• 전기학회논문지
• /
• 제60권9호
• /
• pp.1684-1692
• /
• 2011

Recently, several vector hysteresis models such as vector Preisach, vector Jiles-Atherton and dynamic E&S model have been proposed to describe vector magnetic properties of electrical steel sheets. However, it is still difficult to find an adequate vector hysteresis model in finite element application for both the Non-oriented and Grain-oriented electrical steel sheets under alternating and rotating field conditions. In this paper, an improved E&S vector hysteresis model is suggested to describe the vector magnetic properties of both Non-oriented and Grain-oriented electrical steel sheets under various magnetic field conditions including alternating and rotating magnetic field conditions. The validity of the proposed model is tested through comparisons with the experimental results under various magnetic field conditions.

• 한국지능시스템학회논문지
• /
• 제13권6호
• /
• pp.655-660
• /
• 2003

일반적으로 Support Vector Machine은 이진 분류 모형에 있어 우수한 성능을 보이지만 모델의 한계로 인하여 다중 패턴의 분류 문제에는 쉽게 적용하기가 어렵다. 본 논문에서는 이진 분류를 포함한 다중 레이블을 갖는 데이터의 정확한 패턴 분류를 위하여 Zhu가 제안한 Import Vector Machine에 커널 Bagging 전략을 적용하여 분류의 정확성을 향상시키기 위한 Import Vector Voting 모형을 제안한다. 이러한 Import Vector Voting 모형은 다수의 커널함수를 적용한 결과 중에서 가장 성능이 우수한 커널함수를 이용하여 최종 분류를 수행하기 위한 voting 전략으로 사용한다. 본 논문에서 제안하는 Import Vector Voting 모형은 이진 분류를 포함한 3개 이상의 다중 패턴 데이터에 대한 분류 문제에 있어 매우 정확한 분류 성능을 보임을 실험을 통해 입증한다.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2014년도 추계 학술논문 발표대회
• /
• pp.88-89
• /
• 2014

A vector-photo is a photography which contain image and 5W1H information. Objects pictured and an image in a vector-photo can be linked by 5W1H information in the vector-photo. This study discuss a positioning module to link between vector-photos and 3D BIM model. The module developed in this study can be utilized in a system that can link the vector-photos with objects in BIM model.

• Journal of Information Processing Systems
• /
• 제20권2호
• /
• pp.263-272
• /
• 2024

A model based on genetic algorithm optimization, GA-SVM, is proposed to warn university students of their status. This model improves the predictive effect of support vector machines. The genetic optimization algorithm is used to train the hyperparameters and adjust the kernel parameters, kernel penalty factor C, and gamma to optimize the support vector machine model, which can rapidly achieve convergence to obtain the optimal solution. The experimental model was trained on open-source datasets and validated through comparisons with random forest, backpropagation neural network, and GA-SVM models. The test results show that the genetic algorithm-optimized radial basis kernel support vector machine model GA-SVM can obtain higher accuracy rates when used for early warning in university learning.

• 전기학회논문지
• /
• 제61권12호
• /
• pp.1813-1819
• /
• 2012

This paper presents vector magnetic properties of an electrical steel sheet (ESS) employed for electric machine and iron loss analysis considering the vector magnetic properties of the ESS. The vector magnetic properties of the ESS are measured by using a two-dimensional single sheet tester and modeled by an E&S vector hysteresis model to be applied to finite element method. The finite element analysis considering the vector magnetic properties is applied to iron loss analysis of a three-phase induction motor model, and the influences of the vector magnetic properties on the iron loss distribution are verified by comparing with numerical results from a typical B-H curve model.

• 한국산업정보학회논문지
• /
• 제9권1호
• /
• pp.36-42
• /
• 2004

본 논문은 벡터모델과 확률모델의 성능 비교에 관한 연구이다. 벡터모델로써는 잠재적 의미를 적용한 검색 결과를 찾기 위해 사용되는 LSI 모델을 이용하였다. 확률모델로써는 현재 상용화 단계에 있는 콘도르 정보검색 시스템을 적용하였다. 각 모델 시스템의 검색 성능 비교를 위한 실험은 사용자가 입력한 원래 질의어에 관한 검색 결과를 바탕으로 성능을 비교한 후에, 사전적 의미를 적용한 확장 질의어에 대한 검색 결과를 추가하여 비교하였다. 본 연구에서는 입력된 질의어와 관련된 용어를 추가하여 검색하였을 경우, 확률모델에 비해 벡터모델에서 성능이 대부분의 질의어에 대해서 향상됨을 보인다.

• 정보기술과데이타베이스저널
• /
• 제3권2호
• /
• pp.75-96
• /
• 1996

This study is intended to compare the effectiveness of the neural network inductive learning model with a vector space model in information retrieval. As a result, searches responding to incomplete queries in the neural network inductive learning model produced a higher precision and recall as compared with searches responding to complete queries in the vector space model. The results show that the hybrid methodology of integrating an inductive learning technique with the neural network model can help solve information retrieval problems that are the results of inconsistent indexing and incomplete queries--problems that have plagued information retrieval effectiveness.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제52권2호
• /
• pp.87-92
• /
• 2003

This paper presents a flux estimator for the sensorless vector control of induction motors. The proposed method utilize the combination of the voltage model based on stator equivalent model and the current model based on rotor equivalent model, which enables stable estimation of rotor flux in high speed region and in low speed region. The dynamic performance of proposed method is verified through the experiment. The experimental results show that motors ran easily start even under 150[%] load condition and operate continuously below 0.5[Hz].

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.679-682
• /
• 1997

This paper presents finite element analysis algorithm combined with vector hysteresis model for accurate analysis of the hysteresis motor. Magnetization-dependent vector model is adapted to calculate the vector magnetization. That is to say, from the magnitude and direction of the magnetic field intensity, the magnetization of each ring element is computed by the vector model. By comparing the simulation results with the experimental ones, it is found that good results are obtained.

• Journal of the Korean Statistical Society
• /
• 제34권4호
• /
• pp.345-366
• /
• 2005

This paper considers the cointegrating vector estimator in the error correction model with stationary covariates, which combines the stationary vector autoregressive model and the nonstationary error correction model. The cointegrating vector estimator is shown to follow the locally asymptotically mixed normal distribution. The variance of the estimator depends on the co­variate effect of stationary regressors, and the asymptotic efficiency improves as the magnitude of the covariate effect increases. An economic application of the money demand equation is provided.