• Journal of Internet Computing and Services
• /
• v.14 no.5
• /
• pp.49-57
• /
• 2013

A novel approach for the feature selection is proposed, which is the important preprocessing task of on-line document classification. In previous researches, the features based on information from their single population for feature selection task have been selected. In this paper, a mixed feature set is constructed by selecting features from multi-population as well as single population based on various information. The mixed feature set consists of two feature sets: the original feature set that is made up of words on documents and the transformed feature set that is made up of features generated by LSA. The hybrid feature selection method using both filter and wrapper method is used to obtain optimal features set from the mixed feature set. We performed classification experiments using the obtained optimal feature sets. As a result of the experiments, our expectation that our approach makes better performance of classification is verified, which is over 90% accuracy. In particular, it is confirmed that our approach has over 90% recall and precision that have a low deviation between categories.

• Journal of KIISE:Software and Applications
• /
• v.36 no.12
• /
• pp.1024-1027
• /
• 2009

In this letter, we evaluate the classification performance of mixed numeric and categorical data for comparing the efficiency of feature filtering and feature wrapping. Because the mixed data is composed of numeric and categorical features, the feature selection method was applied to data set after discretizing the numeric features in the given data set. In this study, we choose the feature subset for improving the classification performance of the data set after preprocessing. The experimental result of comparing the classification performance show that the feature wrapping method is more reliable than feature filtering method in the aspect of classification accuracy.

• Journal of KIISE:Software and Applications
• /
• v.31 no.8
• /
• pp.1113-1120
• /
• 2004

This paper proposes a novel hybrid genetic algorithm for the feature selection. Local search operations are devised and embedded in hybrid GAs to fine-tune the search. The operations are parameterized in terms of the fine-tuning power, and their effectiveness and timing requirement are analyzed and compared. Experimentations performed with various standard datasets revealed that the proposed hybrid GA is superior to a simple GA and sequential search algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.472-479
• /
• 1999

In this paper, we propose a land cover pattern classifier for remote sensing image by using neuro-fuzzy algorithm. The proposed pattem classifier has a 3-layer feed-forward architecture that is derived from generic fuzzy perceptrons, and the weights are con~posed of h u y sets. We also implement a neuro-fuzzy pattern classification system in the Visual C++ environment. To measure the performance of this, we compare it with the conventional neural networks with back-propagation learning and the Maximum-likelihood algorithms. We classified the remote sensing image into the eight classes covered the majority of land cover feature, selected the same training sites. Experimental results show that the proposed classifier performs well especially in the mixed composition area having many classes rather than the conventional systems.

• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.372-373
• /
• 2011

인터넷 매체가 급증함에 따라 많은 이들에게 쉽게 노출 되어 유포되고 있는 유해 영상을 검출하기 위해 다양한 분류 방법에 대한 연구들이 이루어지고 있다. 본 논문에서 유해 영상 내의 피부색 영역에서의 Haar-like 특징을 추출하여 유해 영상을 분류하는 방법을 제안한다. 이를 위해, 첫 번째 단계에는 샘플 영상에 대하여 기존에 제안된 피부색 검출 방법을 적용하고, 두 번째 단계에는 검출된 피부색 영역 내의 Haar-like 특징을 추출한다. 각 샘플 영상에서 추출한 특징들은 SVM(Support Vector Machine)을 이용하여 각각 2000 장의 유해, 무해 영상을 학습한다. 학습된 모델은 유해 및 무해 영상이 혼합되어 있는 영상 집합들을 분류하는데 사용한다.

• Annual Conference of KIPS
• /
• 2013.11a
• /
• pp.1354-1357
• /
• 2013

최근 다양한 센서들이 일상생활에 활용되어, 일정한 환경에서 사람의 행동을 분류하고 인식하기 위한 연구들이 활발하게 진행되고 있다. 본 연구에서는 2개의 진동센서 값과 1개의 적외선 센서 값을 은닉 마코프 모델에 적용하여 침대 위에 있는 사람의 3가지 행동유형-눕기, 뒤척임, 일어나기-을 분류하고자 한다. 3개 센서 값의 특징들을 기초로 은닉 마코프 모델에 학습시키고, 특징집합과 학습 데이터량을 변화시키면서 사람의 행동유형에 대한 인식 실험을 수행하였다. 특징 개수 혼합에 따른 인식률의 차이는 거의 없는 것으로 나타났으나, 학습 데이터량을 증가시켜 가면서 수행한 실험에서는 인식률이 평균 78.127%로 향상되는 성과를 거두었다.

