• 음성과학
• /
• 제15권3호
• /
• pp.7-15
• /
• 2008

This paper proposes the method to extract new feature vectors using the difference between the cepstrum for static characteristics and delta cepstrum for dynamic characteristics in speaker recognition (SR). The difference vector (DV) which it proposes from this paper is containing the static and the dynamic characteristics simultaneously at the intermediate characteristic vector which uses the deference between the static and the dynamic characteristics and as the characteristic vector which is new there is a possibility of doing. Compared to the conventional method, the proposed method can achieve new feature vector without increasing of new parameter, but only need the calculation process for the difference between the cepstrum and delta cepstrum. Experimental results show that the proposed method has a good performance more than 2.03%, on average, compared with conventional method in speaker identification (SI).

• 대한전자공학회논문지
• /
• 제25권7호
• /
• pp.807-818
• /
• 1988

This paper proposes new algorithms for the estimation of displacement vector and moving object extraction using difference picture. First, the relations between the boundary of moving objects in two consecutive image and the boundary of difference picture regions are analyzed, then displacement vector estimation algorithm is proposed. Using the estimated displacement vector, moving objects are directly extracted from difference picture. Since the proposed algorithms do not process gray-valued image, they have a short processing time and are suitable to real time processing. From the experimental results, we observed that, if difference picture is wel extracted, the proposecd algorithms work well even in the circumstances of complex background, fast or slow motion, rotation etc., including occlusion where is not moving area.

• Korean Journal of Mathematics
• /
• 제32권3호
• /
• pp.439-451
• /
• 2024

In the present paper, using the notion of difference sequence spaces, we introduce new kind of Cesàro summable difference sequence spaces of vector valued sequences with the aid of paranorm and modulus function. In addition, we extend the notion of statistical convergence to introduce a new sequence space SC₁(∆, q) which coincides with C¹₁(X, ∆, φ, λ, q) (one of the above defined Cesàro summable difference sequence spaces) under the restriction of bounded modulus function.

• Journal of applied mathematics & informatics
• /
• 제20권1_2호
• /
• pp.575-584
• /
• 2006

In this paper we introduce a discrete tangent vector of a polygon defined on each vertex by a linear combination of forward difference and backward difference, and show that if the polygon is originated from a smooth curve then direction of the discrete tangent vector is a second order approximation of the direction of the tangent vector of the original curve. Using this discrete tangent vector, we also introduced the geometric cubic Hermite interpolation of a polygon with controlled initial and terminal speed of the curve segments proportional to the edge length. In this case the whole interpolation is $C^1$. Experiments suggest that about $90\%$ of the edge length is the best fit for the initial and terminal speeds.

• 통합자연과학논문집
• /
• 제13권4호
• /
• pp.147-151
• /
• 2020

In this paper, we propose a method to detect concept drift by applying Convolutional Neural Network (CNN) in a data stream environment. Since the conventional method compares only the final output value of the CNN and detects it as a concept drift if there is a difference, there is a problem in that the actual input value of the data stream reacts sensitively even if there is no significant difference and is incorrectly detected as a concept drift. Therefore, in this paper, in order to reduce such errors, not only the output value of CNN but also the probability vector are used. First, the data entered into the data stream is patterned to learn from the neural network model, and the difference between the output value and probability vector of the current data and the historical data of these learned neural network models is compared to detect the concept drift. The proposed method confirmed that only CNN output values could be used to reduce detection errors compared to how concept drift were detected.

• Journal of the Korean Data and Information Science Society
• /
• 제25권2호
• /
• pp.455-464
• /
• 2014

Unlabeled examples are easier and less expensive to obtain than labeled examples. Semisupervised approaches are used to utilize such examples in an eort to boost the predictive performance. This paper proposes a novel semisupervised classication method named transductive least squares support vector machine (TLS-SVM), which is based on the least squares support vector machine. The proposed method utilizes the dierence convex algorithm to derive nonconvex minimization solutions for the TLS-SVM. A generalized cross validation method is also developed to choose the hyperparameters that aect the performance of the TLS-SVM. The experimental results conrm the successful performance of the proposed TLS-SVM.

