• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.429-434
• /
• 2003

본 논문은 작업일정계획에서 부하평준화 문제를 효율적으로 해결하기 위하여 tabu 탐색을 적용함에 있어서 확률적 선별에 기반하여 이웃해를 생성하는 방법을 제시한다. 이웃해 생성은 부하평준화를 위해 일정을 조정할 대상 작업을 선택하는 단계와 선택된 작업에 대해 일정 조정의 방향을 결정하는 단계로 구분된다. 확률적 선별에 기반한 이웃해 생성은 우선 무작위로 추출된 작업에 대해서 탐색의 질을 개선시킬 수 있는 가능성에 대한 추정치에 따라 확률을 부여하고, 이 확률에 기반하여 선택여부를 결정함으로써 이웃해를 선별하는 방법이다. 실제 현장의 부하평준화 문제를 대상으로 이웃해 생성 방법으로 무작위 방법, 그리디(greedy) 방법과의 비교 실험을 통해 확률적 선별에 기반한 이웃해 생성 방법의 성능을 검증하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.4
• /
• pp.283-288
• /
• 2019

In order to overcome the students' lack of information and experience, we developed a content planning tree that utilizes a decision tree. The content planning tree consists of a tree trunk creation step in which students select a theme and a story to develop, a parent branch generation step for selecting a category that can be developed based on the story, a child branch generation step for selecting the interesting "effect" method of producing the content effectively, a leaf generation step for selecting a multimedia expression 'element' to be visualized. The educational model was applied to game planning design and information visualization lectures, and provides examples of the categories, effects, and elements used in each lecture. The model was used for 145 team projects and the efficiency was confirmed by a step-by-step learning process.

• The Journal of the Korea Contents Association
• /
• v.4 no.3
• /
• pp.115-123
• /
• 2004

This study suggests the output of the fingerprint doorlock design development through the structured methodology of concept selection in the process of design development, after characterizing the doorlock product itself. All of the early phases of product development are very important on eventual product success. Concept selection is the process of evaluating concepts with respect to customer needs and other criteria, comparing the relative strength and weaknesses of the concepts, and selecting one or more concepts for further investigation or development. To obtain the ideal concept o( new product, this work used a two-stage concept selection methodology which consist of concept screening and concept scoring. As a result, this study represents the fixed design rendering for mass production.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.52-54
• /
• 2001

공간 선택 질의에 사용되는 질의 윈도우로는 직사각형이 주로 사용된다. 하지만, 최근에는 GIS 등과 같은 응용 프로그램들이 성능 향상으로 인해 보다 다양한 종류의 응용이 등장하고 있으므로, 직사각형뿐만 아니라 임의의 다각형 형태의 질의 윈도우에도 적합한 정제 단계 수행 전략에 대해 고려해 볼 필요가 있다. 이러한 전략으로는 기존의 공간 조인에서와 같이 plane-sweep 알고리즘을 이용하는 방법이 일반적이다. 하지만, 공간 데이터와 질의 위도우의 특성을 관찰해보면, 일반적으로 질의 윈도우가 공간 데이터보다 훨씬 간단한 모양으로 구성되어 있음을 알 수 있으므로, 본 논문에서는 이러한 상황에 보다 적합한 정제 단계 수행 방법을 제시하고 있으며, 실험을 통하여 제시한 방법의 우수성을 입증하고 있다.

• The KIPS Transactions:PartC
• /
• v.10C no.2
• /
• pp.125-132
• /
• 2003

In the paper, we can select the best safeguard as proposed the definite and systematical method and procedure on risk mitigation of risk management for information system. The practical risk mitigation methodology has a good fulfillment procedure and a definition to fulfill procedure on each phase. So, it is easy to fulfill and can apply to any risk management methodology. The practical risk mitigation is composed of 6 phases, which are the existing safeguard assessment, safeguard means selection, safeguard technique selection, risk admission assessment, cost-effective analysis and safeguard embodiment. The practical risk mitigation's advantages are as follow. Efficient selection of safeguards to apply to risk's features with safeguard's means and techniques before embodying safeguards. Prevention of redundant works and security budgets waste as re-using the existing excellent safeguards through the existing safeguard assessment. Reflection of organization's CEO opinions to require special safeguards for the most important information system.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1077-1085
• /
• 2017

