• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.543-546
• /
• 2004

Bishop과 Nabney에 의해 소개된 기존의 혼합 밀도 네트워크(Mixture Density Network)에서는 조건부 확률밀도 함수의 매개변수들(parameters)이 하나의 MLP(multi-layer perceptron)의 출력 벡터로 주어진다. 최근에는 변형된 혼합 밀도 네트워크(Modified Mixture Density Network)라고 하는 이름으로 조건부 확률밀도 함수의 선분포(priors), 조건부 평균(conditional means), 그리고 공분산(covariances) 등이 각각 독립적인 MLP의 출력벡터로 주어지는 경우를 다룬 연구가 보고된 바 있다. 본 논문에서는 조건부 평균이 입력에 관해 선형인 경우를 위한 버전에 대한 이론과 매트랩 프로그램 개발 및 적용을 다룬다. 본 논문에서는 우선 일반적인 혼합 밀도 네트워크에 대해 간단히 설명하고, 혼합 밀도 네트워크의 출력인 다층 퍼셉트론의 매개변수를 각각 다른 다층 퍼셉트론에서 학습시키는 변형된 혼합 밀도 네트워크를 설명한 후, 각각 다른 다층 퍼셉트론을 통해 매개변수를 얻는 것은 동일하나 평균값은 선형함수를 통해 얻는 혼합 밀도 네트워크 버전을 소개한다. 그리고, 모의실험을 통하여 이러한 혼합 밀도 네트워크를의 적용가능성에 대해 알아본다.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.519-527
• /
• 2003

Speech is much influenced by the existence of outliers which are introduced by such an unexpected happenings as additive background noise, change of speaker's utterance pattern and voice detection errors. These kinds of outliers may result in severe degradation of speaker recognition performance. In this paper, we proposed the GMM based on robust principal component analysis (RPCA-GMM) using M-estimation to solve the problems of both ouliers and high dimensionality of training feature vectors in speaker identification. Firstly, a new feature vector with reduced dimension is obtained by robust PCA obtained from M-estimation. The robust PCA transforms the original dimensional feature vector onto the reduced dimensional linear subspace that is spanned by the leading eigenvectors of the covariance matrix of feature vector. Secondly, the GMM with diagonal covariance matrix is obtained from these transformed feature vectors. We peformed speaker identification experiments to show the effectiveness of the proposed method. We compared the proposed method (RPCA-GMM) with transformed feature vectors to the PCA and the conventional GMM with diagonal matrix. Whenever the portion of outliers increases by every 2%, the proposed method maintains almost same speaker identification rate with 0.03% of little degradation, while the conventional GMM and the PCA shows much degradation of that by 0.65% and 0.55%, respectively This means that our method is more robust to the existence of outlier.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.187-194
• /
• 2005

The background subtraction method is mainly used for the real-time extraction and tracking of moving objects from image sequences. In the outdoor environment, there are many changeable environment factors such as gradually changing illumination, swaying trees and suddenly moving objects , which are to be considered for an adaptive processing. Normally, GMM(Gaussian Mixture Model) is used to subtract the background by considering adaptively the various changes in the scenes, and the adaptive GMMs improving the real-time Performance were Proposed and worked. This paper, for on-line background subtraction, employed the improved adaptive GMM, which uses the small constant for learning rate a and is not able to speedily adapt the suddenly movement of objects, So, this paper Proposed and evaluated the dynamic control method of a using the adaptive selection of the number of component distributions and the global variances of pixel values.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.366-369
• /
• 2005

Background subtraction is mainly used for the real-time extraction and tracking of moving objects from image sequences. In the outdoor environment, there are many changeable factor such as gradually changing illumination, swaying trees and suddenly moving objects, which are to be considered for the adaptive processing. Normally, GMM(Gaussian Mixture Model) is used to subtract the background adaptively considering the various changes in the scenes, and the adaptive GMMs improving the real-time performance were worked. This paper, for on-line background subtraction, applied the improved adaptive GMM, which uses the small constant for learning rate ${\alpha}$ and is not able to speedily adapt the suddenly movement of objects, So, this paper proposed and evaluated the dynamic control method of ${\alpha}$ using the adaptive selection of the number of component distributions and the global variances of pixel values.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.1
• /
• pp.113-122
• /
• 2007

In this paper, we propose a multi-state based hybrid location update scheme, which integrates the time-based and the movement-based methods. In the proposed scheme, a mobile terminal updates its location after n cell boundary crossing and a time interval of T[sec]. We derive an analytical solution for the performance of the hybrid scheme with exponential cell resident time and evaluate it numerically with time-varying random walk mobility model, which we model as multi-states Markov chain. Furthermore, we also evaluate the scheme for arbitrary cell resident times by simulation. From the numerical analysis and the simulation results, we prove that the proposed scheme significantly outperforms the time-based and the movement-based methods, when implemented alone, more accurately adapting to the time-varying user mobility.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.7A
• /
• pp.967-977
• /
• 2000

