• Communications for Statistical Applications and Methods
• /
• 제18권2호
• /
• pp.165-170
• /
• 2011

Support vector quantile regression(SVQR) is capable of providing a good description of the linear and nonlinear relationships among random variables. In this paper we propose a sparse SVQR to overcome a limitation of SVQR, nonsparsity. The asymmetric e-insensitive loss function is used to efficiently provide sparsity. The experimental results are presented to illustrate the performance of the proposed method by comparing it with nonsparse SVQR.

• International Journal of Air-Conditioning and Refrigeration
• /
• 제13권3호
• /
• pp.145-151
• /
• 2005

A thermally asymmetric straight rectangular fin is analysed and optimized using the two-dimensional separation of variables method. The optimum heat loss is presented as a function of bottom to top Biot number ratio, fin base length and top Biot number. Decreasing rate of the optimum fin length with the increase of the fin base length is listed. The optimum fin tip length is shown as a function of bottom to top Biot number ratio, fin base length and tip to top Biot number ratio. One of the results shows that the optimum heat loss and the actual optimum fin length decrease while the optimum fin tip length increases as the fin base length increases.

• Communications for Statistical Applications and Methods
• /
• 제14권2호
• /
• pp.389-399
• /
• 2007

In this paper, Bayes estimates for the parameters k, c and reliability function of the Burr type XII model based on a type II censored samples under asymmetric loss functions viz., LINEX and SQUAREX loss functions are obtained. An approximation based on the Laplace approximation method (Tierney and Kadane, 1986) is used for obtaining the Bayes estimators of the parameters and reliability function. In order to compare the Bayes estimators under squared error loss, LINEX and SQUAREX loss functions respectively and the maximum likelihood estimator of the parameters and reliability function, Monte Carlo simulations are used.

• Communications for Statistical Applications and Methods
• /
• 제12권1호
• /
• pp.19-27
• /
• 2005

The present paper obtains Bayes estimators for the probability p(Y

• 한국추진공학회지
• /
• 제16권1호
• /
• pp.45-54
• /
• 2012

위 측면 표면 기울기가 변화하는 비대칭 사다리꼴 핀의 최적화가 2차원 해석적 방법을 사용하여 수행된다. 고정된 핀 바닥 높이에 대하여 최적 열손실, 핀 길이 그리고 유용도가 내부유체 대류특성계수, 핀 바닥 두께, 핀 바닥 높이, 핀 형상계수 그리고 주위 대류특성계수의 함수로 나타내어진다. 이러한 최적화 절차를 위해서 핀으로부터의 최대 열손실 값의 95%를 최적 열손실 값으로 정의하였다. 결과 중 하나는 최적 열 손실과 유용도는 핀 형상계수의 변화에 독립적으로 보이는 반면 최적 핀 길이는 핀 형상계수가 증가함에 따라 거의 선형적으로 감소함을 보여주고 있다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제4권2호
• /
• pp.153-163
• /
• 2000

The non-dimensional convective heat losses from each surface are investigated as a function of the non-dimensional fin length, width and the ratio of upper surface Biot number to bottom surface Biot number (Bi2/Bi1) using the three-dimensional separation of variables method. Heat loss ratio in view of each surface with the variation of Bi2/Bi1 is presented. The variation of the non-dimensioal temperare profile along the fin center line for a thermally asymmetric conditions is also presented.

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.49-54
• /
• 2024

데이터 불균형은 분류 문제에서 흔히 마주치는 문제로, 데이터셋 내의 클래스간 샘플 수의 현저한 차이에서 기인한다. 이러한 데이터 불균형은 일반적으로 분류 모델에서 과적합, 과소적합, 성능 지표의 오해 등의 문제를 야기한다. 이를 해결하기 위한 방법으로는 Resampling, Augmentation, 규제 기법, 손실 함수 조정 등이 있다. 본 논문에서는 손실 함수 조정에 대해 다루며 특히, 불균형 문제를 가진 Multi-Class 블랙박스 동영상 데이터에서 여러 구성의 손실 함수(Cross Entropy, Balanced Cross Entropy, 두 가지 Focal Loss 설정: 𝛼 = 1 및 𝛼 = Balanced, Asymmetric Loss)의 성능을 I3D, R3D_18 모델을 활용하여 비교하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제14권3호
• /
• pp.631-639
• /
• 2003

Bayes estimates of reliability for the stress-strength system are obtained with respect to LINEX loss function. A reference prior distribution of the reliability is derived and Bayes estimates of the reliability are also obtained. These Bayes estimates are compared with corresponding estimates under squared-error loss function.

• 응용통계연구
• /
• 제7권2호
• /
• pp.131-143
• /
• 1994

엔트로피와 스타인손실들을 포함한 비대칭 손실함수아래서 포아송 평균이 사전분포 함수를 갖는 경우에서 베이즈적, 경험적 베이즈 추정치들의 집합을 구하였다. 또한 Efron과 Morris의 접근방법에 의하여 앞에서 제안된 추정치와 기존의 추정치들의 상대절약 손실량을 모의실험을 통하여 비교하였다.

• 한국입자에어로졸학회지
• /
• 제10권1호
• /
• pp.27-31
• /
• 2014

A simple bimodal model has been developed to analyze charged particle coagulation by modifying previously suggested bimdal model for evolution of particle generation and growth. In the present model, two monodisperse modes are used and 40 charge nodes are assigned to each mode to account both change of the particle size and charge distribution. In addition, we also implemented the effect of electrostatic dispersion loss in the present model. Based on the developed model, we analyzed coagulation of asymmetric bipolar charged particles by computing evolutions of particle number concentration, geometric mean diameter of particles, charge asymmetric ratio and geometric standard deviation of particle size distribution for various initial charge asymmetric ratios. The number concentration of asymmetric bipolar charged particles decreases faster than that of neutral particles but that does not give faster growth of particles since the electrostatic dispersion loss overwhelms particle growth by coagulation.