• 한국콘텐츠학회논문지
• /
• 제15권8호
• /
• pp.24-36
• /
• 2015

최근 실시간으로 생성되는 대용량의 SNS 데이터로부터 유의미한 정보를 찾아내고 분석하는 것이 중요해지면서 핫 토픽 검출에 대한 관심도 크게 증가하고 있다. SNS 특성상 사전 확인이 이루어지지 않은 불특정 다수의 글들을 대상으로 하기 때문에 이 글들을 대상으로 핫 토픽을 예측했을 때 결과의 신뢰성이 저하된다는 문제점이 있다. 이를 해결하기 위하여 본 논문에서는 소셜 네트워크에서 사용자의 영향력을 고려한 신뢰성 높은 핫 토픽 예측 기법을 제안한다. 트위터를 기반으로 변형된 TF-IDF 알고리즘을 통하여 순간적으로 많이 이슈화되는 키워드 후보 집합을 추출하고, 트윗에 사용자 영향력을 가중치로 부여함으로써 핫 토픽 예측 결과의 신뢰성을 높인다. 제안하는 기법의 우수성을 보이기 위해 기존 기법과 제안하는 기법의 성능평가를 수행한다. 성능평가 결과, 제안하는 기법은 기존 기법에 비해 정확도, 재현율 모두 향상됨을 확인하였다.

• Earthquakes and Structures
• /
• 제11권5호
• /
• pp.779-807
• /
• 2016

Ground Motion Prediction Equations (GMPEs) are essential tools in seismic hazard analysis. With the introduction of probabilistic approaches for the estimation of seismic response of structures, also known as, performance based earthquake engineering framework; new tasks are defined for response spectrum such as the reference criterion for effective structure-specific selection of ground motions for nonlinear time history analysis. One of the recent efforts to introduce a high quality databank of ground motions besides the corresponding selection scheme based on the broadband spectral consistency is the development of SIMBAD (Selected Input Motions for displacement-Based Assessment and Design), which is designed to improve the reliability of spectral values at all natural periods by removing noise with modern proposed approaches. In this paper, a new global GMPE is proposed by using selected ground motions from SIMBAD to improve the reliability of computed spectral shape indicators. To determine regression coefficients, 204 pairs of horizontal components from 35 earthquakes with magnitude ranging from Mw 5 to Mw 7.1 and epicentral distances lower than 40 km selected from SIMBAD are used. The proposed equation is compared with similar models both qualitatively and quantitatively. After the verification of model by several goodness-of-fit measures, the epsilon values as the spectral shape indicator are computed and the validity of available prediction equations for correlation of the pairs of epsilon values is examined. General consistency between predictions by new model and others, especially, in short periods is confirmed, while, at longer periods, there are meaningful differences between normalized residuals and correlation coefficients between pairs of them estimated by new model and those are computed by other empirical equations. A simple collapse assessment example indicate possible improvement in the correlation between collapse capacity and spectral shape indicators (${\varepsilon}$) up to 20% by selection of a more applicable GMPE for calculation of ${\varepsilon}$.

• 대한기계학회논문집A
• /
• 제34권9호
• /
• pp.1281-1286
• /
• 2010

발전소를 비롯한 각종 플랜트 설비는 많은 기계설비들로 구성되어 고장이 발생할 경우, 고장이 발생된 설비와 시간을 명확하게 파악하기가 쉽지 않다, 또한 고장발생시 정비비용 증가와 함께 설비의 이용률이 감소하여 막대한 경제적 손실이 발생한다. 발전소는 각종 계측센서를 설치하여 설비를 상시 감시하고 있으며, 경고발생 이전 지시치의 변화를 관찰하여 설비의 이상상태를 자동 감지하는 신호기반 고장 조기경보 시스템도 설치된 발전소도 있다. 그러나 고장경보 시스템은 이상신호 발생을 인지하여 설비의 이상상태 여부는 알려주지만 고장원인과 중요도에 대한 정보는 제공하지 않는다. 본 연구에서는 고장분석 기능을 가지고 있는 RCM(Reliability Centered Maintenance) 분석 시스템과 고장경보시스템을 연계하여 설비의 이상신호로부터 고장원인과 정비방법에 대한 정보를 제공하는 고장예측시스템을 개발하고자 한다.

