• 한국CDE학회논문집
• /
• 제3권1호
• /
• pp.15-21
• /
• 1998

Several adaptive and direct slicing methods have been developed to make the slice data for RP parts with better accuracy and speed. This research deals with a new adaptive slicing algorithm that shows drastic improvement in computing time for calculating the slices of a part. First, it uses less number of sampling points fur each slice in determining the thickness of the next slice. Secondly, the idea of contour map is utilized to determine the optimal sampling point on each slice. Thirdly, the calculation efficiency is further improved by introducing vertical character lines of the given part. The results in terms of accuracy and speed are compared with the existing methods.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2000년도 추계학술발표회 논문집
• /
• pp.135-140
• /
• 2000

베이지안 신경망 모형(Bayesian Neural Networks Models)에서 주어진 입력값(input)은 블랙 박스(Black-Box)와 같은 신경망 구조의 각 층(layer)을 거쳐서 출력값(output)으로 계산된다. 새로운 입력 데이터에 대한 예측값은 사후분포(posterior distribution)의 기대값(mean)에 의해 계산된다. 주어진 사전분포(prior distribution)와 학습데이터에 의한 가능도함수(likelihood functions)를 통해 계산되어진 사후분포는 매우 복잡한 구조를 갖게 됨으로서 기대값의 적분계산에 대한 어려움이 발생한다. 이때 확률적 추정에 의한 근사 방법인 몬테칼로 적분을 이용한다. 이러한 방법으로서 Hybrid Monte Carlo 알고리즘은 우수한 결과를 제공하여준다(Neal 1996). 본 논문에서는 Hybrid Monte Carlo 알고리즘과 기존에 많이 사용되고 있는 Gibbs sampling, Metropolis algorithm, 그리고 Slice Sampling등의 몬테칼로 방법들을 비교한다.

• Journal of the Korean Statistical Society
• /
• 제31권1호
• /
• pp.63-75
• /
• 2002

Most attempts at Bayesian analysis of neural networks involve hierarchical modeling. We believe that similar results can be obtained with simpler models that require less computational effort, as long as appropriate restrictions are placed on parameters in order to ensure propriety of posterior distributions. In particular, we adopt a model first introduced by Lee (1999) that utilizes an improper prior for all parameters. Straightforward Gibbs sampling is possible, with the exception of the bias parameters, which are embedded in nonlinear sigmoidal functions. In addition to the problems posed by nonlinearity, direct sampling from the posterior distributions of the bias parameters is compounded due to the duplication of hidden nodes, which is a source of multimodality. In this regard, we focus on sampling from the marginal posterior distribution of the bias parameters with Markov chain Monte Carlo methods that combine traditional Metropolis sampling with a slice sampler described by Neal (1997, 2001). The methods are illustrated with data examples that are largely confined to the analysis of nonparametric regression models.

• Smart Structures and Systems
• /
• 제21권5호
• /
• pp.601-609
• /
• 2018

The estimated probabilistic model of wind data based on the conventional approach may have high discrepancy compared with the true distribution because of the uncertainty caused by the instrument error and limited monitoring data. A sequential quadratic programming (SQP) algorithm-based finite mixture modeling method has been developed in the companion paper and is conducted to formulate the joint probability density function (PDF) of wind speed and direction using the wind monitoring data of the investigated bridge. The established bivariate model of wind speed and direction only represents the features of available wind monitoring data. To characterize the stochastic properties of the wind parameters with the subsequent wind monitoring data, in this study, Bayesian inference approach considering the uncertainty is proposed to update the wind parameters in the bivariate probabilistic model. The slice sampling algorithm of Markov chain Monte Carlo (MCMC) method is applied to establish the multi-dimensional and complex posterior distribution which is analytically intractable. The numerical simulation examples for univariate and bivariate models are carried out to verify the effectiveness of the proposed method. In addition, the proposed Bayesian inference approach is used to update and optimize the parameters in the bivariate model using the wind monitoring data from the investigated bridge. The results indicate that the proposed Bayesian inference approach is feasible and can be employed to predict the bivariate distribution of wind speed and direction with limited monitoring data.

• 천문학회지
• /
• 제41권6호
• /
• pp.157-161
• /
• 2008

We have estimated the fractal dimension of the molecular clouds associated with the Hii region Sh 156 in the Outer Galaxy. We selected the $^{12}CO$ cube data from the FCRAO CO Survey of the Outer Galaxy. Using a developed code within IRAF, we identified slice-clouds (2-dimensional clouds in velocity-channel maps) with two threshold temperatures to estimate the fractal dimension. With the threshold temperatures of 1.8 K, and 3 K, we identified 317 slice-clouds and 217 slice-clouds, respectively. There seems to be a turn-over location in fractional dimension slope around NP (area; number of pixel) = 40. The fractal dimensions was estimated to be D = $1.5\;{\sim}\;1.53$ for $NP\;{\geq}\;40$, where $P\;{\propto}\;A^{D/2}$ (P is perimeter and A is area), which is slightly larger than other results. The sampling rate (spatial resolution) of observed data must be an important parameter when estimating fractal dimension. Fractal dimension is apparently invariant when varying the threshold temperatures applied to slice-clouds identification.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.287-290
• /
• 2001

Bishop이 제안한 generative Topographic Mapping(GTM)은 Kohonen이 제안한 자율 학습 신경망인 Self Organizing Maps(SOM)의 확률적 버전이다. 본 논문에서는 이러한 GTM 모형에 베이지안 추론을 결합하여 작은 오분류율을 가지는 분류 알고리즘인 베이지안 GTM(Bayesian GTM)을 제안한다. 이 방법은 기존의 GTM의 빠른 계산 처리 능력과 베이지안 추론을 이용하여 기존의 분류 알고리즘보다 우수한 결과가 나타남을 실험을 통하여 확인하였다.

