• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.47-52
• /
• 1999

데이타 마이닝이란 축적된 방대한 양의 실제 데이타로부터 이전에는 알지 못했던, 숨겨진 임의의 규칙성들을 비전통적인 방식으로 발견해 내는 작업을 말한다. 많은 데이타로부터 무엇인가 흥미로운 경향이나 패턴을 발굴해 내는 것이 데이타 마이닝의 목적이다. 본 연구에서는 다양한 측정값으로 표현되는 \circled1 인지 유형 데이타와, \circled2 생리적 반응 특성 데이터가 \circled3 직관적 예측의 성과에 미치는 영향을 데이타 마이닝 기술을 이용하여 분석함으로써 존재하는 규칙적인 관련성을 탐사하였다. 현재까지 분석한 바로는 첫째, 분석적인 사람이 직관적인 사람보다 예측이 더 정확한 경향이 있었다. 둘째, 실험 전과 실험중 간의 뇌파증가율이 높거나 뇌파량이 적으면 분석적인 사람일 가능성이 많았다. 셋째, 분석적인 사람은 실험 전에 뇌파량이 적을수록 더 정확해지며, 직관적인 사람은 실험전에 뇌파량이 많을수록 더 정확해지는 것으로 관측되었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.342-344
• /
• 2023

클라우드 시장의 성장과 마이크로 서비스 접근식이 제기됨에 따라 IT인프라를 관리하기 위한 연구가 최근 활발히 이루어지고 있다. 하지만 고도화 및 분산된 환경에서 관찰 가능성 응용을 확보하기 어렵다는 문제점을 가지고 있다. 따라서 본 연구에서는 모니터링 시스템을 통한 데이터 분석 중 수집한 데이터의 분석이 난해하다는 문제를 해결하기 위한 방법을 제안한다. 제안된 방법은 NAB 데이터셋을 대상으로 STUMPY를 이용하여 데이터를 시각화하고, CNN을 이용하여 분류 작업을 수행한다. 분류를 수행한 데이터셋은 이상치 데이터와 이상 전조 데이터, 정상 데이터셋으로 분류하여 데이터셋을 구성한다. 구성한 학습 데이터셋에 대해 훈련을 마친 딥러닝 모델은 부하 테스트 환경에서 수집한 데이터에 대한 그래프 패턴을 분석하여 이상치 데이터와 이상 전조 데이터를 탐지한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.1139-1142
• /
• 2008

인터넷의 이용이 증가함에 따라 네트워크를 통한 다양한 공격 역시 증가 추세에 있다. 따라서 네트워크 이상징후를 사전에 탐지하고 상황에 따라 유연하게 대처할 수 있도록 하기 위한 연구가 절실하다. 본 연구는 은닉마코프모델을 이용해 트래픽에서 이상징후를 탐지하는 기법을 제안한다. 제안하는 기법은 시계열 예측 기법을 이용해 트래픽에서 징후를 추출한다. 징후추출 과정의 결과를 은닉마코프모델을 활용한 징후판단과정을 통해 네트워크 이상징후인지를 판단하고 결정한다. 일련의 과정을 perl로 구현하고, 실제 공격이 포함된 트래픽을 사용하여 검증한다. 하지만 결과가 확연히 증명되지는 않는데, 이는 학습과정의 부족과 실제에 가까운 트래픽의 사용으로 인해 나타나는 현상으로 연구의 본질을 흐리지는 않는다고 판단된다. 오히려 실제 상황을 가정했을 때 접근이나 적용을 판단함에 관리자의 의견을 반영할 수 있으므로 공격의 탐지와 판단에 유연성을 증대시킬 수 있다. 본 연구는 실시간 네트워크의 상황 파악이나 네트워크에서의 신종 공격 탐지 및 분류에 응용가능할 것으로 기대된다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.3
• /
• pp.11-19
• /
• 2010

In recent years, Korea has witnessed an increase to natural disasters such as landslides due to localized sudden and intensive rainfalls. Thus there have been researches on surface displacements to detect and monitor displacements in the areas prone to landslides by using high-precision and density numerical elevation data from LiDAR, which is an advanced 3D measuring equipment. However, the commercial software to process large-capacity LiDAR data, is expensive and difficult to be applied to specialized tasks such as analysis of landslide. In addition, there are no measures for many users to easily access diverse spatial information related to landslides and put it to intuitive uses. Thus this study developed an application program to analyze landslides by processing time series LiDAR data and intuitively serve many users with information about the topography and landslides of given areas. It analyzed the current state of landslides in the subject region through case study and proposed that 3D-based landslide and topography information can be served intuitively.

