• 산업공학
• /
• 제25권1호
• /
• pp.96-105
• /
• 2012

Recently, the interoperability has become more important to enhance the net-centric capabilities of the warfighter. DITA (Defense Information Technical stAndard) is the set of IT standards for improving interoperability, scalability, effectiveness, and efficiency. In this paper, we analyzed the standardizing process to derive the selection criteria and structurized the derived selection criteria using the KJ (Kawakita Jiro) method. Finally, we developed an evaluation model for selecting a standard for DITA using AHP (Analytic Hierarchy Process). As a result, we present eight selection criteria (maintainability, trend, stability, portability, effect of other standard, constraint of the network, and applicability to the systems). We also applied some examples that several IT standards to our selection model for validating the model. We expect our model to help to decide objectively whether the new standard can be listed in DITA.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2004년도 춘계학술대회논문집
• /
• pp.876-881
• /
• 2004

Finite element model updating is an inverse problem to identify and correct uncertain modeling parameters that leads to better predictions of the dynamic behavior of a target structure. Unlike other inverse problems, the restrictions on selecting parameters all: very high since the updated model should maintains its physical meaning. That is, only the regions with modeling errors should be parameterized. And the variations of the parameters should be kept small while the updated results give acceptable correlations with experimental data. To avoid an ill-conditioned numerical problem, the number of parameters should be kept as small as possible. Thus it is very difficult to select an adequate set of updating parameters which meet all these requirements. In this paper, the importance of updating parameter selection is illustrated through a case study, and an automated procedure to guide the parameter selection is suggested based on simple observations. The effectiveness of the suggested procedure is tested with two example problems, ones is a simulated case study and the other is a real engineering structure.

• 대한음성학회지:말소리
• /
• 제63호
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• 지능정보연구
• /
• 제20권4호
• /
• pp.121-139
• /
• 2014

기업의 부도 예측은 재무 및 회계 분야에서 매우 중요한 연구 주제이다. 기업의 부도로 인해 발생하는 비용이 매우 크기 때문에 부도 예측의 정확성은 금융기관으로서는 매우 중요한 일이다. 최근에는 여러 개의 모형을 결합하는 앙상블 모형을 부도 예측에 적용해 보려는 연구가 큰 관심을 끌고 있다. 앙상블 모형은 개별 모형보다 더 좋은 성과를 내기 위해 여러 개의 분류기를 결합하는 것이다. 이와 같은 앙상블 분류기는 분류기의 일반화 성능을 개선하는 데 매우 유용한 것으로 알려져 있다. 본 논문은 부도 예측 모형의 성과 개선에 관한 연구이다. 이를 위해 사례 선택(Instance Selection)을 활용한 배깅(Bagging) 모형을 제안하였다. 사례 선택은 원 데이터에서 가장 대표성 있고 관련성 높은 데이터를 선택하고 예측 모형에 악영향을 줄 수 있는 불필요한 데이터를 제거하는 것으로 이를 통해 예측 성과 개선도 기대할 수 있다. 배깅은 학습데이터에 변화를 줌으로써 기저 분류기들을 다양화시키는 앙상블 기법으로 단순하면서도 성과가 매우 좋은 것으로 알려져 있다. 사례 선택과 배깅은 각각 모형의 성과를 개선시킬 수 있는 잠재력이 있지만 이들 두 기법의 결합에 관한 연구는 아직까지 없는 것이 현실이다. 본 연구에서는 부도 예측 모형의 성과를 개선하기 위해 사례 선택과 배깅을 연결하는 새로운 모형을 제안하였다. 최적의 사례 선택을 위해 유전자 알고리즘이 사용되었으며, 이를 통해 최적의 사례 선택 조합을 찾고 이 결과를 배깅 앙상블 모형에 전달하여 새로운 형태의 배깅 앙상블 모형을 구성하게 된다. 본 연구에서 제안한 새로운 앙상블 모형의 성과를 검증하기 위해 ROC 커브, AUC, 예측정확도 등과 같은 성과지표를 사용해 다양한 모형과 비교 분석해 보았다. 실제 기업데이터를 사용해 실험한 결과 본 논문에서 제안한 새로운 형태의 모형이 가장 좋은 성과를 보임을 알 수 있었다.