• 천문학회지
• /
• 제37권4호
• /
• pp.137-141
• /
• 2004

We have estimated the fractal dimension of the molecular clouds in the Antigalactic Center based on the $^{12}CO$ (J = 1- 0) and $^{13}CO$ (J = 1- 0) database obtained using the 14m telescope at Taeduk Radio Astronomy Observatory. Using a developed code within IRAF, we were able to identify slice-clouds, and determined the dispersions of two spatial coordinates as well as perimeters and areas. The fractal dimension of the target region was estimated to be D = 1.34 for low resolution $^{12}CO$ (J = 1 - 0) database, and D = 1.4 for higher resolution $^{12}CO$ (J = 1 - 0) and $^{13}CO$ (J = 1 - 0) database, where $P {\propto} A^{D/2}$. The sampling rate (spatial resolution) of observed data must be an important parameter when estimating fractal dimension. Our database with higher resolution of 1 arcminute, which is corresponding to 0.2 pc at a distance of 1.1 kpc, gives us the same estimate of fractal dimension to that of local dark clouds. Fractal dimension is apparently invariant when varying the threshold temperatures applied to cloud identification. According to the dispersion pattern of longitudes and latitudes of identified slice-clouds, there is no preference of elongation direction.

• 방송공학회논문지
• /
• 제10권3호
• /
• pp.340-347
• /
• 2005

이 논문에서는 다상 다운 샘플링 (Polyphase down sampling)에 기반 한 다중 부호화 기법 (multiple description coding)을 H.264 동영상 기술에 적용한 기술을 제시한다. 먼저 입력된 원 매크로블록에 대해서, 움직임 보상된 잔여 매크로블록을 계산한다. 제안하는 기술은 이 잔여 매크로블록을 DCT, 양자화, 엔트로피 부호화 과정을 거쳐 부호화화는 H.264 동영상 부호화 기술에 있어서 DCT 처리 이전에 다상 다운 샘플링을 적용하여 하나의 매크로블록을 4 개의 기술(description)로 나누어 각각을 부호화한다. 복호화에 있어 4 개의 기술이 모두 수신되면, 원래의 영상을 완전히 복호하고, 일부 기술이 수신되지 않으면, 에러 없이 수신된 기술로부터 보간법에 의해 원래의 영상과 유사한 영상을 복호한다. 모의실험은 JVT SVC(Scalable Video Coding) 표준화를 위한 9 개 시험 동영상 전체에 대해 다양한 패킷 손실 형태의 환경에서 수행 되었다. 실험 결과는 제안된 방법이 H.264 기반의 슬라이스 그룹 맵에 기반 한 에러 숨김 방법보다 0.5-5 dB 향상된 성능을 보여주었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.93-96
• /
• 2002

This paper presents robust and efficient scene-based video watermarking method using visual rhythm (spatio-temporal slice) in compressed domain. Scene change can be detected easily using visual rhythm and video sequences are conveniently edited at the scene boundaries. Therefore, scene-based watermark embedding Process it a natural choice. Temporal spread spectrum can be achieved by applying spread spectrum methods to visual rhythm. Additive Gaussian noise, low-pass filtering, median filtering and histogram equalization attack are simulated for all frames. Frame sub-sampling is also simulated as a typical video attack Simulation results show that proposed algorithm is robust and efficient in the presence of such kind of attacks.

• 대한전자공학회논문지
• /
• 제21권6호
• /
• pp.27-33
• /
• 1984

본 논문은 TDM 전자교환기의 국간신호 장비인 CCITT R2-MF 수신기(32CH용)의 디지탈 하드웨어 실현에 관한 실험적인 연구이다. MF 검출을 위한 DSP(digital signal Processing)방법은 여러 가지가 있지만 본 수신장치의 요구조건은 특정 주파수의 예민한 주파수 응답 특성과 그의 유무 판별이 필요하므로 DFT(discrete Fourier transform)에 의한 방법이 가장 효율적이다 이의 실현은 실 시간 처리를 위해 "bit-slice micro-processor"인 Am2900 series를 사용, micro-programming 기법을 도입하여 고속처리를 하였다. 그리고 전 시스템 제어를 위하여 Z-80A processor를 사용, 하드웨어 및 소프트웨어의 융통성을 최대한 높임으로서 TDM 전자교환기의 국간 신호장치로서의 활용 가능성을 확인하였다.