• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.336-338
• /
• 2012

본 연구에서는 고차 데이터 분류를 위해 순차적 베이지만 샘플링 기반의 진화연산 기법을 이용한 하이퍼네트워크 모델의 학습 알고리즘을 제시한다. 제시하는 방법에서는 모델의 조건부 확률의 사후(posterior) 분포를 최대화하도록 학습이 진행된다. 이를 위해 사전(prior) 분포를 문제와 관련된 사전지식(prior knowledge) 및 모델 복잡도(model complexity)로 정의하고, 측정된 모델의 분류성능을 우도(likelihood)로 사 용하며, 측정된 사전분포와 우도를 이용하여 모델의 적합도(fitness)를 정의한다. 이를 통해 하이퍼네트워크 모델은 고차원 데이터를 효율적으로 학습 가능할 뿐이 아니라 모델의 학습시간 및 분류성능이 개선될 수 있다. 또한 학습 시에 파라미터로 주어지던 하이퍼에지의 구성 및 모델의 크기가 학습과정 중에 적응적으로 결정될 수 있다. 제안하는 학습방법의 검증을 위해 본 논문에서는 약 25,000개의 유전자 발현정보 데이터셋에 대한 분류문제에 모델을 적용한다. 실험 결과를 통해 제시하는 방법이 기존 하이퍼네트워크 학습 방법 뿐 아니라 다른 모델들에 비해 우수한 분류 성능을 보여주는 것을 확인할 수 있다. 또한 다양한 실험을 통해 사전분포로 사용된 사전지식이 모델 학습에 끼치는 영향을 분석한다.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.1
• /
• pp.76-81
• /
• 2010

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 second-order conditional maximum a posteriori (CMAP). 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 current observation and the speech activity decisions in the pervious two frames. Experimental results show that the proposed approach yields better results compared to the statistical model-based and the CMAP-based VAD using the LR test.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.3
• /
• pp.419-425
• /
• 2010

Kernel machine learning is gaining a lot of popularities in analyzing large or high dimensional nonlinear data. We use this technique to estimate a GARCH model for predicting the conditional volatility of stock market returns. GARCH models are usually estimated using maximum likelihood (ML) procedures, assuming that the data are normally distributed. In this paper, we show that GARCH models can be estimated using kernel machine learning and that kernel machine has a higher predicting ability than ML methods and support vector machine, when estimating volatility of financial time series data with fat tail.

• Journal of Internet Computing and Services
• /
• v.13 no.2
• /
• pp.1-11
• /
• 2012

The purpose of this paper is to estimate 'willingness to pay' for mobile data service by using contingent valuation method with double bounded dichotomous choice question. The findings are as follows.: First, the willingness to pay of mobile data service is considerably lower than current retail price. Second, the perceived degree of mobile data service such as awareness and benefit recognition is positively related to the willingness to pay of mobile data service. Our results suggest that active promotion and strengthening of the content of mobile data service are needed in order to enhance the profitability of mobile operators. The analysis results will be used to set the mobile operator's pricing strategy and to build up a successful communication policies in the mobile ecosystem.

• Journal of Korean Society of Forest Science
• /
• v.99 no.6
• /
• pp.891-899
• /
• 2010

The purpose of this study is to estimate economic value of forest landscape function using conditional logit model, applied by Choice Experiment. For the study, we have chosen attributes and levels of forest landscape. In specific, topographical forest type, forest type, forest density, recreational factor (side trip, accessibility of valley) and WTP were included in attributes. Based on factors, we have made 48 choice sets with Balanced and Orthogonal form using SAS 9.1. The efficiency of questionnaire was 6.02 (D-Error: 0.1) and choice set and socio-economic variable were selected. In order to reduce cognitive load of respondent, 96 choice sets were divided into 4 types in questionnaire so that respondent could respond to 12 choice sets respectively. Population was citizens from 7 metropolitan cities including Seoul, and the interview survey was conducted to find out average annual WTP per household for the total 280 interviewees. As a result, In the Non-ASC model, Mcfadden' ${\rho}$ had 0.21, and Log Likelihood: -2,631. Average annual WTP per household for forest landscape was 266,723 Won(Korean currency).

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.61-73
• /
• 2016

We consider the wild bootstrap Ljung-Box (LB) test for autocorrelation in residuals of fitted multivariate time series models. The asymptotic chi-square distribution under the IID assumption is traditionally used for the LB test; however, size distortion tends to occur in the usage of the LB test, due to the conditional heteroskedasticity of financial time series. In order to overcome such defects, we propose the wild bootstrap LB test for autocorrelation in residuals of fitted vector autoregressive and error correction models. The simulation study and real data analysis are conducted for finite sample performance.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.1
• /
• pp.49-62
• /
• 2022

Online customer review data can be easily collected on the Internet and also they describe sentimental evaluation of a product in different aspects. Previous sentiment analysis studies evaluate the degree of sentiment with review data, which may have multiple sentences describing different product aspects. Since different aspects of a product can be described in a sentence, the proposed method suggested analyzing a sentence to build a pair of a product aspect terms and sentimental terms. Bidirectional LSTM and CRF algorithms were used in this paper. A pair of aspect terms and sentimental terms are evaluated by pre-defined evaluation rules. The paper suggested using the result of evaulation as inputs of QFD, so that the quantified customer voices effect on the requirements of a new product. Online reviews for a hair dryer were used as an example showing that the proposed approach can derive reasonable sentiment analysis results.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.5 no.2
• /
• pp.163-169
• /
• 2000

From the viewpoint of the cost effective design of power conversion systems, it is very important to fully u utilize the CillTent capacity of power devices over all circumstances. Therefore this paper deals with the l practical design of digital CillTent controller to meet the requirements of fast and overshoot free control r response over the varying control voltage bOlmds, the accompanied computational delay, and the system U W1certainties. The proposed controller consists of high gain PI control schemes using both the conditional i integrator and the modified delay compensator. The simulation and experimental results show the validity of t the proposed controller.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.183-188
• /
• 2006

본 논문에서는 베이지안 네트워크를 기반으로 생성하고 평가한 가상예제를 활용하여 범주속성 및 수치속성 데이터에 대한 분류 성능을 향상시키는 방안을 제안한다. 가상예제를 활용하는 종래의 연구들은 주로 수치 속성 데이터를 대상으로 한 반면 본 연구에서는 범주속성 데이터에 대해서도 가상예제를 적용하여 효과를 확인하였다. 그리고 대상 도메인에 특화된 지식을 활용하여 특정 학습 알고리즘의 성능을 향상시키는 것을 목표로 한 기존 연구들과는 달리 본 연구에서는 도메인에 특화된 지식을 활용하는 대신 주어진 훈련 집합을 기반으로 만든 베이지안 네트워크로부터 가상예제를 생성하고, 그 예제가 네트워크의 조건부 우도를 증가시키는데 기여할 경우 유용한 것으로 선별한다. 이러한 생성 및 선별과정을 반복하여 적절한 크기의 가상예제 집합을 수집하여 사용한다. 범주 속성 데이터와 수치 속성을 포함한 데이터를 대상으로 한 실험 결과, 여러 가지 학습 모델의 성능이 향상됨을 확인하였다.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1263-1272
• /
• 2014

Longitudinal categorical data commonly occur from medical, health, and social sciences. In these data, the correlation of repeated outcomes is taken into account to explain the effects of covariates exactly. In this paper, we introduce marginalized random effects models that are used for the estimation of the population-averaged effects of covariates. We also review how these models have been developed. Real data analysis is presented using the marginalized random effects.