• Communications for Statistical Applications and Methods
• /
• 제27권4호
• /
• pp.469-486
• /
• 2020

Entropy is an important term in statistical mechanics that was originally defined in the second law of thermodynamics. In this paper, we consider the maximum likelihood estimation (MLE), maximum product spacings estimation (MPSE) and Bayesian estimation of the entropy of an inverse Weibull distribution (InW) under a generalized type I progressive hybrid censoring scheme (GePH). The MLE and MPSE of the entropy cannot be obtained in closed form; therefore, we propose using the Newton-Raphson algorithm to solve it. Further, the Bayesian estimators for the entropy of InW based on squared error loss function (SqL), precautionary loss function (PrL), general entropy loss function (GeL) and linex loss function (LiL) are derived. In addition, we derive the Lindley's approximate method (LiA) of the Bayesian estimates. Monte Carlo simulations are conducted to compare the results among MLE, MPSE, and Bayesian estimators. A real data set based on the GePH is also analyzed for illustrative purposes.

• Journal of applied mathematics & informatics
• /
• 제2권1호
• /
• pp.33-40
• /
• 1995

Entropy loss is derived by the scale parameter of Rayleigh distribution. Under this entropy loss we obtain the best invariant estimators and the Bayes estimators of the scale parameter. Also we compare MLE with the proposed estimators.

• 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.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.40-44
• /
• 2023

The defect detection based on deep learning requires minimal loss and high accuracy to pinpoint product defects. In this paper, we confirm the loss rate of deep learning training based on disc-shaped artificial scaffold images. It is intended to compare the performance of Cross-Entropy functions used in object detection algorithms. The model was constructed using normal, defective artificial scaffold images and category cross entropy and sparse category cross entropy. The data was repeatedly learned five times using each loss function. The average loss rate, average accuracy, final loss rate, and final accuracy according to the loss function were confirmed.

• Journal of the Korean Data and Information Science Society
• /
• 제28권3호
• /
• pp.659-668
• /
• 2017

The inverse Weibull distribution (IWD) can be readily applied to a wide range of situations including applications in medicines, reliability and ecology. It is generally known that the lifetimes of test items may not be recorded exactly. In this paper, therefore, we consider the maximum likelihood estimation (MLE) and Bayes estimation of the entropy of a IWD under generalized progressive hybrid censoring (GPHC) scheme. It is observed that the MLE of the entropy cannot be obtained in closed form, so we have to solve two non-linear equations simultaneously. Further, the Bayes estimators for the entropy of IWD based on squared error loss function (SELF), precautionary loss function (PLF), and linex loss function (LLF) are derived. Since the Bayes estimators cannot be obtained in closed form, we derive the Bayes estimates by revoking the Tierney and Kadane approximate method. We carried out Monte Carlo simulations to compare the classical and Bayes estimators. In addition, two real data sets based on GPHC scheme have been also analysed for illustrative purposes.

• 한국인공지능학회지
• /
• 제5권1호
• /
• pp.1-9
• /
• 2017

Recently, the Q-Learning algorithm, which is one kind of reinforcement learning, is mainly used to implement artificial intelligence system in combination with deep learning. Many research is going on to improve the performance of Q-Learning. Therefore, purpose of theory try to improve the performance of Q-Learning algorithm. This Theory apply Cross Entropy Error to the loss function of Q-Learning algorithm. Since the mean squared error used in Q-Learning is difficult to measure the exact error rate, the Cross Entropy Error, known to be highly accurate, is applied to the loss function. Experimental results show that the success rate of the Mean Squared Error used in the existing reinforcement learning was about 12% and the Cross Entropy Error used in the deep learning was about 36%. The success rate was shown.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.709-710
• /
• 2024

Super resolution에서 High-frequency Details를 개선하는 것이 최근 문제이다. 기존에는 Super resolution을 Regression task로 접근하므로써 L2 Loss를 사용하여 이미지가 흐릿하게 되었다. 이를 해결하기위해, Classification task로 바꾸므로써 Cross Entropy Loss을 적용하여 Cross-entropy Super-resolution (CS)를 설계한다. CS를 통해 선명도와 Details이 개선되지만, 저주파의 CE Loss 학습으로인한 Black Artifacts가 발생한다. 그래서, L2 Loss는 저주파와 같이 큰 신호에 더 초점을 맞추므로, 성능 개선을 위해 저주파를 L2 Loss에서, 고주파를 CE Loss에서 학습시킨 Frequency-specific Cross-entropy Super-resolution (FCS)을 제안한다. 우리는 왜곡에 강하며 Human의 인식과 유사한 측정지표인 Learned Perceptual Image Patch Similarity (LPIPS)로 평가한다. 실험한 모든 데이터 셋에서 우리의 FCS는 Baseline보다 LPIPS가 약 1.7배 정도 개선되었다.

• Journal of applied mathematics & informatics
• /
• 제3권1호
• /
• pp.55-64
• /
• 1996

Let $X_1, ....$X_P be p($\geq$2) independent random variables, where each X1 has a gamma distribution with $k_i and ${\heta}_i$. The problem is to simultaneously estimate p gammar parameters ${\heta}_i$ under entropy loss where the parameters are believed priori. Hierarchical bayes(HB) and empirical bayes(EB) estimators are investigated. Next computer simulation is studied to compute the risk percentage improvement of the HB, EB and the estimator of Dey et al.(1987) compared to MVUE of ${\heta}$.

• 정보보호학회논문지
• /
• 제17권2호
• /
• pp.73-81
• /
• 2007

본 논문에서는 스트림 암호 MICKEY의 두 가지 취약점에 대해서 논한다. 첫째, time-memory-data tradeoff 공격이 가능함을 보인다. 둘째, 상태 갱신 함수 (state update function)를 반복해서 적용할수록 내부 상태 (internal state)의 엔트로피가 감소하므로 다르게 시작된 키 스트림이 마침내 같아질 수 있다.

• 설비공학논문집
• /
• 제17권5호
• /
• pp.410-417
• /
• 2005

The cooling performance of a transcritical $CO_{2}$ cycle varies significantly with a variation of refrigerant charge amount. In this study, the performance of the $CO_{2}$ system was measured and analyzed by varying refrigerant charge amount at a standard test condition. Besides, the losses of the major components in the $CO_{2}$ system were estimated by evaluating entropy generation with refrigerant charge amount. The losses in the expansion device and the gascooler show the major portion of the total loss. For undercharging conditions, the expansion loss dominates the overall system performance, while the gascooler loss increases significantly with an increase of refrigerant charge amount.