• Journal of the Korean Data and Information Science Society
• /
• 제25권1호
• /
• pp.211-218
• /
• 2014

Qu et. al. (2000) proposed the quadratic inference functions (QIF) method to marginal model analysis of longitudinal data to improve the generalized estimating equations (GEE). It yields a substantial improvement in efficiency for the estimators of regression parameters when the working correlation is misspecified. But for the longitudinal data with time-dependent covariates, when the implicit full covariates conditional mean (FCCM) assumption is violated, the QIF can not provide more consistent and efficient estimator than GEE (Cho and Dashnyam, 2013). Lai and Small (2007) divided time-dependent covariates into three types and proposed generalized method of moment (GMM) for longitudinal data with time-dependent covariates. They showed that their GMM type II and GMM moment selection methods can be more ecient than GEE with independence working correlation (GEE-ind) in the case of type II time-dependent covariates. We develop upgraded QIF method for type II time-dependent covariates. We show that this upgraded QIF method can provide substantial gains in efficiency over QIF and GEE-ind in the case of type II time-dependent covariates.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 춘계 학술대회 발표논문집
• /
• pp.131-134
• /
• 2006

The narrowband speech over the telephone network is lacking in the information from low-band (0-300 Hz) and high-band (3400-8000 Hz) that are found in wideband speech (0-8000 Hz). As a result, narrowband speech is characterized by the reduced intelligibility and muffled quality, and degraded speaker identification. Spectral folding is the easiest way to reconstruct the missing high-band; however, the reconstructed speech still brings the sense of band-limited characteristic because of the absence of low-band and mid-band frequency components. To compensate for the lack of the extended speech, we propose to combine the spectral folding method and GMM transformation method, which is a statistical method to reconstruct wideband speech. The reconstructed wideband speech showed that the absent frequency components was filled up with relatively low spectral mismatch. According to the subjective speech quality evaluations, the proposed method was preferred to other methods.

• 한국음향학회지
• /
• 제22권7호
• /
• pp.519-527
• /
• 2003

음성신호는 주변 잡음과 화자의 발성 패턴 변화, 음성 검출 오류에서 생기는 이상치(outlier)에 많은 영향을 받고 있다. 이러한 음성 신호를 이용하여 화자인식에 이용할 경우 인식률이 저하된다. 본 논문에서는 화자식별 (speaker identification)에서 학습 특징 벡터의 이상치와 고차원 문제를 해결하기 위하여 M-추정을 이용한 강인한 주성분 분석 가우시안 혼합모델 (Robust Principal Component Analysis-Gaussian Mixture Model)방법을 제안하였다. 제안된 방법은 먼저, 특징 벡터에 이상치가 존재할 경우 M-추정에 의하여 강인한 공분산 행렬을 재추정하여 얻어진 고유벡터로부터 변환 행렬을 구하여 감소된 차원을 갖는 새로운 특징벡터를 구한다. 여기에서 얻은 선형변환된 특징벡터로부터 화자의 가우시안 혼합 모델을 구한다. 제안된 방법의 성능을 검증하기 위하여 화자식별 실험을 하였다. 실험은 전형적인 가우시안 혼합 모델 방법과 주성분 분석법, 제안된 방법을 비교 분석하였다. 이상치가 2%씩 증가할 때마다 가우시안 혼합모델 방법과 주성분 분석법은 각각 0.65%, 0.55%씩 화자식별 성능이 저하되었지만, 제안된 방법은 0.03%정도 감소하였으므로 이상치에 더욱 강인함을 알 수 있다.

• 한국통신학회논문지
• /
• 제40권11호
• /
• pp.2291-2297
• /
• 2015

본 연구에서는 레이더 검지 시스템과 통합하여 적용하기 위해 도로 위를 이동하는 자동차의 영상을 입력 받아 자동차를 검출하는 방법을 제안한다. 입력 영상의 제약조건이 있다. 도로 위에서 아래 방향을 비스듬히 내려 보는 고정된 시야를 가져야한다는 점이다. 주어진 영상 중 도로 영역만을 이용하기 위해 도로 영역을 관심영역으로 검출해 적용한다. 서론에서는 도로 영역 내에서 차량 검출을 위해 사용한 모션 히스토리 이미지 추출 방법, SIFT(Scale-Invariant Feature Transform) 알고리즘, 히스토그램 분석 등을 적용한 실험결과와 이에 대한 한계점을 제시했다. 이를 해결하기 위해서 가우시안 혼합 모델(GMM, Gaussian Mixture Model)의 응용을 제안한다. 가우시안 혼합 모델 알고리즘을 응용한 차량 검출 GMM(VDGMM, Vehicle Detection GMM)과 이를 차량 검출에 더 최적화한 차량 검출 GMM 2.0을 설명하고, 차량 검출 GMM 2.0을 적용한 실험결과 및 결론을 제시한다. 도로 영역 검출 없이 GMM을 적용한 결과는 정확율, 재현율, F1이 각각 9%, 53%, 15%이었고, 도로 영역 검출 후 차량 검출 GMM 2.0을 적용한 결과는 각각 85%, 77%, 80%로 많은 차이를 보였다.