• 한국정보통신학회논문지
• /
• 제6권6호
• /
• pp.873-878
• /
• 2002

고정자 전류 스펙트럼(stator current spectrum)은 유도전동기의 고장 검출에 널리 사용되어왔다. 본 논문에서는 고정자 전류 스펙트럼 중에서 회전자 고장에 의해서 큰 영향을 받는 주파수 성분들로 특징벡터(feature vector)를 구성하고, 특징벡터와 기준벡터(reference vector)와의 평균 절대치 차이(mean absolute difference)를 구함으로써, 회전자 고장을 검출하는 방법을 제안한다. 제안한 방법에서는 전류 스펙트럼 중에서 추출된 매우 작은 크기(dimension)의 특징 벡터에 대한 평균 절대치 차이를 이용하기 때문에 신경회로망에 의한 고장 검출 알고리즘 둥에 비해서 훨씬 적은 계산량만으로 모터의 고장을 효율적으로 검출할 수 있다

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 추계학술대회
• /
• pp.101-104
• /
• 2015

영상에서 이전 프레임과 현재 프레임을 비교하여 얼마나 움직였는지를 나타내는 모션 벡터(motion vector)라 한다. 이러한 모션 벡터를 이용하여 현재 프레임의 이미지안의 객체들이 이전프레임의 이미지 객체가 있었던 위치로 보정을 한다면 손 떨림이나 카메라의 흔들림에서 오는 작은 떨림을 보정할 수 있다. 본 논문에서는 모션 벡터를 추출하는 방법인 SAD(Sum of Absolute Difference) 방정식을 이용한 블록 정합 매칭 알고리즘, 위상상관을 이용한 매칭, 특징점을 이용한 매칭, Bitplane을 이용한 블록매칭의 성능을 비교하였다.

• 방송공학회논문지
• /
• 제15권3호
• /
• pp.426-433
• /
• 2010

H.264/AVC 비디오 압축 표준은 압축 효율을 높이기 위해 다양한 크기의 블록을 사용하여 화면 사이의 움직임 예측을 수행한다. H.264/AVC는 가변적인 블록 크기의 움직임 보상을 통해 세밀한 영역의 움직임까지 예측할 수 있어 잔여 영상을 나타내는 정보량을 효과적으로 줄일 수 있다. 복호를 위해서는 각 블록의 움직임 벡터를 전송해야 하는데, 저비트율 환경에서는 움직임 벡터 정보가 전체 비트스트림의 약 40%를 차지한다. 움직임 벡터 정보량을 줄이기 위해 비디오 부호화 전문가 그룹(VCEG)에서는 다양한 움직임 벡터 예측(Motion Vector Competition) 방법을 제안하였다. 다양한 예측 움직임 벡터를 사용하여 실제 전송해야 할 움직임 벡터 차분값(Motion Vector Difference, MVD)의 크기를 줄이기 때문에 압축 효율을 높일 수 있다. 그러나 다양한 예측 움직임 벡터를 사용하기 때문에 선택된 예측 움직임 벡터의 인덱스 정보를 복호기로 전송해야 한다. 이 논문에서는 인덱스 정보를 효율적으로 전송하기 위해 Phased-in 코드를 기반으로 한 새로운 코드워드 표를 제안했다. 실험을 통해 제안한 방법을 이용하여 동일한 화질에서 평균 약 7.24%의 비트율을 절감할 수 있었고, 동일한 비트율에서는 평균 약 0.36dB의 화질을 향상시킬 수 있었다.

• 한국전산유체공학회지
• /
• 제5권1호
• /
• pp.43-59
• /
• 2000

Characteristic boundary conditions are discussed in conjunction with a flux-difference splitting formulation as modified from Roe's linearization. Details of how one can implement the characteristic boundary conditions which are made compatible with the interior point formulation are described for different types of boundaries including subsonic outflow and adiabatic wall. The validity of boundary conditions are demonstrated through computation of transonic airfoil, supersonic ogive-cylinder, hypersonic cylinder, and S-duct internal flows. The computed wall pressure distributions are compared with published experimental and computed data. Objectives of this paper are thus to give insight of formulation procedure of a flux-difference splitting method and to pave ways for other users to adopt present boundary procedure on their numerical methods.