• Journal of Electrical Engineering and Technology
• /
• 제12권3호
• /
• pp.1053-1063
• /
• 2017

Power prediction is critical to improve power efficiency in Smart Grids. Markov chain provides a useful tool for power prediction. With careful investigation of practical power datasets, we find an interesting phenomenon that the stochastic property of practical power datasets does not follow the Markov features. This mismatch affects the prediction accuracy if directly using Markov prediction methods. In this paper, we innovatively propose a spatial transform based data processing to alleviate this inconsistency. Furthermore, we propose an enhanced power prediction method, named by Spatial Mapping Markov-Difference (SMMD), to guarantee the prediction accuracy. In particular, SMMD adopts a second prediction adjustment based on the differential data to reduce the stochastic error. Experimental results validate that the proposed SMMD achieves an improvement in terms of the prediction accuracy with respect to state-of-the-art solutions.

• Communications for Statistical Applications and Methods
• /
• 제7권3호
• /
• pp.871-884
• /
• 2000

Using simulation, we compare the perturbation analysis estimate and the forward difference estimate for the first and second derivatives of performance measures in a Markov renewal process. We find the perturbation analysis estimate has much les mean squared error than the traditional forward difference estimate.

• 한국정보통신학회논문지
• /
• 제12권12호
• /
• pp.2253-2258
• /
• 2008

산화물 반도체 감지막이 동작온도에 따라 감응특성을 가지는 마이크로 흐름센서를 설계하기 위해서 통계적 수법에 기초한 Markov 체인 MCM을 이용하여 기초방정식을 정식화하고 마이크로 소자의 열 전달특성을 해석하였다. 계산 결과를 통하여 기존 유한차분법이 가지는 계산 정밀도와 차이가 없음을 확인하였다. 본 논문에서 제안한 Markov 체인 MCM을 활용하면 다양한 마이크로 소자의 열전달 특성과 같은 물리적 특성을 해석하고 설계하는데 유용할 것으로 판단된다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.307-308
• /
• 2007

This paper proposes a discriminative training algorithm for estimating hidden Markov model (HMM) parameters. The proposed algorithm estimates the Parameters by minimizing the p-norm of log-likelihood difference (PLD) between the utterance probability given the correct transcription and the most competitive transcription.

• 대한산업공학회지
• /
• 제38권4호
• /
• pp.249-253
• /
• 2012

This paper suggests a numerical method for valuation of American options under the Kou model (double exponential jump diffusion model). The method is based on approximation of underlying asset price using a finite-state, time-homogeneous Markov chain. We examine the effectiveness of the proposed method with simulation results, which are compared with those from the conventional numerical method, the finite difference method for PIDE (partial integro-differential equation).

• 시스템엔지니어링학술지
• /
• 제14권1호
• /
• pp.36-43
• /
• 2018

The availability of the weapon system can be analyzed through state modeling and simulation using the Markov process. In this paper, show how to analyze the availability of the weapon system and can use the Markov process to analyze the system's steady state as well as the RAM at a transient state in time. As a result of the availability analysis of tracked vehicles, the inherent availability was 2.6% and the operational availability was 1.2% The validity criterion was defined as the case where the difference was within 3%, and thus it was judged to be valid. We have identified the faulty items through graphs of the number of visits per state among the results obtained through the MPS and can use them to provide design alternatives.

• Journal of Biosystems Engineering
• /
• 제29권5호
• /
• pp.441-450
• /
• 2004

This study was performed to estimate mid and long term demands of a tractor, a rice transplanter, a combine and a grain dryer by using logistic curve function and Markov chain model. Field survey was done to decide some parameters far logistic curve function and Markov chain model. Ceiling values of tractor and combine fer logistic curve function analysis were 209,280 and 85,607 respectively. Based on logistic curve function analysis, total number of tractors increased slightly during the period analysed. New demand for combine was found to be zero. Markov chain analysis was carried out with 2 scenarios. With the scenario 1(rice price $10\%$ down and current supporting policy by government), new demand for tractor was decreased gradually up to 700 unit in the year 2012. For combine, new demand was zero. Regardless of scenarios, the replacement demand was increased slightly after 2003. After then, the replacement demand is decreased after the certain time. Two analysis of logistic owe function and Markov chain model showed the similar trend in increase and decrease for total number of tractors and combines. However, the difference in numbers of tractors and combines between the results from 2 analysis got bigger as the time passed.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1999년도 추계학술대회 논문집
• /
• pp.294-298
• /
• 1999

In this paper, through simulations, we find the second derivative SPA(Smoothed Perturbation Analysis) estimates of mean busy cycle with respect to a given parameter in a Markov renewal process which is generated by two exponential distributions. We compare these SPA estimates with the traditional SD(symetric difference) estimates.

• 전자공학회논문지
• /
• 제51권9호
• /
• pp.111-118
• /
• 2014

본 논문에서는 영상접합 조작 검출을 위한 효율적인 마코프 특징을 추출하는 방법을 제안한다. 제안 방법에서 사용하는 마코프 상태는 이산 코사인 변환 영역에서 인접한 블록간 계수의 차이로 구성되며, 블록간 대칭성을 이용하여 다양한 1차 마코프 천이확률을 접합 검출을 위한 특징으로 추출한다. 아울러 마코프 확률의 분포를 분석하여 특징의 수를 줄이는 방법을 제안한다. 추출된 특징 벡터를 SVM(support vector machine) 분류기를 이용하여 학습한 후 영상의 접합 여부를 판별한다. 실험 결과를 통하여 본 논문의 방법이 기존의 방법보다 적은 수의 특징으로 높은 영상접합 조작 결과를 보임을 확인하였다.

• 물과 미래
• /
• 제14권4호
• /
• pp.19-26
• /
• 1981

자연하천에서의 수질은 유량의 변화에 많은 영향을 받을 것으로 기대되는 바, 유량과 각 수질인자의 통계적 특성 및 유량변화와 수질인자간의 상관관계를 조사하기 위하여 자기 및 상호상관함수 power spectrum, coherence 함수 및 Markov 모형을 적용하였다. 일부 자료만이 입수 가능한 한강 하류부 인도교 지점에서의 유량, 용존산소, 전기전도도는 명백한 1년 주기와 6, 4, 3개월의 약한 주기를 가지며, 유량과 용존산소, 유량과 전도도 사이의 상관은 약하게 나타났고 상호상관함수에서 첨두가 지체 1일에서 발생하여 미약하지만 유량의 변화에 의한 영향이 1일 정도 차이로 수질인자에게 미치는 것으로 해석된다. 계열 발생 및 예측수단인 선형회귀모형의 검토에서 유량은 1차 및 2차 Markov 모형과, 용존산소와 전도도는 1차 Markov 모형과 흡사하게 나타났다.