In this study, we have found the major factors which affect Korean women's wage analysing the data provided by 2015 Korea Labor Panel Survey (KLIPS). In general, wage data is difficult to analyze because random sampling is infeasible. Heckman sample selection model is the most widely used method for analysing the data with sample selection. Heckman proposed two kinds of selection models: the one is the model with maximum likelihood method and the other is the Heckman two stage model. Heckman two stage model is known to be robust to the normal assumption of bivariate error terms. Recently, Marchenko and Genton (2012) proposed the Heckman selectiont model which generalizes the Heckman two stage model and concluded that Heckman selection-t model is more robust to the error assumptions. Employing the two models, we carried out the analysis of the data and we compared those results.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.4
• /
• pp.111-116
• /
• 2003

We proposed a optimal clock period selection algorithm for low power Register Transfer Level design. The proposed algorithm use the way of maintaining the throughput by reducing supply voltage after improve the system performance in order to minimize the power consumption. In this paper, it select the low power to use pipeline in the transformation of architecture. Also, the proposed algorithm is important the clock period selection in order to maximize the resource sharing. however, it execute the optimal clock period selection algorithm. The experiment result is to set the same result AR and HAL filter on the high level benchmark and to reduce in the case of two pipe stage 10.5% and three pipe stage as many as 33.4%.

• Journal of KIISE:Software and Applications
• /
• v.34 no.9
• /
• pp.857-868
• /
• 2007

The good classifier ensemble should have a high complementarity among classifiers in order to produce a high recognition rate and its size is small in order to be efficient. This paper proposes a classifier ensemble selection algorithm with coarse-to-fine stages. for the algorithm to be successful, the original classifier pool should be sufficiently diverse. This paper produces a large classifier pool by combining several different classification algorithms and lots of feature subsets. The aim of the coarse selection is to reduce the size of classifier pool with little sacrifice of recognition performance. The fine selection finds near-optimal ensemble using genetic algorithms. A hybrid genetic algorithm with improved searching capability is also proposed. The experimentation uses the worldwide handwritten numeral databases. The results showed that the proposed algorithm is superior to the conventional ones.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.107-114
• /
• 2022

In this paper, we have enhanced the risk prediction of hypertension using the feature selection method in the Korean National Health and Nutrition Examination Survey (KNHANES) database of the Korea Centers for Disease Control and Prevention. The study identified various risk factors correlated with chronic hypertension. The paper is divided into three parts. Initially, the data preprocessing step of removes missing values, and performed z-transformation. The following is the feature selection (FS) step that used a factor analysis (FA) based on the feature selection method in the dataset, and feature importance (FI) and multicollinearity analysis (MC) were compared based on FS. Finally, in the predictive analysis stage, it was applied to detect and predict the risk of hypertension. In this study, we compare the accuracy, f-score, area under the ROC curve (AUC), and mean standard error (MSE) for each model of classification. As a result of the test, the proposed MC-FA-RF model achieved the highest accuracy of 80.12%, MSE of 0.106, f-score of 83.49%, and AUC of 85.96%, respectively. These results demonstrate that the proposed MC-FA-RF method for hypertension risk predictions is outperformed other methods.

• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.104-112
• /
• 2016

The Adaboost chooses a good set of features in rounds. On each round, it chooses the optimal feature and its threshold value by minimizing the weighted error of classification. The involved process of classification performs a hard decision. In this paper, we expand the process of classification to a soft fuzzy decision. We believe this expansion could allow some flexibility to the Adaboost algorithm as well as a good performance especially when the size of a training data set is not large enough. The typical Adaboost algorithm assigns a same weight to each training datum on the first round of a training process. We propose a new algorithm to assign different initial weights based on some statistical properties of involved features. In experimental results, we assess that the proposed method shows higher performance than the traditional one.