• Communications for Statistical Applications and Methods
• /
• 제4권1호
• /
• pp.177-183
• /
• 1997

A data-adaptive order selection procedure is proposed for local polynomial nonparametric regression. For each given polynomial order, bias and variance are estimated and the adaptive polynomial order that has the smallest estimated mean squared error is selected locally at each location point. To estimate mean squared error, empirical bias estimate of Ruppert (1995) and local polynomial variance estimate of Ruppert, Wand, Wand, Holst and Hossjer (1995) are used. Since the proposed method does not require fitting polynomial model of order higher than the model order, it is simpler than the order selection method proposed by Fan and Gijbels (1995b).

• Management Science and Financial Engineering
• /
• 제18권2호
• /
• pp.13-17
• /
• 2012

Set covering has widely been accepted as a staple tool for feature selection in data mining. We present a generalized version of this classical combinatorial optimization model to make it better suited for the purpose and propose a surrogate relaxation-based procedure for its meta-heuristic solution. Mathematically and also numerically with experiments on 25 set covering instances, we demonstrate the utility of the proposed model and the proposed solution method.

• 디지털융복합연구
• /
• 제6권3호
• /
• pp.75-84
• /
• 2008

The purpose of our this research, based on the Media Selection Theory, the Technology Acceptance Model, and the Social Influence Theory, is to investigate the influential factors that affect media selection in banking transactions. Analyses showed that for location sensitive bank window's and ATMs (automatic teller machines), defined as offline-based transaction channels, convenience was the variable affecting media selection. However, in the case of online media not related to location, (phone banking, internet banking, and mobile banking) reliability was the significant variable influencing use. The findings show that banking organizations may benefit from identifying traits of media affecting use, and should differentiate customer services for competitive advantage.

• 한국지능시스템학회논문지
• /
• 제12권6호
• /
• pp.549-553
• /
• 2002

본 논문은 전문학술 인력을 자동으로 순위를 매겨 선정하는 지식기반 퍼지 다중 규칙을 제시하고 있다 이를 위하여 학술전문가 선정에 대한 추론규칙을 만들고 다중퍼지 규칙에 대한 최대-최소 추론 및 선정기준에 따라 동적으로 선정기준이 적용되는 방안을 제시하며 이를 위한 시뮬레이션 모델을 구현하고 있다. 본 제안은 학술전문가 선정의 자동화, 공정성, 신뢰성 등을 제공하여 준다.

• 대한산업공학회지
• /
• 제33권4호
• /
• pp.402-409
• /
• 2007

Markov Chains has proven to be effective in predicting human behaviors in the areas of web site assess, multimedia educational system, and driving environment. In order to extend an application area of predicting human behaviors using Markov Chains, this study was conducted to investigate whether Markov Chains could be used to predict human behavior in selecting mobile phone menu item. Compared to the aforementioned application areas, this study has different aspects in using Markov Chains : m-order 1-step Markov Model and the concept of Power Law of Learning. The results showed that human behaviors in predicting mobile phone menu selection were well fitted into with m-order 1-step Markov Model and Power Law of Learning in allocating history path vector weights. In other words, prediction of mobile phone menu selection with Markov Chains was capable of user's actual menu selection.

• 한국항해항만학회지
• /
• 제33권4호
• /
• pp.271-275
• /
• 2009

A strategic decision making on location selection for product transportation includes many tangible and untangible factors. To choose the best locations is a difficult job in the sense that objectives usually conflict with each other. In this paper, we consider a multi stage multi criteria transshipment problem with different types of items to be transported from the sources to the destination points. For the optimization of the problem, a goal programming formulation will be presented in which the location selection for each product type will be determined under the multi objective criteria. In the study, we generalize the transshipment model with a variety of product types and finite number of different intermediate nodes between origins and destinations. For the selection of the criteria we selected the costs(fixed cost and transportation cost), location numbers, and unsatisfied demand for each type of products in multi stage transportation, which are the main goals in transshipment modelling problems. The related conditions are also modelled through linear formats.