• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 춘계학술대회
• /
• pp.981-984
• /
• 2010

우리는 본 연구에서 학습방법으로서 연속음성을 초성, 중성, 종성의 음소단위로 분할하기 위하여 인공 신경회로망의 하나인 SVMs을 사용하였으며 분할한 음소단위의 음성으로 연속음성인식에 적용하여 그 성능을 살펴보았다. 음소경계는 단 구간에서의 최대 주파수를 가진 알고리듬에 의하여 결정되며 또한 음성인식처리는 CHMM에 의하여 이루어지며 목측에 의한 분할결과와도 비교하여 살펴보았다. 시뮬레이션 결과로부터 초성의 분할성능에서 제안한 SVMs를 적용한 결과가 GMMs보다 효율적인을 알 수 있었다.

• 전기전자학회논문지
• /
• 제25권3호
• /
• pp.425-429
• /
• 2021

커넥티드 기반 자율주행 시스템에서 차량의 군집주행은 중앙 시스템의 계산량과 네트워크 트래픽 로드를 크게 감소시켜 줄 뿐만 아니라 교통흐름을 개선하는 효과도 얻을 수 있는 효율적인 교통운영모델이다. 효율적인 군집주행집단 관리를 위해서는 군집의 규모를 적절하게 유지하는 것이 중요하며 이를 위한 신규차량 및 타 군집 소속 차량의 효율적인 병합 제어가 필수적이다. 본 연구에서는 군집의 현재 규모와 차량의 우선순위에 따라 병합 요청을 수락 또는 거절하는 병합 제어 방안을 제시한다. 제안하는 방안은 마코프 체인 기반의 수학적 분석모델을 이용해 분석하고 검증하었다. 성능평가 결과 제안한 방안이 중앙 시스템의 부하를 적절하게 잘 관리하는 것을 확인할 수 있었다.

• 대한조선학회논문집
• /
• 제56권2호
• /
• pp.161-167
• /
• 2019

In general, fatigue analysis is performed by using deterministic model to estimate the optimal parameters. However, the deterministic model is difficult to clearly describe the physical phenomena of fatigue failure that contains many uncertainty factors. With regard to this, efforts have been made in this research to compare with the deterministic model and the stochastic models. Firstly, One deterministic S-N curve was derived from ordinary least squares technique and two P-S-N curves were estimated through Bayesian-linear regression model and Markov-Chain Monte Carlo simulation. Secondly, the distribution of Long-term fatigue damage and fatigue life were predicted by using the parameters obtained from the three methodologies and the long-term stress distribution.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권1호
• /
• pp.15-22
• /
• 2021

This study aims to obtain a stock investment strategy model based on the industrial sector in Indonesia Stock Exchange (IDX). This study uses IDX data for the period of January 1996 to December 2016. This study uses the Markov Regime Switching Model to identify trends in market conditions that occur in industrial sectors on IDX. Furthermore, by using the Logit Regression Model, we can see the influence of economic factors in determining trends in market conditions sectorally and the probability of trends in market conditions. This probability can be the basis for determining stock investment decisions in certain sectors. The results showed descriptively that the stocks of the consumer goods industry sector had the highest average return and the lowest standard deviation. The trend in sectoral stock market conditions that occur in IDX can be divided into two conditions, namely bullish condition (high returns and low volatility) and bearish condition (low returns and high volatility). Differences in the conditions are mainly due to differences in volatility. The use of a Logit Regression Model to produce probability of market conditions and to estimate the influence of economic factors in determining stock market conditions produces models that have varying predictive abilities.

• Journal of information and communication convergence engineering
• /
• 제20권2호
• /
• pp.79-89
• /
• 2022

To compute the mean and variance of component-based reliability software, we focused on path-based reliability analysis. System reliability depends on the transition probabilities of components within a system and reliability of the individual components as basic input parameters. The uncertainty in these parameters is estimated from the test data of the corresponding components and arises from the software architecture, failure behaviors, software growth models etc. Typically, researchers perform Monte Carlo simulations to study uncertainty. Thus, we considered a Markov chain Monte Carlo (MCMC) simulation to calculate uncertainty, as it generates random samples through sequential methods. The MCMC approach determines the input parameters from the probability distribution, and then calculates the average approximate expectations for a reliability estimation. The comparison of different techniques for uncertainty analysis helps in selecting the most suitable technique based on data requirements and reliability measures related to the number of components.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.127-127
• /
• 2021

In order to estimate parameter uncertainty of hydrological models, the consideration of the likelihood functions which provide reliable parameters of model is necessary. In this study, the Bayesian Markov Chain Monte Carlo (MCMC) method with informal likelihood functions is used to analyze the uncertainty of parameters of the SURR model for estimating the hourly streamflow of Gunnam station of Imjin basin, Korea. Three events were used to calibrate and one event was used to validate the posterior distributions of parameters. Moreover, the performance of four informal likelihood functions (Nash-Sutcliffe efficiency, Normalized absolute error, Index of agreement, and Chiew-McMahon efficiency) on uncertainty of parameter is assessed. The indicators used to assess the uncertainty of the streamflow simulation were P-factor (percentage of observed streamflow included in the uncertainty interval) and R-factor (the average width of the uncertainty interval). The results showed that the sensitivities of parameters strongly depend on the likelihood functions and vary for different likelihood functions. The uncertainty bounds illustrated the slight differences from various likelihood functions. This study confirms the importance of the likelihood function selection in the application of Bayesian MCMC to the uncertainty assessment of the SURR model.

