• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권5_6호
• /
• pp.570-578
• /
• 2003

최대 엔트로피 모델은 자연언어를 모델링하기 위한 좋은 방법이다. 하지만, 최대 엔트로피 모델을 전치사구 접속과 같은 실제 언어 문제에 적용할 때, 자질 선택과 계산 복잡도의 두 가지 문제가 발생한다. 본 논문에서는, 이런 문제와 자연언어 자원에 존재하는 불균형 데이터 문제를 해결하기 위한 최대 엔트로피 부스팅 모델(maximum entropy boosting model)을 제시하고, 이를 영어의 전치사구 접속과 품사 결정 모호성 해소에 적용한다. Wall Street Journal 말뭉치에 대한 실험 결과, 문제의 모델링에 아주 작은 노력을 들였음에도 불구하고, 전치사구 접속 문제에 대해 84.3%의 정확도와 품사 결정 문제에 대해 96.78%의 정확도를 보여 지금까지 알려진 최고의 성능과 비슷한 결과를 보였다.

• 수산해양기술연구
• /
• 제54권1호
• /
• pp.38-53
• /
• 2018

The purpose of this study is to estimate potential yield (PY) for Korean west coast fisheries using the holistic production method (HPM). HPM involves the use of surplus production models to apply input data of catch and standardized fishing efforts. HPM compared the estimated parameters of the surplus production from four different models: the Fox model, CYP model, ASPIC model, and maximum entropy model. The PY estimates ranged from 174,232 metric tons (mt) using the CYP model to 238,088 mt using the maximum entropy model. The highest coefficient of determination ($R^2$), the lowest root mean square error (RMSE), and the lowest Theil's U statistic (U) for Korean west coast fisheries were obtained from the maximum entropy model. The maximum entropy model showed relatively better fits of data, indicating that the maximum entropy model is statistically more stable and accurate than other models. The estimate from the maximum entropy model is regarded as a more reasonable estimate of PY. The quality of input data should be improved for the future study of PY to obtain more reliable estimates.

• 대한기계학회논문집A
• /
• 제30권7호
• /
• pp.787-793
• /
• 2006

Recently kriging model has been widely used in the DACE (Design and Analysis of Computer Experiment) because of prominent predictability of nonlinear response. Since DACE has no random or measurement errors contrast to physical experiment, space filling experimental design that distributes uniformly design points over whole design space should be employed as a sampling method. In this paper, we examine the maximum entropy experimental design that reveals the space filling strategy in which defines the maximum entropy based on Gaussian or exponential. The influence of these two correlation functions on space filling design and their model parameters are investigated. Based on the exploration of numerous numerical tests, enhanced maximum entropy design based on exponential correlation function is suggested.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2002년도 가을 학술발표논문집 Vol.29 No.2 (2)
• /
• pp.670-672
• /
• 2002

Park과 Zhang은 최대 엔트로피 모델(maximum entropy model)을 실제 자연언어 처리에 적용함에 있어서 나타날 수 있는 여러가지 문제를 해결하기 위한 최대 엔트로피 모델(maximum entropy boosting model)을 제시하여 문서 단위화(text chunking)에 성공적으로 적용하였다. 최대 엔트로피 부스팅 모델은 쉬운 모델링과 높은 성능을 보이는 장점을 가지고 있다. 본 논문에서는 최대 엔트로피 부스팅 모델을 영어 전치사 접속 모호성 해소에 적용한다. Wall Street Journal 말뭉치에 대한 실험 결과, 아주 작은 노력을 들였음에도 84.3%의 성능을 보여 지금까지 알려진 최고의 성능과 비슷한 결과를 보였다.

• Communications for Statistical Applications and Methods
• /
• 제4권2호
• /
• pp.497-505
• /
• 1997

We attempt to get a probabilistic model of a queueing system in the maximum entropy condition. Applying the maximum entropy principle to the queueing system, we obtain the most uncertain probability model compatible with the available information expressed by moments.

• 수산해양교육연구
• /
• 제18권1호
• /
• pp.19-30
• /
• 2006

For fishery stock assessment and optimum sustainable yield of anchovy in Korea, surplus production(SP) models and a maximum entropy(ME) model are employed in this paper. For determining appropriate models, five traditional SP models-Schaefer model, Schnute model, Walters and Hilborn model, Fox model, and Clarke, Yoshimoto and Pooley (CYP) model- are tested for effort and catch data of anchovy that occupies 7% in the total fisheries landings of Korea. Only CYP model of five SP models fits statistically significant at the 10% level. Estimated intrinsic growth rates are similar in both CYP and ME models, while environmental carrying capacity of the ME model is quite greater than that of the CYP model. In addition, the estimated maximum sustainable yield(MSY), 213,287 tons in the ME model is slightly higher than that of CYP model (198,364 tons). Biomass for MSY in the ME model, however, is calculated 651,000 tons which is considerably greater than that of the CYP model (322,881 tons). It is meaningful in that two models are compared for noting some implications about any significant difference of stock assessment and their potential strength and weakness.

• Communications for Statistical Applications and Methods
• /
• 제10권3호
• /
• pp.909-917
• /
• 2003

Although many classification models have been used to classify binary data, none of the classification models dominates all varying circumstances depending on the number of variables and the size of data(Asparoukhov and Krzanowski (2001)). This paper proposes a classification model which uses information on marginal distributions of sub-variables and its maximum entropy distribution. Classification experiments by using simulation are discussed.

• Journal of Communications and Networks
• /
• 제5권1호
• /
• pp.65-72
• /
• 2003

Internet roundtrip delay/time (RTT) prediction plays an important role in detecting packet losses in reliable transport protocols for traditional web applications and determining proper transmission rates in many rate-based TCP-friendly protocols for Internet-based real-time applications. The widely adopted autoregressive and moving average (ARMA) model with fixed-parameters is shown to be insufficient for all scenarios due to its intrinsic limitation that it filters out all high-frequency components of RTT dynamics. In this paper, we introduce a novel parameter-varying RTT model for Internet roundtrip time prediction based on the information theory and the maximum entropy principle (MEP). Since the coefficients of the proposed RTT model are updated dynamically, the model is adaptive and it tracks RTT dynamics rapidly. The results of our experiments show that the MEP algorithm works better than the ARMA method in both RTT prediction and RTO estimation.

• Communications for Statistical Applications and Methods
• /
• 제12권1호
• /
• pp.125-137
• /
• 2005

Many discriminant analysis models for binary data have been used in real applications, but none of the classification models dominates in all varying circumstances(Asparoukhov & Krzanowski(2001)). Lee and Hwang (2003) proposed a new classification model by using multinomial distribution with the maximum entropy estimation method. The model showed some promising results in case of small number of variables, but its performance was not satisfactory for large number of variables. This paper explores to use the iterative cross entropy minimization estimation method in replace of the maximum entropy estimation. Simulation experiments show that this method can compete with other well known existing classification models.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 추계학술대회
• /
• pp.1846-1851
• /
• 2003

Approximate optimization has become popular in engineering field such as MDO and Crash analysis which is time consuming. To accomplish efficient approximate optimization, accuracy of approximate model is very important. As surrogate model, Kriging have been widely used approximating highly nonlinear system . Because Kriging employs interpolation method, it is adequate for deterministic computer simulation. Because there are no random errors and measurement errors in deterministic computer simulation, instead of classical DOE ,space filling experiment design which fills uniformly design space should be applied. In this work, various space filling designs such as maximin distance design, maximum entropy design are reviewed. And new design improving maximum entropy design is suggested and compared.