• The Journal of the Acoustical Society of Korea
• /
• v.30 no.6
• /
• pp.324-329
• /
• 2011

In this paper, we propose a novel approach to improve the performance of a statistical model-based voice activity detection (VAD) which is based on the conditional maximum a posteriori (CMAP) with deviation. In our approach, the VAD decision rule is expressed as the geometric mean of likelihood ratios (LRs) based on adapted threshold according to the speech presence probability conditioned on both the speech activity decisions and spectral deviation in the pervious frame. Experimental results show that the proposed approach yields better results compared to the CMAP-based VAD using the LR test.

• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.63-73
• /
• 2002

The one of analytic imputation technique involving conditional means was mentioned by Schafer and Schenker(2000). And their derivations are based on asymptotic expansions of point estimator and their associated variance estimator, and the result of imputation can be thought of as first-order approximations to the estimators. Specially in this paper, we are presenting the method of estimating a Binomial proportion with Bayesian approach of imputed conditional means. That is, instead of using maximum likelihood(ML) estimator to estimate a Binomial proportion, in general, we use the Bayesian estimators and will show the result of estimated Imputed conditional means.

• Communications for Statistical Applications and Methods
• /
• v.22 no.6
• /
• pp.615-624
• /
• 2015

We consider the estimation of seasonal cointegration in the presence of conditional heteroskedasticity (CH) using a feasible generalized least squares method. We capture cointegrating relationships and time-varying volatility for long-run and short-run dynamics in the same model. This procedure can be easily implemented using common methods such as ordinary least squares and generalized least squares. The maximum likelihood (ML) estimation method is computationally difficult and may not be feasible for larger models. The simulation results indicate that the proposed method is superior to the ML method when CH exists. In order to illustrate the proposed method, an empirical example is presented to model a seasonally cointegrated times series under CH.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.429-431
• /
• 2012

하이퍼네트워크를 학습하는 기존의 방법은 데이터의 분포를 학습하기 위하여 주로 하이퍼에지의 적절한 조합을 찾는데 초점을 맞추었다. 반면 본 논문에서는 주어진 하이퍼에지의 조합 내에서 가중치를 조절하여 데이터의 분포를 학습하도록 하는 방법을 제안한다. 이 방법은 분류 문제에서 하이퍼네트워크가 표현하고 있는 클래스 y에 대한 데이터 x의 조건부 우도(Conditional Likelihood)를 대화하는 방식으로 학습을 진행한다. 본 논문에서는 제안된 학습 방법이 기존의 학습 방법보다 개선된 학습 성능을 보일 뿐만아니라, 제안된 가중치 학습 방법이 기존의 가중치 학습 방법을 포함하는 관계임을 논증한다.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2002.03b
• /
• pp.49-59
• /
• 2002

이 연구에서는 강원도 삼척시를 대상으로 산불취약지역 분석모델을 개발하고, 개발된 분석모델을 기반으로 산불취약지역을 표출하였으며, 이를 위한 전산프로그램을 개발하였다. 산불취약지역 공간분석자료로는 NGIS 사업을 통해 구축된 1/25천 축척의 수치지형도, 수치임상도 그리고 과거 산불발화위치자료를 사용하였다. 산불발화위치에 대한 공간적 분포특성(지형, 임상, 접근성)을 기반으로 모델을 설정하였으며, 공간분석은 간단하면서도 일반인들이 이해하기 쉬운 Conditional probability, Likelihood ratio 방법을 사용하였다. 그리고 각각의 모델에 대한 검증(cross validation)을 실시하였다. 모델 검증방법으로는 과거 산불발화위치자료를 발생시기에 따라 두 개의 그룹으로 나누어 하나는 예측을 위한 자료로 사용하고, 다른 하나는 검증을 위한 자료로 사용하였다. 모델별 예측성능은 prediction rate curve를 비교·분석하여 판단하였다. 삼척시를 대상으로 한 예측성능에서 Likelihood ratio 모델이 Conditional probability 모델보다 더 낳은 결과를 보였다. 산불취약지역 분석기술로 작성된 상세 산불취약지역지도와 현재 산림청에서 예보하고 있는 전국단위의 산불발생위험지수와 함께 상호보완적으로 사용한다면 산불취약지역에 대한 산불감시인력 및 감시시설의 효율적인 배치를 통하여 일선 시군 또는 읍면 산불예방업무의 효율성이 한층 더 증대될 것으로 기대된다.

• Communications for Statistical Applications and Methods
• /
• v.17 no.3
• /
• pp.441-450
• /
• 2010

In this paper we consider the problem of forecasting binomial time series, modelled by the binomial autoregressive model. This paper considers proposed by McKenzie (1985) and is extended to a higher order by $Wei{\ss}$(2009). Since the binomial autoregressive model is a Markov chain, we can apply the earlier work of Bu and McCabe (2008) for integer valued autoregressive(INAR) model to the binomial autoregressive model. We will discuss how to compute the h-step-ahead forecast of the conditional probabilities of $X_{T+h}$ when T periods are used in fitting. Then we obtain the maximum likelihood estimator of binomial autoregressive model and use it to derive the maximum likelihood estimator of the h-step-ahead forecast of the conditional probabilities of $X_{T+h}$. The methodology is illustrated by applying it to a data set previously analyzed by $Wei{\ss}$(2009).

• Communications for Statistical Applications and Methods
• /
• v.22 no.5
• /
• pp.507-518
• /
• 2015

It is not easy to select a linear mixed model since the main interest for model building could be different and the number of parameters in the model could not be clearly defined. In this paper, performance of conditional Akaike Information Criteria and its bias-corrected version are compared with marginal Bayesian and Akaike Information Criteria through a simulation study. The results from the simulation study indicate that bias-corrected conditional Akaike Information Criteria shows promising performance when candidate models exclude large models containing the true model, but bias-corrected one prefers over-parametrized models more intensively when a set of candidate models increases. Marginal Bayesian and Akaike Information Criteria also have some difficulty to select the true model when the design for random effects is nested.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.1
• /
• pp.251-261
• /
• 2004

The paper focuses primarily on the standard linear multiple regression model where the parameter of interest is a ratio of two regression coefficients. The general model includes the calibration model, the Fieller-Creasy problem, slope-ratio assays, parallel-line assays, and bioequivalence. We provide an orthogonal transformation (cf. Cox and Reid (1987)) of the original parameter vector. Also, we give some remarks on the difficulties associated with likelihood based confidence interval.

• Communications for Statistical Applications and Methods
• /
• v.4 no.1
• /
• pp.271-280
• /
• 1997

It should be noted that the number of observation in the up-and-down procedure is a random variable. Therefore, We need to justify the employment of the conditional likelihood even in the above situation and show the algorithm of simulation. Also, the strategy of halving or widening the level space in modified up-and-down method is suggested.

• Communications of the Korean Mathematical Society
• /
• v.21 no.2
• /
• pp.363-374
• /
• 2006

A new bivariate beta distribution based on the Appell function of the third kind is introduced. Various representations are derived for its product moments, marginal densities, marginal moments, conditional densities and conditional moments. The method of maximum likelihood is used to derive the associated estimation procedure as well as the Fisher information matrix.