• 한국항공우주학회지
• /
• 제41권8호
• /
• pp.625-631
• /
• 2013

핀풀러의 신뢰도를 몬테카를로 시뮬레이션을 통해서 예측하였다. 예측방법은 응력-강도 간섭 모델에 근거한다. 이 모델은 강도가 응력보다 작을 경우를 고장으로 간주한다. 본 연구에서 강도는 핀을 예정된 거리까지 후퇴시키는데 필요한 에너지로, 응력은 이 핀의 운동을 방해하는데 소요되는 에너지로 간주하였다. 전자는 주로 화약량에 의해 결정되고 후자는 여러 가지 마찰력과 반발방지장치에서 소모되는 에너지에 의존한다. 응력과 강도 변수들은 해석적 성능 모델로부터 계산하였다. 본 연구에서 제시된 방법은 많은 시료가 필요하지 않기 때문에 유사한 종류의 파이로 장치 신뢰도 계산에도 적용될 수 있다.

• 융합보안논문지
• /
• 제22권3호
• /
• pp.101-110
• /
• 2022

다양한 분야에서 인공지능을 활용한 사례가 증가하면서 침입탐지 분야 또한 다양한 이슈를 인공지능을 통해 해결하려는 시도가 증가하고 있다. 하지만, 머신러닝을 통한 예측된 결과에 관한 이유를 설명하거나 추적할 수 없는 블랙박스 기반이 대부분으로 이를 활용해야 하는 보안 전문가에게 어려움을 주고 있다. 이러한 문제를 해결하고자 다양한 분야에서 머신러닝의 결정을 해석하고 이해하는데 도움이 되는 설명 가능한 AI(XAI)에 대한 연구가 증가하고 있다. 이에 본 논문에서는 머신러닝 기반의 침입탐지 예측 결과에 대한 신뢰성을 강화하기 위한 설명 가능한 AI를 제안한다. 먼저, XGBoost를 통해 침입탐지 모델을 구현하고, SHAP을 활용하여 모델에 대한 설명을 구현한다. 그리고 기존의 피처 중요도와 SHAP을 활용한 결과를 비교 분석하여 보안 전문가가 결정을 수행하는데 신뢰성을 제공한다. 본 실험을 위해 PKDD2007 데이터셋을 사용하였으며 기존의 피처 중요도와 SHAP Value에 대한 연관성을 분석하였으며, 이를 통해 SHAP 기반의 설명 가능한 AI가 보안 전문가들에게 침입탐지 모델의 예측 결과에 대한 신뢰성을 주는데 타당함을 검증하였다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.208-208
• /
• 2022

Recently, the frequency of abnormal weather due to complex factors such as global warming is increasing frequently. From the past rainfall patterns, it is evident that climate change is causing irregular rainfall patterns. This phenomenon causes difficulty in predicting rainfall and makes it difficult to prevent and cope with natural disasters, casuing human and property damages. Therefore, accurate rainfall estimation and rainfall occurrence time prediction could be one of the ways to prevent and mitigate damage caused by flood and drought disasters. However, rainfall prediction has a lot of uncertainty, so it is necessary to understand and reduce this uncertainty. In addition, when accurate rainfall prediction is applied to the rainfall-runoff model, the accuracy of the runoff prediction can be improved. In this regard, this study aims to increase the reliability of rainfall prediction by analyzing the uncertainty of the Korean rainfall ensemble prediction data and the outflow analysis model using the Limited Area ENsemble (LENS) and the Grid based Rainfall-runoff Model (GRM) models. First, the possibility of improving rainfall prediction ability is reviewed using the QM (Quantile Mapping) technique among the bias correction techniques. Then, the GRM parameter calibration was performed twice, and the likelihood-parameter applicability evaluation and uncertainty analysis were performed using R², NSE, PBIAS, and Log-normal. The rainfall prediction data were applied to the rainfall-runoff model and evaluated before and after calibration. It is expected that more reliable flood prediction will be possible by reducing uncertainty in rainfall ensemble data when applying to the runoff model in selecting behavioral models for user uncertainty analysis. Also, it can be used as a basis of flood prediction research by integrating other parameters such as geological characteristics and rainfall events.

