of the Web site through the evaluation of Coolcheck. These findings set the target value of the company's priority (importance) companies want to influence the direction of the business judgment are set up correctly, and the user's needs and behavior will be appropriate for the service seems to help improvement.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2003.12a
• /
• pp.179-184
• /
• 2003

컴퓨터를 통한 침입을 탐지하기 위해서 많은 연구들이 오용탐지 기법을 개발하였다. 최근에는 오용 탐지 기법을 개선하기 위해서 비정상행위 탐지 기법에 관련된 연구들이 진행중이다. 본 논문에서는 클러스터링 기법을 응용한 새로운 네트워크 비정상행위 탐지 기법을 제안한다. 이를 위해서 정상 행위를 다양한 각도에서 분석될 수 있도록 네트워크 로그로부터 여러 특징들을 추출하고 각 특징에 대해서 클러스터링 알고리즘을 이용하여 정상행위 패턴을 생성한다. 제안된 방법에서는 정상행위 패턴 즉 클러스터를 축약된 프로파일로 생성하는 방법을 제시하며 제안된 방법의 성능을 평가하기 위해서 DARPA에서 수집된 네트워크 로그를 이용하였다.