• 응용통계연구
• /
• 제27권6호
• /
• pp.959-973
• /
• 2014

자산가격의 비대칭적 변동을 설명하기 위해 최근 비대칭적 점프확산 모형이 제안되었다. 본 논문에서는 이러한 자산가격 모형을 분석하는데 사용되는 효율적인 베이지안 방법을 제안한다. 본 논문에서 제안되는 방법은 모형 요소가 쉽게 추출되는 편의성을 희생하지 않으면서도 조건부 분포들간의 함수적 비호환성을 통해 효율성을 향상시킬 수 있는 부분붕괴 깁스 샘플러를 고안함으로써 개발되었다. 제안된 방법은 모의실험 자료에 적용되어 그 효율성을 검증하였고 1980년 9월부터 2014년 8월까지 관찰된 일별 S&P 500 자료에 적용되었다.

• Communications for Statistical Applications and Methods
• /
• 제25권5호
• /
• pp.471-488
• /
• 2018

In this paper, we propose extending proportional hazards frailty models to allow a discrete distribution for the frailty variable. Having zero frailty can be interpreted as being immune or cured. Thus, we develop a new survival model induced by discrete frailty with zero-inflated power series distribution, which can account for overdispersion. This proposal also allows for a realistic description of non-risk individuals, since individuals cured due to intrinsic factors (immunes) are modeled by a deterministic fraction of zero-risk while those cured due to an intervention are modeled by a random fraction. We put the proposed model in a Bayesian framework and use a Markov chain Monte Carlo algorithm for the computation of posterior distribution. A simulation study is conducted to assess the proposed model and the computation algorithm. We also discuss model selection based on pseudo-Bayes factors as well as developing case influence diagnostics for the joint posterior distribution through ${\psi}-divergence$ measures. The motivating cutaneous melanoma data is analyzed for illustration purposes.

• 한국농공학회지
• /
• 제36권1호
• /
• pp.63-72
• /
• 1994

The objective of the study is to develop weather generators for daily rainfall and small pan evaporation and to test the applicability with recorded data. Daily rainfall forecasting model(DRFM) was developed that uses a first order Markov chain to describe rainfall seque- nces and applies an incomplete Gamma function to predict the amount of precipitation. Daily evaporation forecasting model(DEFM) that adopts a normal distribution function to generate the evaporation for dry and wet days was also formulated. DRFM and DEFM were tested with twenty year weather data from eleven stations using Chi-square and Kolmogorov and Smirnov goodness of fit tests. The test results showed that the generated sequences of rainfall occurrence, amount of rainfall, and pan evaporation were statistically fit to recorded data from eleven, seven, and seven stations at the 5% level of significance. Generated rainfall data from DRFM were very close in frequency distri- bution patterns to records for stations all over the country. Pan evaporation for rainy days generated were less accurate than that for dry days. And the proposed models may be used as tools to provide many mathematical models with long-term daily rainfall and small pan evaporation data. An example is an irrigation scheduling model, which will be further detailed in the paper.

• 대한산업공학회지
• /
• 제21권4호
• /
• pp.609-628
• /
• 1995

This paper presents a reliability model and a data-analytic procedure for a repairable unit subject to failures due to multiple non-identifiable causes. We regard a failure cause as a state and assume the life distribution for each cause to be exponential. Then we represent the dependency among the causes by a Markov switching model(MSM) and estimate the transition probabilities and failure rates by maximum likelihood(ML) method. The failure data are incomplete due to masked causes of failures. We propose a specific version of EM(expectation and maximization) algorithm for finding maximum likelihood estimator(MLE) under this situation. We also develop statistical procedures for determining the number of significant states and for testing independency between state transitions. Our model requires only the successive failure times of a unit to perform the statistical analysis. It works well even when the causes of failures are fully masked, which overcomes the major deficiency of competing risk models. It does not require the assumption of stationarity or independency which is essential in mixture models. The stationary probabilities of states can be easily calculated from the transition probabilities estimated in our model, so it covers mixture models in general. The results of simulations show the consistency of estimation and accuracy gradually increasing according to the difference of failure rates and the frequency of transitions among the states.