• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2000년도 추계학술발표회 논문집
• /
• pp.27-32
• /
• 2000

To overcome boundary problems with wavelet regression, we propose a simple method that reduces bias at the boundaries. It is based on a combination of wavelet functions and low-order polynomials. The utility of the method is illustrated with simulation studies and a real example. Asymptotic results show that the estimators are competitive with other nonparametric procedures.

• Journal of Mechanical Science and Technology
• /
• 제19권8호
• /
• pp.1611-1620
• /
• 2005

This paper shows the use of wavelet transformation combined with inverse acoustics to reconstruct the surface velocity of a noise source. This approach uses the boundary element analysis based on the measured sound pressure at a set of field points, the Helmholtz integral equations and wavelet transformation for reconstructing the normal surface velocity field. The reconstructed field can be diverged due to the small measurement errors in the case of nearfield acoustic holography (NAH) using an inverse boundary element method. In order to avoid this instability in the inverse problem, the reconstruction process should include some form of regularization for enhancing the resolution of source images. The usual method of regularization has been the truncation of wave vectors associated with small singular values, although the order of an optimal truncation is difficult to determine. In this paper, a wavelet transformation is applied to reduce the computation time for inverse acoustics and to enhance the reconstructed vibration field. The computational speed-up is achieved, with solution time being reduced to $14.5\%$.

• 대한수학회논문집
• /
• 제12권2호
• /
• pp.427-456
• /
• 1997

This paper concerns constructing wavelet bases on the unit interval, where a new boundary treatment is provided to overcome certain drawbacks of eariler constructions. Wavelet expansions on the unit interval usually suffer from artificial boundary effects and poor convergence at the boundaries. Many researchers have suggested a solution to the drawbacks. From a practical point of view, their solutions also have a common disadvantage. This paper provides a new solution using biorthogonality near the boundaries, that avoids the disadvantage while preserving their advantages.

• 전자공학회논문지CI
• /
• 제39권6호
• /
• pp.24-35
• /
• 2002

Maxwell 방정식을 효율적으로 풀기 위해 웨이브렛 행렬 변환(wavelet matrix transformation)과 경계요소법(Boundary Element Method)을 결합하는 방법을 제안하였으며, 2차원 위상변이 마스크(phase- shifting mask) 문제에 적용하였다. 계산 결과를 해석적인 해 및 참고문헌의 결과와 비교함으로써 구현된 모듈의 정확도를 검증하였으며, 제안된 방법이 경계요소법만을 적용한 경우에 비해 연산 시간과 메모리 사용 측면에서 효율적임을 확인하였다.

• 한국방사선학회논문지
• /
• 제2권1호
• /
• pp.23-29
• /
• 2008

본 연구에서는 웨이블릿 변환과 경계선 검출 필터를 이용하여 초음파영상의 다해상도 분해를 한 후 경계선 검출 필터링을 통해 초음파 영상의 화질을 개선하는 방안을 제안하였다. 제안된 방법에서는 잡음을 줄이고 에지를 강화하기 위해 웨이블릿 변환된 영상으로부터 얻어진 저해상도 영상에서 고해상도 영상으로 단계적으로 영역별 선택계수 조정과 방향성을 고려한 에지 필터링을 수행하였다. 이를 통해 반점영역의 픽셀은 웨이블릿 계수를 줄여 에지를 제외한 영역에서 선택적 저역통과 필터링 효과를 만들고, 에지에서는 접선 방향으로 평활화를 하여 연속성을 향상시키고, 법선 방향으로는 세선화를 하여 contrast를 높였다. 실험을 통해 단일해상도에서 비선형적 이방성의 확산모델을 이용한 필터링 방법과 웨이블릿 수축구조를 이용한 필터링 방법에 대해 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2434-2453
• /
• 2019

To improve the separation performance of time-frequency overlapped radar and communication signals from a single channel, this paper proposes an effective separation method based on an improved empirical wavelet transform (EWT) that introduces a fast boundary detection mechanism. The fast boundary detection mechanism can be regarded as a process of searching, difference optimization, and continuity detection of the important local minima in the Fourier spectrum that enables determination of the sub-band boundary and thus allows multiple signal components to be distinguished. An orthogonal empirical wavelet filter bank that was designed for signal adaptive reconstruction is then used to separate the input time-frequency overlapped signals. The experimental results show that if two source components are completely overlapped within the time domain and the spectrum overlap ratio is less than 60%, the average separation performance is improved by approximately 32.3% when compared with the classic EWT; the proposed method also improves the suitability for multiple frequency shift keying (MFSK) and reduces the algorithm complexity.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2319-2324
• /
• 2005