• 무역상무연구
• /
• 제61권
• /
• pp.165-190
• /
• 2014

The purpose of this study is to measure the trade insurance's macroeconomic effects by analyzing the causality between major economic variables(GDP per capita, market interest rate, inflation, unemployment rate, exchange rate) and trade insurance variable. I conducted empirical analyses using First-difference GMM(Generalized Method of Moments), System GMM and Panel-VAR Model, with panel data from 11 countries(Korea, United States, Japan, BRICs, Indonesia, Singapore, Hong Kong, Vietnam) between 1992 and 2011. There are several important findings. Above all, Trade insurance is positively and significantly related to GDP. This results show that trade insurance serves to increase economic growth. In other words, trade insurance leads to economic growth by helping increase GDP per capita. Especially, trade insurance negatively related to unemployment rate, it is for sure that trade insurance contribute to decrease unemployment rate. And trade insurance helps control of inflation. It is also confirmed that trade insurance contributes to price stability, which in turn serves to stabilize the overall economy. And this research finds as uncertainty in the market increases, seen it as increase of exchange rate, increasing trade insurance supply is stabilize the exchange rate.

• 대한전자공학회논문지SP
• /
• 제45권5호
• /
• pp.111-117
• /
• 2008

본 논문에서는 패턴 인식에서 우수한 성능을 보이는 가우시안 혼합모델 (Gaussian mixture model, GMM)을 이용하여 비정상적인 잡음환경에서 3GPP2 selectable mode vocoder (SMV)의 유/무성음 분류 알고리즘 성능 향상을 위한 방법을 제안한다. 기존의 SMV에 대해서 분석하고, 이론 기반으로 유/무성음 분류 알고리즘에서 우수한 성능을 보여주는 특징 벡터를 선택하여 GMM의 입력벡터로 효과적으로 이용한다 다양한 잡음환경에서 시스템의 성능을 평가한 결과 GMM을 이용한 제안된 방법이 기존의 SMV의 방법보다 우수한 유/무성음 분류 성능을 보였다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제38권2호
• /
• pp.182-187
• /
• 2014

We propose nonlinear GMM-based transformation functions in an attempt to deal with the over-smoothing effects of linear transformation for voice processing. The proposed methods adopt RBF networks as a local transformation function to overcome the drawbacks of global nonlinear transformation functions. In order to obtain high-quality modifications of speech signals, our voice conversion is implemented using the Harmonic plus Noise Model analysis/synthesis framework. Experimental results are reported on the English corpus, MOCHA-TIMIT.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2004-2007
• /
• 2003

This paper describes a method of performance enhancement using Flatness Mesure(FM) for the Gaussian Mixture Model(GMM) face recognition systems. Using this measure we discard the frames having low information before training and test. As the result, the performance increases about 9％ in the lower mixtures and calculation burden is decreased. As well, the recognition error rate is decreased under the illumination change surroundings. We use the 2D DCT coefficients lot face feature vectors and experiments are carried out on the Olivetti Research Laboratory (ORL) face database.

• IEIE Transactions on Smart Processing and Computing
• /
• 제2권5호
• /
• pp.277-281
• /
• 2013

Modern speaker verification systems based on support vector machines (SVMs) use Gaussian mixture model (GMM) supervectors as their input feature vectors, and the maximum a posteriori (MAP) adaptation is a conventional method for generating speaker-dependent GMMs by adapting a universal background model (UBM). MAP adaptation requires the appropriate amount of input utterance due to the number of model parameters to be estimated. On the other hand, with limited utterances, unreliable MAP adaptation can be performed, which causes adaptation noise even though the Bayesian priors used in the MAP adaptation smooth the movements between the UBM and speaker dependent GMMs. This paper proposes a sparse MAP adaptation method, which is known to perform well in the automatic speech recognition area. By introducing sparse MAP adaptation to the GMM-SVM-based speaker verification system, the adaptation noise can be mitigated effectively. The proposed method utilizes the L0 norm as a regularizer to induce sparsity. The experimental results on the TIMIT database showed that the sparse MAP-based GMM-SVM speaker verification system yields a 42.6% relative reduction in the equal error rate with few additional computations.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.558-570
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.