• Journal of Mechanical Science and Technology
• /
• 제19권2호
• /
• pp.558-566
• /
• 2005

We propose a feature-based multi-resolution representation of B-rep solid models using history-based Boolean operations based on the merge-and-select algorithm. Because union and subtraction are commutative in the history-based Boolean operations, the integrity of the models at various levels of detail (LOD) is guaranteed for the reordered features regardless of whether the features are subtractive or additive. The multi-resolution solid representation proposed in this paper includes a non-manifold topological merged-set model of all feature primitives as well as a feature-modeling tree reordered consistently with a given LOD criterion. As a result, a B-rep solid model for a given LOD can be provided quickly, because the boundary of the model is evaluated without any geometric calculation and extracted from the merged set by selecting the entities contributing to the LOD model shape.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 춘계 학술대회 발표논문집
• /
• pp.91-94
• /
• 2005

The performance of speech recognition is degraded by the mismatch between training and test environments. Many methods have been presented to compensate for additive noise and channel effect in the cepstral domain, and Cepstral Mean Subtraction (CMS) is the representative method among them. Recently, high order cepstral moment normalization method has introduced to improve recognition accuracy. In this paper, we apply high order moment normalization method and smoothing filter for real-time processing. In experiments using Aurora2 DB, we obtained error rate reduction of 49.7% with the proposed algorithm in comparison with baseline system.

• ETRI Journal
• /
• 제34권5호
• /
• pp.684-689
• /
• 2012

A mode-singular-value-decomposition (SVD) maximum likelihood (ML) estimation procedure is proposed for the source localization problem under an additive measurement error model. In a practical situation, the noise variance is usually unknown. In this paper, we propose an algorithm that does not require the noise covariance matrix as a priori knowledge. In the proposed method, the weight is derived by the inverse of the noise magnitude square in the ML criterion. The performance of the proposed method outperforms that of the existing methods and approximates the Taylor-series ML and Cram$\acute{e}$r-Rao lower bound.

• 전자공학회논문지A
• /
• 제31A권4호
• /
• pp.39-46
• /
• 1994

In this paper, the idea of using a multiple symbol obervation interval to improve error probability performance is applied to differential detection of MTCM(multiple trellis code modulation) with ${\Pi}$/4 shift QPSK, 8DPSK and 16DPSK. We propose two types of sliding multiple symbol differential detection algorithm, type 1 and type 2. The two types of sliding detection scheme are examined and compared with conventional(symbol-by-symbol) detection and bolck detection with these modulation formats in an additive white Gaussian noise(AWGN) using the Monte Carlo simulation. We show that the amount of improvement over conventional and block detection depends on the number of phases and the number of additional symbol intervals added to the observation. Computer simulagtion results are presented for 2,4,8 states in AWGN channel.

• Journal of Computing Science and Engineering
• /
• 제4권2호
• /
• pp.97-109
• /
• 2010

Nonnegative matrix factorization (NMF) is a popular method for multivariate analysis of nonnegative data, which is to decompose a data matrix into a product of two factor matrices with all entries restricted to be nonnegative. NMF was shown to be useful in a task of clustering (especially document clustering), but in some cases NMF produces the results inappropriate to the clustering problems. In this paper, we present an algorithm for orthogonal nonnegative matrix factorization, where an orthogonality constraint is imposed on the nonnegative decomposition of a term-document matrix. The result of orthogonal NMF can be clearly interpreted for the clustering problems, and also the performance of clustering is usually better than that of the NMF. We develop multiplicative updates directly from true gradient on Stiefel manifold, whereas existing algorithms consider additive orthogonality constraints. Experiments on several different document data sets show our orthogonal NMF algorithms perform better in a task of clustering, compared to the standard NMF and an existing orthogonal NMF.