• 한국환경보건학회지
• /
• 제40권2호
• /
• pp.105-113
• /
• 2014

Objectives: It is necessary to apply quantitative structure activity relationship (QSAR) for the various chemicals with insufficient toxicity data that are used in the workplace, based on the precautionary principle. This study aims to find application plan of QSAR software tool for predicting health hazards such as genetic toxicity, and carcinogenicity for some chemicals used in the electronics industries. Methods: Toxicity prediction of 21 chemicals such as 5-aminotetrazole, ethyl lactate, digallium trioxide, etc. used in electronics industries was assessed by Toxicity Prediction by Komputer Assisted Technology (TOPKAT). In order to identify the suitability and reliability of carcinogenicity prediction, 25 chemicals such as 4-aminobiphenyl, ethylene oxide, etc. which are classified as Group 1 carcinogens by the International Agency for Research on Cancer (IARC) were selected. Results: Among 21 chemicals, we obtained prediction results for 5 carcinogens, 8 non-carcinogens and 8 unpredictability chemicals. On the other hand, the carcinogenic potential of 5 carcinogens was found to be low by relevant research testing data and Oncologic TM tool. Seven of the 25 carcinogens (IARC Group 1) were wrongly predicted as non-carcinogens (false negative rate: 36.8%). We confirmed that the prediction error could be improved by combining genetic toxicity information such as mutagenicity. Conclusions: Some compounds, including inorganic chemicals and polymers, were still limited for applying toxicity prediction program. Carcinogenicity prediction may be further improved by conducting cross-validation of various toxicity prediction programs, or application of the theoretical molecular descriptors.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제17권4호
• /
• pp.280-288
• /
• 2017

Purpose: PBA buried in underwater requires high reliability because of its mission critical characteristic and harsh operational environment during its life cycle. Therefore, various reliability improvement activities are necessary. The defect on PBA manufacturing process have been studied, as a result, many activities and standards have been presented. However, there are less studies regarding failure pattern on physical features based on design. In this paper, we studied a possible failure patten based on physical features that is related with manufacturing process of PBA. And reliability improvement design based on PoF (Physical of Failure) were intruduced in this paper. Methods: A reliability prediction simulation were performed on the components A and B of the H system using Sherlock Software which is a PoF commercial tool from DFR solution. Solder fatigue and PTH fatigue analysis based on thermal cycling profiles and random vibration was analyzed on three earthquake response spectrum. Result: It was validated that life time and reliability improvement design through solder fatigue and PTH fatigue analysis in case of component. For compoenet B, random vibration fatigue was additionally analyzed and validated reliability for earthquakes profile. Conclusion: In design stage prior to manufacturing, PoF can be analyzed, and it is possible to make a reliability improvement/validated design using design data. This study can be applied in every design step and contribute to make more stable development product.

• 대한기계학회논문집A
• /
• 제26권6호
• /
• pp.1069-1076
• /
• 2002

The high temperature creep behavior of heat machine systems such as aircraft engines, boilers and turbines in power plants and nuclear reactor components have been considered as an important and needful fact. There are considerable research results available for the design of high temperature tube materials in power plants. However, few studies on the Initial Strain Method (ISM) capable of securing repair, maintenance, cost loss and life loss have been made. In this method, 3 long time prediction Of high temperature creep characteristics can be dramatically induced through a short time experiment. The purpose of present study is to investigate the high temperature creep lift of Udimet 720, SCM 440-STD61 and 1Cr-0.5Mo steel using the ISM. The creep test was performed at 40$0^{\circ}C$ to $700^{\circ}C$ under a pure loading. In the prediction of creep life for each materials, the equation of ISM was superior of Larson-Miller Parameter(LMP). Especially, the long time prediction of creep life was identified to improve the reliability.

• Computers and Concrete
• /
• 제17권2호
• /
• pp.173-188
• /
• 2016

Generally, thermal stress induced by hydration heat causes cracking in mass concrete structures, requiring a thorough control during the construction. The prediction of the thermal stress is currently undertaken by means of numerical analysis despite its lack of reliability due to the properties of concrete varying over time. In this paper, a method for the prediction of thermal stress in concrete structures by adjusting thermal stress measured by a thermal stress device according to the degree of restraint is proposed to improve the prediction accuracy. The ratio of stress in concrete structures to stress under complete restraint is used as the degree of restraint. To consider the history of the degree of restraint, incremental stress is predicted by comparing the degree of restraint and the incremental stress obtained by the thermal stress device. Furthermore, the thermal stresses of wall and foundation predicted by the proposed method are compared to those obtained by numerical analysis. The thermal stresses obtained by the proposed method are similar to those obtained by the analysis for structures with internally as well as externally strong restraint. It is therefore concluded that the prediction of thermal stress for concrete structures with various boundary conditions using the proposed method is suggested to be accurate.