• The KIPS Transactions:PartA
• /
• v.11A no.5
• /
• pp.383-390
• /
• 2004

This paper propose a method that controls facial expression of 3D avatar by having the user select a sequence of facial expressions in the space of facial expressions. And we setup its system. The space of expression is created from about 2400 frames consist of motion captured data of facial expressions. To represent the state of each expression, we use the distance matrix that represents the distances between pairs of feature points on the face. The set of distance matrices is used as the space of expressions. But this space is not such a space where one state can go to another state via the straight trajectory between them. We derive trajectories between two states from the captured set of expressions in an approximate manner. First, two states are regarded adjacent if the distance between their distance matrices is below a given threshold. Any two states are considered to have a trajectory between them If there is a sequence of adjacent states between them. It is assumed . that one states goes to another state via the shortest trajectory between them. The shortest trajectories are found by dynamic programming. The space of facial expressions, as the set of distance matrices, is multidimensional. Facial expression of 3D avatar Is controled in real time as the user navigates the space. To help this process, we visualized the space of expressions in 2D space by using the multidimensional scaling(MDS). To see how effective this system is, we had users control facial expressions of 3D avatar by using the system. As a result of that, users estimate that system is very useful to control facial expression of 3D avatar in real-time.

• Journal of the Mineralogical Society of Korea
• /
• v.18 no.3 s.45
• /
• pp.227-236
• /
• 2005

Hydrothermal tourmaline occurs as aggregates or dissemination in the diaspore nodule from an aluminum-rich clay deposit, Milyang, southeastern Korea. Most crystals of tourmaline show complex textures that are finely zoned. The fine-scale chemical zonation of hydrothermal tourmaline reflects the fluctuation conditions that would be expected from fluid mixing in open systems. Oscillatory chemical zoning in tourmaline formed and showed similar patterns, regardless of its crystallographic directions. Mg was enriched in the early stage of crystal growth while Fe was enriched in the later stage, with fluctuations of the ratio of Fe to Mg. Chemical analysis, BSE images, and X-ray compositional maps confirm that the oscillatory Boning in tourmaline is exclusively controlled by the variations of Fe and Mg contents, but the contribution of boron to the zonation is insignificant. The fact that tourmaline altered to diaspore and dickite indicates that tourmaline was unstable with respect to these aluminous minerals as the B, Fe, and Mg activities decreased. Therefore, the aluminum activity may control the stability of tourmaline in the hydrothermal system.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.318-322
• /
• 2006

댐군 운영 문제는 여러 상충되는 목적 및 구성 요소들 간의 타협, 조정을 위한 다목적 특성을 갖고 있다. 본 연구의 목적은 댐군 연계 운영 문제에 대해 다기준 의사결정 기법을 적용하여 최선의 운영 계획을 수립하는 것이다. 이를 위해 순위선호(outranking) 관계와 유사기준(pseudo-criteria)을 기반으로 해서 여러 선호 대안을 선정하는 데 유용한 ELECTRE (ELimination Et Choice Translating REality)를 적용하고자 한다. ELECTRE IS는 주어진 후보 대안들 중에서 원하는 수의 대안을 선정하는 데 유용하다. 그러나 기존의 ELECTRE IS는 대안선정 과정에서 의사결정자에게 기준들의 가중치(weight), 유사기준판정 경계치(pseudo-criteria thresholds), 그리고 일치판정 기준비율(concordance level)의 매개변수에 대한 설정을 요구하고 이들의 설정 상태에 따라 도출되는 대안의 수가 달라질 수 있는 성질을 갖고 있다. 특히 일치판정 기준비율은 ELECTRE IS의 최종적인 순위선호 관계의 형성여부에 결정적 영향을 주어 매개변수의 아주 작은 변화에도 선정되는 대안의 수가 달라질 수 있다. 따라서 실제 ELECTRE IS를 적용하여 원하는 수의 대안을 선정하기 위해서는 일치판정 기준비율에 대한 반복적용이 불가피하다. 이에 본 연구에서는 CoMOM (Coordinated Multireservoir Operating Model)을 활용한 댐군 연계운영 시 제시되는 파레토 최적해 집합(Pareto set)중에서 최선의 파레토 최적해를 선정할 때 ELECTRE IS의 수학적 구현 모형을 활용할 것을 제안하고 그 방법론을 제시한다. 제안된 모형은 혼합정수계획모형으로서 ELECTRE IS를 적용하는 과정에서 일치판정 기준비율을 자동으로 도출하고, 궁극적으로 많은 반복 없이 원하는 수나 그에 근사한 수의 선호대안(핵심대안)을 도출할 수 있는 특징을 갖고 있다. 이 모형을 낙동강 수계의 댐군 연계운영 문제에 적용해 보고, 핵심대안을 효율적으로 도출할 수 있음을 보인다.

• The KIPS Transactions:PartB
• /
• v.11B no.5
• /
• pp.545-554
• /
• 2004

Combining multiple classifiers to obtain improved performance over the individual classifier has been a widely used technique. The task of constructing a multiple classifier system(MCS) contains two different Issues how to generate a diverse set of base-level classifiers and how to combine their predictions. In this paper, we review the characteristics of existing multiple classifier systems : Bagging, Boosting, and Slaking. For document classification, we propose new MCSs such as Stacked Bagging, Stacked Boosting, Bagged Stacking, Boosted Stacking. These MCSs are a sort of hybrid MCSs that combine advantages of existing MCSs such as Bugging, Boosting, and Stacking. We conducted some experiments of document classification to evaluate the performances of the proposed schemes on MEDLINE, Usenet news, and Web document collections. The result of experiments demonstrate the superiority of our hybrid MCSs over the existing ones.