• The Journal of the Acoustical Society of Korea
• /
• 제17권4E호
• /
• pp.3-10
• /
• 1998

This paper concerns the dynamical behavior, in probabilistic sense, of a feedforward neural network performing auto association for novelty. Networks of retinotopic topology having a one-to-one correspondence between and output units can be readily trained using back-propagation algorithm, to perform autoassociative mappings. A novelty filter is obtained by subtracting the network output from the input vector. Then the presentation of a "familiar" pattern tends to evoke a null response ; but any anomalous component is enhanced. Such a behavior exhibits a promising feature for enhancement of weak signals in additive noise. As an analysis of the novelty filtering, this paper shows that the probability density function of the weigh converges to Gaussian when the input time series is statistically characterized by nonsymmetrical probability density functions. After output units are locally linearized, the recursive relation for updating the weight of the neural network is converted into a first-order random differential equation. Based on this equation it is shown that the probability density function of the weight satisfies the Fokker-Planck equation. By solving the Fokker-Planck equation, it is found that the weight is Gaussian distributed with time dependent mean and variance.

• 대한수학회보
• /
• 제57권1호
• /
• pp.251-274
• /
• 2020

We study a dynamical system that was originally defined by Romik in 2008 using an old theorem of Berggren concerning Pythagorean triples. Romik's system is closely related to the Farey map on the unit interval which generates an additive continued fraction algorithm. We explore some number theoretical properties of the Romik system. In particular, we prove an analogue of Lagrange's theorem in the case of the Romik system on the unit quarter circle, which states that a point possesses an eventually periodic digit expansion if and only if the point is defined over a real quadratic extension field of rationals.

• 한국통신학회논문지
• /
• 제11권5호
• /
• pp.349-359
• /
• 1986

본 연구는 3~7MHz 사이의 단파대역에서 200Hz이하의 대역폭을 가지며 출현빈도가 극히 낮은 신호를 자동 식별하기 위한 기본 연구이다. 이를 위하여 1차적으로 100KHz대역에서 0dB정도의 OOK신호에 대하여 그 존재유무를 판단하는 검출과 추정 방법에 대하여 기수한 것이다. 검출과 추정 과정에서 OOK변조 신호에 잡음이 혼입되어 오염된 상태에서 LOD와 E-C는 약 77%를 상관함수 패턴모형 방법은 약90%를 올바르게 판정하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.367-370
• /
• 2007

Both impluse noise and AWGN (additive white Gaussian noise) are easily corrupted into images, during signal transmission and acquisition. Thus, an algorithm for removing both noises is represented in this paper. An impulse noise detection step can effectively separate impulse noise with AWGN, then in the noise filtering step, by using several parameters, not only impulse noise but also AWGN can be reduced. The value of those parameters are automatically changeable when the standard deviation of AWGN, the impulse noise density, and the spatial distances between pixels are different. Results of computer simulations show that the proposed approach performs better than other conventional filters.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2000년도 봄 학술발표논문집 Vol.27 No.1 (B)
• /
• pp.426-428
• /
• 2000

화상회의 시스템의 영상 압축표준 중 하나인 H.261은 화상전화기에서 주로 사용되고 있다. 본 논문에서는 기존의 H.261 영상에 부가영상을 삽입하는 방법을 제안한다. H.261 영상에 단순히 부가영상을 삽입하면 움직임보상 데이터 처리를 하지 않기 때문에 전달된 H.261 영상으로부터 원래의 영상을 복원하기 어렵다. 이를 해결하는 방법으로 원시 H.261 영상 전체를 복호화 한 후 부가영상을 삽입하고 다시 부호화 하는 방법이 있으나 이 경우 처리해 주어야 할 데이터가 너무 많아 수행속도의 저하를 가져온다. 제안한 방법은 움직임 보상 정보가 영상에 아무 영향을 미치지 않을 경우에는 허프만 복/부호화만을 사용하여 단순 삽입을 하고, 움직임 보상 정보가 부가영상과 겹치게 되어 부가 영상이 포함된 영상을 전달 받는 측에서 문제가 될 경우만 복호화해 두었던 영상데이터를 보낸다. 간단한 실험을 통하여 제안된 알고리즘의 성능을 분석한 결과 전체를 복/부호화하는 방법에 비하여 대략 3배의 속도의 향상을 보였다.