• 한국인쇄학회지
• /
• 제22권2호
• /
• pp.55-72
• /
• 2004

The term color management system design, an ensemble of algorithm that provides a framework in which color information can be processed consistently throughout a digital imaging system. This is most commonly achieved through the use of special color transformation, known as device independent color transformation based on ICC device profiles. The purpose of this paper is to present some of the scientific principles of color management, and the original color management algorithms and solutions for digital soft color proofing system development.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2003년도 추계학술발표논문집 (상)
• /
• pp.301-304
• /
• 2003

SVM은 일반화된 높은 분류 정확률을 보인다. 그러나, SVM은 데이터의 양이 커질수록 높은 시간 공간적 복잡성 때문에 근사화 알고리즘(Approximation Algorithm)을 이용한다. 이러한 접근 방법은 실제구현에서 높은 시간 공간적 복잡성을 요구하여 분류 정확률과 효율성을 낮아지게 한다. 따라서, 본 논문은 SVM을 앙상블 구조로 구성하여 분류 정확률을 높이고, 분류자의 최적 하이퍼플랜(Optimal Hyperplane)결정을 위해 마진 벡터만을 이용하여 시간 공간적 문제를 해결하였다. 실험결과, 본 논문에서 제시한 방법이 단일 SVM을 이용한 방법보다 높은 분류 정확률과 높은 효율성을 가짐을 보여준다...

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.468-472
• /
• 1992

In this paper, we classified electromyographic(EMG) signal for prothesis control using neural network. For this study fast Fourier transform(FFT) with ensemble averaged spectrum is applied to two-channeI EMG signal for biceps and triceps. We used the three layer network. And a cumulative back-propagation algorithm is used for classification of six arm functions, flexion and extension of elbow and pronation and supination of the forearm and abduction and adduction of wrist.

• International Journal of Contents
• /
• 제7권3호
• /
• pp.1-5
• /
• 2011

It has been an interesting challenge to find a good classifier for imbalanced data, since it is pervasive but a difficult problem to solve. However, classifiers developed with the assumption of well-balanced class distributions show poor classification performance for the imbalanced data. Among many approaches to the imbalanced data problems, the algorithmic level approach is attractive because it can be applied to the other approaches such as data level or ensemble approaches. Especially, the error back-propagation algorithm using the target node method, which can change the amount of weight-updating with regards to the target node of each class, attains good performances in the imbalanced data problems. In this paper, we analyze the relationship between two optimal outputs of neural network classifier trained with the target node method. Also, the optimal relationship is compared with those of the other error function methods such as mean-squared error and the n-th order extension of cross-entropy error. The analyses are verified through simulations on a thyroid data set.

• 대한기계학회논문집
• /
• 제19권3호
• /
• pp.751-762
• /
• 1995

The snapshot method is introduced to approximate the coherent structures of planar jet flow. The numerical simulation of instantaneous flow field is analyzed by SIMPLE algorithm. An ensemble of realizations is collected using a sampling condition that corresponds to the passage of a large scale vortex at positions 4 and 6 diameters downstream from the nozzle. With snapshot mothod we could treat the data efficiently and approximate coherent structures inhered in the planar jet flow successfully 94% of total turbulent kinetic energy with 10 terms of Karhunen-Loeve expansions. Finally, In accordance with the recent trend to try to explain and model turbulence phenomena with the existence of coherent structures, in the present study, we express the underlying coherent structures of planar jet flow in the minimum number of modes by calculating Karhunen-Loeve expansions in order to improve to understanding of jet flow and to make the information storage and management in computers easier.

• 대한기계학회논문집A
• /
• 제31권8호
• /
• pp.826-832
• /
• 2007

Fully flexible cell preserves Hamiltonian in structure so that the symplectic time integrator is applicable to the equations of motion. In the direct formulation of fully flexible cell N-Sigma-T ensemble, a generalized leapfrog time integration (GLF) is applicable for fully flexible cell simulation, but the equations of motion by GLF has structure of implicit algorithm. In this paper, the time integration formula is derived for the fully flexible cell molecular dynamics simulation by using the splitting time integration. It separates flexible cell Hamiltonian into terms corresponding to each of Hamiltonian term. Thus the simple and completely explicit recursion formula was obtained. We compare the performance and the result of present splitting time integration with those of the implicit generalized leapfrog time integration.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2000년도 봄 학술발표논문집 Vol.27 No.1 (B)
• /
• pp.226-228
• /
• 2000

최근 제안된 관찰학습(OLA: Observational Learning Algorithm)은 committee를 구성하는 각각의 학습 모델들이 다른 학습 모델들을 관찰함으로써 얻어진 가상데이터를 실제 데이터와 결합시켜 학습에 이용하는 방법이다. 본 논문에서는, UCI 데이터 셋의 분류(classification)와 예측(regression)문제에 대하여 다층 퍼셉트론을 학습 모델로 설정하고, 이에 대하여 OLA와 bagging, boosting의 성능을 비교, 분석하였다.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.433-438
• /
• 2007

Mechanical behavior of copper Nanowire is investigated, An FCC Nanowire model composed of 1,408 atoms is used for NID simulation, Simulations are performed within NVT ensemble setting without periodic boundary conditions, Nose-Poincare MD algorithm is employed to guarantee preservation of Hamiltonian. Numerical tensile tests are carried out with constant strain rate, Stress-strain curve is constructed from the calculated Cauchy stresses and specified strain values, Non-linear behavior appears around $\varepsilon$=0.064, At this instance, starting of structural reorientations are observed.

• Journal of Electrical Engineering and Technology
• /
• 제8권4호
• /
• pp.813-823
• /
• 2013

On-line monitoring system is important for high voltage vacuum circuit breakers (HVCBs) in operation condition assessment and fault diagnosis. A distributed multilayer system with client/server architecture is developed on rated voltage 10kV HVCB with spring operating mechanism. It can collect data when HVCB switches, calculate the necessary parameters, show the operation conditions and provide abundant information for fault diagnosis. Ensemble empirical mode decomposition (EEMD) is used to detect the singular point which is regarded as the contact moment. This method has been applied to on-line monitoring system successfully and its satisfactory effect has been proved through experiments. SVM and FCM are both effective methods for fault diagnosis. A combinative algorithm is designed to judge the faults of HVCB's operating mechanism. The system's precision and stability are confirmed by field tests.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2327-2347
• /
• 2018

Human actions can be recognized from depth sequences. In the proposed algorithm, we initially construct depth, motion maps (DMM) by projecting each depth frame onto three orthogonal Cartesian planes and add the motion energy for each view. The body part of the action (BPoA) is calculated by using bounding box with an optimal window size based on maximum spatial and temporal changes for each DMM. Furthermore, feature vector is constructed by using BPoA for each human action view. In this paper, we employed an ensemble based learning approach called Rotation Forest to recognize different actions Experimental results show that proposed method has significantly outperforms the state-of-the-art methods on Microsoft Research (MSR) Action 3D and MSR DailyActivity3D dataset.