• Geophysics and Geophysical Exploration
• /
• v.1 no.2
• /
• pp.92-100
• /
• 1998

Array CSAMT surveys were conducted in two areas where it was not easy to identify the presence of faults only with geological survey because of thick overburden. The purpose of these surveys were to locate the faults and to delineate the deep resistivity structures around the faults. The steep dip lineaments having high contrast in resistivity laterally and the low resistive zones having some width in the resistivity sections were interpreted as faults and fracture zones associated with faults, respectively, The good applicability of array CSAMT to the investigation of fault was recognized owing to the agreement between the interpretation results of array CSAMT and the conclusive evidences collected by the following geological survey. The evidences includes the recent exposure of fault and the trajectory of fault evidences of the survey line. A comparison of the applicabilities of array CSAMT method and the resistivity method using dipole-dipole array was presented with the results of both methods along a same traverse line.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.31 no.4
• /
• pp.19-27
• /
• 2023

In this study, a total of 2,584 domestic research papers with the keywords "Aviation Safety" and "Aviation Accidents" were subjected to Text Mining analysis. Various text mining techniques, including keyword frequency analysis, word correlation analysis, network analysis, and topic modeling, were applied to examine the research trends in the field of aviation safety. The results revealed a significant increase in research using the keyword "Aviation Safety" since 2015, with over 300 papers published annually. Through keyword frequency analysis, it was observed that "Aircraft" was the most frequently mentioned term, followed by "Drones" and "Unmanned Aircraft." Phi coefficients were calculated for words closely related to "Aircraft," "Aviation," "Drones," and "Safety." Furthermore, topic modeling was employed to identify 12 distinct topics in the field of aviation safety and aviation accidents, allowing for an in-depth exploration of research trends.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1141-1151
• /
• 2008

Data mining is the process of sorting through large amounts of data and picking out useful information. One of the well-studied problems in data mining is the exploration of association rules. An association rule technique finds the relation among each items in massive volume database. Some interestingness measures have been developed in association rule mining. Interestingness measures are useful in that it shows the causes for pruning uninteresting rules statistically or logically. This paper propose a conditional pure confidence to evaluate association rules and then describe some properties for a proposed measure. The comparative studies with confidence and pure confidence are shown by numerical example. The results show that the conditional pure confidence is better than confidence or pure confidence.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.11a
• /
• pp.61-66
• /
• 2005

Spatiotemporal data mining represents the confluence of several fields including spatiotemporal databases, machine loaming, statistics, geographic visualization, and information theory. Exploration of spatial data mining and temporal data mining has received much attention independently in knowledge discovery in databases and data mining research community. In this paper, we introduce an algorithm Max_MOP for discovering moving sequences in mobile environment. Max_MOP mines only maximal frequent moving patterns. We exploit the characteristic of the problem domain, which is the spatiotemporal proximity between activities, to partition the spatiotemporal space. The task of finding moving sequences is to consider all temporally ordered combination of associations, which requires an intensive computation. However, exploiting the spatiotemporal proximity characteristic makes this task more cornputationally feasible. Our proposed technique is applicable to location-based services such as traffic service, tourist service, and location-aware advertising service.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.633-640
• /
• 2001

In this paper we examine the machine learning issues raised by the domain of the Intrusion Detection Systems(IDS), which have difficulty successfully classifying intruders. There systems also require a significant amount of computational overhead making it difficult to create robust real-time IDS. Machine learning techniques can reduce the human effort required to build these systems and can improve their performance. Genetic algorithms are used to improve the performance of search problems, while data mining has been used for data analysis. Data Mining is the exploration and analysis of large quantities of data to discover meaningful patterns and rules. Among the tasks for data mining, we concentrate the classification task. Since classification is the basic element of human way of thinking, it is a well-studied problem in a wide variety of application. In this paper, we propose a classifier system based on genetic algorithm, and the proposed system is evaluated by applying it to IDS problem related to classification task in data mining. We report our experiments in using these method on KDD audit data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.306-309
• /
• 2009