In this paper, we apply a mixed $H_2/H_{\infty}$ control to a generalized plant of inverted pendulum system represented by an LFR(Linear Fractional Representation). First, in order to obtain the generalized plant, the linear model of the inverted pendulum represented by an LFR(Linear fractional Representation) is derived. In LFR, we consider system uncertainties as three nonlinear components and a pendulum mass uncertainty. Augmenting the LFR model by adding weighting functions, we get a generalized plant. And then, we design a mixed $H_2/H_{\infty}$ controller for the generalized plant. In order to design the mixed $H_2/H_{\infty}$ controller, we use the LMI technique. To evaluate control performances and robust stability of the mixed $H_2/H_{\infty}$ controller designed, we compare it with the $H_{\infty}$ controller through the simulation and experiment. In the result, with the fewer feedback information, the mixed $H_2/H_{\infty}$ controller shows the better control performances and robust stability than the $H_{\infty}$ controller in the sense of pendulum angle.

• Journal of the Korean Chemical Society
• /
• v.59 no.4
• /
• pp.271-279
• /
• 2015

The critical micelle concentration (CMC), the counter ion binding constant (B) and the aggregation number (N^* ) for the mixed micellization of sodium dodecanoate and sodium n-octanoate as two anionic surfactants have been investigated by means of electric conductivity and light scattering. As its experimental results are found to be deviated from ideal mixed model, thus two different kinds of regular solution models such as Rubingh and Motomura are used for interpreting our experimental data. The stability of the mixed micelles has been confirmed from the negative values of the standard Gibbs energy of mixed micellization ΔG^micel,0 over all compositions and the measured values of ΔG^micel,0 agreed with the theoretical ones within the experimental error.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.2
• /
• pp.79-89
• /
• 2017

The Optimization of a Closed-Loop Supply Chain (CLSC) Model Using an Adaptive Hybrid Genetic Algorithm (AHGA) Approach is Considered in this Paper. With Forward and Reverse Logistics as an Integrated Logistics Concept, The CLSC Model is Consisted of Various Facilities Such as Part Supplier, Product Manufacturer, Collection Center, Recovery Center, etc. A Mathematical Model and the AHGA Approach are Used for Representing and Implementing the CLSC Model, Respectively. Several Conventional Approaches Including the AHGA Approach are Used for Comparing their Performances in Numerical Experiment.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2010.05a
• /
• pp.190-193
• /
• 2010

The turbulent mixing and combustion of a shear coaxial injector under supercritical pressures have been theoretically/numerically investigated. Turbulent numerical model is based on large eddy simulation with real-fluid transport and thermodynamics over the entire pressure; Soave modification of Redlich-Kwong equation of state, Chung's model for viscosity/conductivity, and Fuller's theorem for diffusivity to take account Takahashi's compressible effect. The results are compared with previous researcher's. The large-scale vortices shedding from the outer rim into the recirculation region to react with gaseous oxygen was investigated.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.231-231
• /
• 2022

하구에서의 흐름은 하천의 담수와 바다에서부터 유입되는 염수, 조석, 파랑 등으로 인해 복잡한 흐름구조와 혼합 양상을 보인다. 특히 만 내에 하천이 있을 경우 만의 해류특성은 하구에서의 혼합과 이송에 지배적인 영향을 미치며, 하천에서부터 방류되는 입자들은 만의 해류특성 따라 만에서의 체류시간과 이송이 결정된다. 잔차류 특성에 의한 순 물질 플럭스의 방향과 조석비대칭에 따른 하구에서의 퇴적 형태들이 결정되며, 이로 인해 하구에서의 퇴적물 퇴적 및 물질의 집적 위치, 하구 인근과 만에서의 환경변화에 영향을 줄 수 있다. 따라서 만 내에서의 혼합과 입자의 이송확산, 하천 담수의 영향역 등과 같은 만과 하천의 흐름 특성을 이해하는 것은 연안 및 하구의 환경 및 관리에 중요하다. 본 연구에서는 영일만과 형산강을 대상으로 계절변화에 따른 영일만 내 흐름과 형산강 하구에서의 퇴적양상에 대해 수치모의를 통해 수행하였다. 수치모델로는 천수방정식으로 준 3차원 유동해석을 하는 Delft-3D Flow와 파랑모형인 SWAN 모델을 결합하여 형산강하구와 영일만의 유동을 해석하였다. 상류개방경계는 형산강하구 9 km, 하류개방경계는 영일만 외해 50 km로 설정하였고, 경계조건은 대상지역의 관측소 자료와 전지구 모형자료를 결합하여 구성하였다. 또한, 라그랑쥬 입자추적모델을 통해 형산강 상류에서 유입한 입자들의 영일만 내 체류시간과 집적 위치를 평가하였다.