• Journal of the Korean Society for information Management
• /
• v.33 no.3
• /
• pp.263-285
• /
• 2016

Nowadays, Social Network Service (SNS), which has been in the spotlight as a way of communication, has become a most effective tool to improve easy of information use and accessibility for users. In this paper, we chose Twitter as the most representative SNS services because of automatic crawling and investigated tweet data gathered from domestic and foreign National Archives - NARA of U.S.A., TNA of U.K.. NAA of Australia, and National Archives of Korea. We also conducted information genres analysis and trend analysis by timeline. Information genres analysis shows how archives satisfied users' information needs as well as trends analysis of tweets helps to understand how users' interestedness was changed. Based on comparison results, we distilled four characteristics of National Archives and suggested vitalization ways for National Archives of Korea.

• Journal of the Korean Society for information Management
• /
• v.30 no.1
• /
• pp.285-302
• /
• 2013

This study identified topic shifts and patterns over time by analyzing an enormous amount of Twitter data whose characteristics are high accessibility and briefness. First, we extracted keywords for a certain product and used them for representing the topic network allows for intuitive understanding of keywords associated with topics by nodes and edges by co-word analysis. We conducted temporal analysis of term co-occurrence as well as topic modeling to examine the results of network analysis. In addition, the results of comparing topic shifts on Twitter with the corresponding retrieval results from newspapers confirm that Twitter makes immediate responses to news media and spreads the negative issues out quickly. Our findings may suggest that companies utilize the proposed technique to identify public's negative opinions as quickly as possible and to apply for the timely decision making and effective responses to their customers.

• Journal of KIISE:Databases
• /
• v.31 no.1
• /
• pp.23-29
• /
• 2004

In this paper, we propose a search method for time sequences which supports the normalized distance as a similarity measure. In many applications where the shape of the time sequence is a major consideration, the normalized distance is a more suitable similarity measure than the simple Lp distance. To support normalized distance queries, most of the previous work has the preprocessing step for vertical shifting which normalizes each sequence by its mean. The proposed method is motivated by the property of sequence for feature extraction. That is, the variation between two adjacent elements of a time sequence is invariant under vertical shifting. The extracted feature is indexed by the spatial access method such as R-tree. The proposed method can match time series of similar shape without vertical shifting and guarantees no false dismissals. The experiments are performed on real data(stock price movement) to verify the performance of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.8
• /
• pp.708-715
• /
• 2014

In this paper, we suggest a method of realtime confidence interval estimation to detect abnormal states of sensor data. For realtime confidence interval estimation, the mean square errors of the exponential smoothing method and moving average method, two of the time series analysis method, where compared, and the moving average method with less errors was applied. When the sensor data passes the bounds of the confidence interval estimation, the administrator is notified through alarming. As the suggested method is for realtime anomaly detection in a ship, an Android terminal was adopted for better communication between the wireless sensor network and users. For safe navigation, an administrator can make decisions promptly and accurately upon emergency situation in a ship by referring to the anomaly detection information through realtime confidence interval estimation.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2011.04a
• /
• pp.531-538
• /
• 2011

To ensure the structural integrity of membrane type LNG tank, the rational assessment of impact pressure and structural responses due to sloshing should be preceded. The sloshing impact pressures acting on the insulation system of LNG tank are typical irregular loads and the structural responses caused by them also very complex behaviors including fluid structure interaction. So it is not easy to estimate them accurately and huge time consuming process would be necessary. In this research, a simplified method to analyze the dynamic structural responses of LNG tank insulation system under pressure time histories obtained by sloshing model test or numerical analysis was proposed. This technique basically based on the concept of linear combination of the triangular response functions which are obtained by the transient response analysis under the unit triangular impact pressure acting on structures in time domain. The validity of suggested method was verified through the example calculations and applied to the structural analysis of real Mark III type insulation system using the sloshing impact pressure time histories obtained by model test.

• Journal of Korea Multimedia Society
• /
• v.3 no.2
• /
• pp.201-208
• /
• 2000

In this paper We describe an algorithm which is devised for 4he partition o# the input space and the generation of fuzzy rules by the fuzzy entropy and tested with the time series prediction problem using Mackey-Glass chaotic time series. This method divides the input space into several fuzzy regions and assigns a degree of each of the generated rules for the partitioned subspaces from the given data using the Shannon function and fuzzy entropy function generating the optimal knowledge base without the irrelevant rules. In this scheme the basic idea of the fuzzy neural network is to realize the fuzzy rules base and the process of reasoning by neural network and to make the corresponding parameters of the fuzzy control rules be adapted by the steepest descent algorithm. The Proposed algorithm has been naturally derived by means of the synergistic combination of the approximative approach and the descriptive approach. Each output of the rule's consequences has expressed with its connection weights in order to minimize the system parameters and reduce its complexities.