This paper proposes a intelligent gain and boundary layer based sliding mode control (SMC) method for robotic systems with unknown model uncertainties. For intelligent gain and boundary layer, we employ the self recurrent wavelet neural network (SRWNN) which has the properties such as a simple structure and fast convergence. In our control structure, the SRWNNs are used for estimating the width of boundary layer, uncertainty bound, and nonlinear terms of robotic systems. The adaptation laws for all parameters of SRWNNs and reconstruction error bounds are derived from the Lyapunov stability theorem, which are used for an on-line control of robotic systems with unknown uncertainties. Accordingly, the proposed method can overcome the chattering phenomena in the control effort and has the robustness regardless of unknown uncertainties. Finally, simulation results for the three-link manipulator, one of the robotic systems, are included to illustrate the effectiveness of the proposed method.

• 한국정보통신학회논문지
• /
• 제7권6호
• /
• pp.1229-1235
• /
• 2003

직교 웨이브렛 변환을 이용하여 유한길이를 가지는 영상 신호를 2-대역으로 분해하고 이를 합성하는 경우 경계영역 신호는 완전히 재생되지 않는다. 이를 완전 재생하기 위해 경계 영역에는 웨이브렛 필터와 다른 필터를 적용하여야 한다. 그러나 기존에 제안된 필터를 경계 영역에 적용하는 경우 필터의 만족스럽지 못한 주파수 특성으로 인하여 원하는 성능을 얻기에는 한계가 있다. 여기서는 기존에 제안된 경계필터의 주파수 특성을 개선하기 위한 새로운 경계필터의 설계방법을 제안하였다. 설계 방법은 우선 경계 영역을 완전히 재생할 수 있는 새로운 조건을 유도하고, 여기서 얻은 필터에 영점을 삽입하여 주파수 특성을 개선하였다. 제안된 방법으로 설계된 필터는 2-대역인 경우 기존의 경계 필터에 비하여 필터의 길이가 짧으면서도 통과 대역 및 저지 대역의 성능이 약 4.2dB∼6.6dB 개선됨을 보인다. 그러나 합성 과정이 복잡하여지는 단점을 가지고 있다.

• Structural Engineering and Mechanics
• /
• 제30권6호
• /
• pp.699-712
• /
• 2008

The effectiveness of wavelet transform in detecting delamination damages in multilayered composite beams and plates is studied here. The damaged composite beams and plates are modeled in finite element software ABAQUS and the first few mode shapes are obtained. The mode shapes of the damaged structures are then wavelet transformed. It is observed that the distribution of wavelet coefficients can identify the damage location of beams and plates by showing higher values of wavelet coefficients at the position of damage. The effectiveness of the method is studied for different boundary conditions, damage location and size for single as well as multiple delaminations in composite beams and plates. It is observed that both discrete wavelet transform (DWT) and continuous wavelet transform (CWT) can detect the presence and location of the damaged region from the mode shapes of the structures. DWT may be used to approximately evaluate the size of the delamination area, whereas, CWT is efficient to detect smaller delamination areas in composites.

• 한국정밀공학회지
• /
• 제16권10호
• /
• pp.194-202
• /
• 1999

A method for pattern recognition based on wavelet transform is proposed in this paper. The boundary of the object to be recognized includes shape information for object of machine parts. The contour is first represented using a one-dimensional signal and normalized about translation, rotation and scale, then is used to build the wavelet transform representation of the object. Wavelets allow us to decompose a function into multi-resolution hierarchy of localized frequency bands. The recognition of 2-dimensional object based on the wavelet is described to analyze the shape of analysis technique; the discrete wavelet transform(DWT). The feature vectors obtained using wavelet analysis is classified using a multi-layer neural network. The results show that, compared with the use of fourier descriptors, recognition using wavelet is more stable and efficient representation. And particularly the performance for objects corrupted with noise is better than that of other method.