일반적으로 이벤트는 발생 시점이라는 시간 속성을 갖는다. 그리고 고객 단위로 이벤트를 축적한 데이터베이스가 있다면 데이터 마이닝을 통하여 유용한 정보를 탐사할 수 있다. 특히 이벤트 발생의 원인과 결과에 대한 관계 규칙을 찾아낼 수 있다면 과거의 정보를 바탕으로 미래를 예측할 수 있는 예측 판단 정보로 사용할 수 있다. 본 연구에서는 데이터 스트림 시스템에서 시간 관계 규칙을 탐사하고 시간 관계 규칙을 구성하는 이벤트 간의 영향력을 측정하기 위한 SM-EC(data Stream Mining for Exploration of Causality)기법을 제안한다. 실험을 통하여 SM-EC가 제공하는 영향력 정보는 다양한 비상 상황에 대처하는 중요한 척도가 될 수 있음을 확인하였다.

• Economic and Environmental Geology
• /
• v.46 no.6
• /
• pp.569-580
• /
• 2013

Co-rich ferromanganese crusts (Fe-Mn crusts) distributed on the seamounts in the western Pacific are potential economic resources for cobalt, nickel, platinum, and other rare metals in the future. Regulations for prospecting and exploration of Fe-Mn crusts in the Area, which enables the process to obtain an exclusive exploration right for blocks of the fixed size, were enacted recently by the International Seabed Authority, which led to public attention on its potential for commercial development. Evaluation and selection of a mining site can be established based on abundance and grade of Fe-Mn crusts in the site as well as topography that should be smooth enough for mining efficiency. Therefore, acquisition of shipboard echo-sounding and acoustic backscatter data are prerequisite to select potential mine sites in addition to visual and sampling operations. Acoustic backscatter data can be used to locate crust-covered areas in a regional scale with the understanding of acoustic properties of crust through its correlation with visual and sampling data. KIOST had collected the topographic and geologic data to assess the resources potential for Fe-Mn crusts in the west Pacific region from 1994 to 2001. However, they could not obtain acoustic backscatter data that is crucial for the selection of prospective mining sites. Therefore, additional exploration surveys are required to carry out side scan sonar mapping combined with seafloor observation and sampling to decide the blocks for application of an exclusive exploration right.

• Geophysics and Geophysical Exploration
• /
• v.17 no.4
• /
• pp.242-246
• /
• 2014

Spectral induced polarization (SIP) is a useful technique, which uses electrochemical properties, for exploration of metallic sulfide minerals. Equivalent circuit analysis is commonly conducted to calculate IP parameters from SIP data. An equivalent circuit model, which indicates the SIP response of rock, has a non-uniqueness problem. For this reason, it is very important to select the proper model for accurate analysis. Thus, this study focused on suggesting a new model, which suitable for the analysis of an anomalous SIP response, such as ore. A suitability of the new model was verified by comparing it with the existing Dias model and Cole-Cole models. Analysis errors were represented as a normalized root mean square error (NRMSE). The analysis result using the Dias model was the NRMSE of 10.50% and was the NRMSE using the Cole-Cole model of 17.03%. Howerver, because the NRMSE of the new model is 0.87%, it is considered that the new model is more useful for analyzing the anomalous SIP data than other models.

• Proceedings of the KSEEG Conference
• /
• 2002.04a
• /
• pp.298-300
• /
• 2002

• Tunnel and Underground Space
• /
• v.29 no.1
• /
• pp.1-11
• /
• 2019

This study investigated use cases of machine learning technology in domestic medical, manufacturing, finance, automobile, urban sectors and those in overseas mining industry. Through a literature survey, it was found that the machine learning technology has been widely utilized for developing medical image information system, real-time monitoring and fault diagnosis system, security level of information system, autonomous vehicle and integrated city management system. Until now, the use cases have not found in the domestic mining industry, however, several overseas projects have found that introduce the machine learning technology to the mining industry for improving the productivity and safety of mineral exploration or mine development. In the future, the introduction of the machine learning technology to the mining industry is expected to spread gradually.