• Proceedings of the Acoustical Society of Korea Conference
• /
• 1997.06a
• /
• pp.5-8
• /
• 1997

음성신호는 성대를 통과한 공기 흐름의 성질에 따라 유성음과 무성음으로 구분될 수 있다. 그 중 유성음에서는 성대의 규칙적인 지동이 존재하게 된는 데 이때 성대가 닫히는 순간을 GCI(Glotal Closure Instant)라 하며 성대 진동의 기본주기를 피치라고 한다. 이러한 피치는 음성합성, 음성인식, 피치동기 음성신호의 분석등에 중요한 파라미터 중의 하나이다. 본 논문에서는 가우시안 함수의 일차미분형태를 갖는 웨이브렛 함수를 사용할 경우 신호의 급격한 변화부분을 검출할 수 있다는 성질을 이용하여 음성 신호의 GCI를 찾아내고 이를 이용하여 피치를 검출하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.1-10
• /
• 2022

Deep neural networks are widely used to solve various problems. In a fully connected neural network, the nonlinear activation function is a function that nonlinearly transforms the input value and outputs it. The nonlinear activation function plays an important role in solving the nonlinear problem, and various nonlinear activation functions have been studied. In this study, we propose a combined parametric activation function that can improve the performance of a fully connected neural network. Combined parametric activation functions can be created by simply adding parametric activation functions. The parametric activation function is a function that can be optimized in the direction of minimizing the loss function by applying a parameter that converts the scale and location of the activation function according to the input data. By combining the parametric activation functions, more diverse nonlinear intervals can be created, and the parameters of the parametric activation functions can be optimized in the direction of minimizing the loss function. The performance of the combined parametric activation function was tested through the MNIST classification problem and the Fashion MNIST classification problem, and as a result, it was confirmed that it has better performance than the existing nonlinear activation function and parametric activation function.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.1
• /
• pp.36-42
• /
• 2006

A Principal component analysis (PCA)-based Mel-Frequency Discrete Wavelet Coefficients (MFDWC) feature Parameters for speaker verification system is Presented in this Paper In this method, we used the 1st-eigenvector obtained from PCA to calculate the energy of each node of level that was approximated by. met-scale. This eigenvector satisfies the constraint of general weighting function that the squared sum of each component of weighting function is unity and is considered to represent speaker's characteristic closely because the 1st-eigenvector of each speaker is fairly different from the others. For verification. we used Universal Background Model (UBM) approach that compares claimed speaker s model with UBM on frame-level. We performed experiments to test the effectiveness of PCA-based parameter and found that our Proposed Parameters could obtain improved average Performance of $0.80\%$compared to MFCC. $5.14\%$ to LPCC and 6.69 to existing MFDWC.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.347-348
• /
• 2018

본 논문에서는 야간 도로 영상을 보정하여 주간 영상으로 변환하는 알고리즘을 제안한다. 영상 변환 딥러닝 알고리즘인 Generative Adversarial Network(GAN)를 기반으로 주야간 도로 영상을 학습시켜 주야간 상호 변환이 가능한 시스템을 구현한다. 우선, 입력 영상에 대해 변환된 영상을 출력하는 generative network 를 정의한다. 또한, 변환된 영상을 다시 본래 영상으로 변환하는 inverse network 를 정의한다. Generative network 와 inverse network 를 모두 통과한 결과 영상과 본래 영상의 차 영상을 통해 손실 함수를 정의함으로써 파라미터를 목적에 맞게 학습시킬 수 있다. 또한, generative network 를 통과한 결과 영상과 목적하는 영상을 구분하는 discrimination network 를 정의하여 discrimination network 와 generative network 의 minimax two- player game 을 통해 변환된 영상이 실제 목적 영상과 유사하도록 유도한다. 제안하는 알고리즘을 적용하여 야간 도로 영상의 보정을 수행하면 주변 물체 인식이 어려운 야간 영상을 물체 인식이 용이한 주간 영상으로 변환 할 수 있다.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.15 no.6
• /
• pp.82-88
• /
• 2001

This paper considers the problem of the identification of the time invariant parameters of distributed systems. In general, the parameters are identified by using the CBPOM(Conventional Block Pulse Operational Matrices), but in this paper, the parameters ard identified by using the EBPOMS(Extended Block Pulse Operational Matrices) which can reduce the burden of operation md the volume of error caused by matrices multiplication. The simulation cloves the effectiveness of the proposed method.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.129-132
• /
• 2002

본 논문은 웨이브렛 변환 다중해상도 분해(multi-resolution Analysis : MRA)와 적응성 뉴로-퍼지 인터페이스 시스템(Adaptive Neuro-Fuzzy Inference System : ANFIS)을 기반으로 한 웨이브렛 신경망을 가지고 임의의 비선형 함수 학습 근사화를 개선하는 것이다. ANFIS 구조는 벨형 퍼지 함수로 구성이 되었고, 웨이브렛 신경망은 전파 알고리즘과 역전파 신경망 알고리즘으로 구성되었다. 여기 웨이브렛 구성은 단일 크기이고, ANFIS 기반 웨이브렛 신경망의 학습을 위해 역전파 알고리즘을 사용하였다. 1차원과 2차원 함수에서 웨이브렛 전달 파라미터 학습과 ANFIS의 벨형 소속 함수를 이용한 ANFIS 모델 기반 웨이브렛 신경망의 웨이브렛 기저 수 감소와 수렴 속도 성능이 기존의 알고리즘 보다 개선되었음을 확인하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.3
• /
• pp.224-239
• /
• 2013

An exact performance analysis of an ML detector for a 2-dimensional rotation-transform aided QPSK system operating over an impulsive noise environment is presented using Rieman integrals of a two-dimensional Gaussian Q-function over Voronoi cells. A set of interesting features of the Voronoi cells is also characterised systematically. An optimum rotation angle yielding the minimum BER is also studied. The differences between the proposed exact method and the previous approximate analysis method are investigated in terms of the corresponding BERs and the derived optimum angles.

• The Journal of the Korea Contents Association
• /
• v.10 no.6
• /
• pp.329-335
• /
• 2010

Digital imaging detectors can use a variety of detection materials to convert X-ray radiation either to light or directly to electron charge. Many detectors such as amorphous silicon flat panels, CCDs, and CMOS photodiode arrays incorporate a scintillator screen to convert x-ray to light. The digital radiography systems based on semiconductor detectors, commonly referred to as flat panel detectors, are gaining popularity in the clinical & hospital. The X-ray detectors are described between a-Silicon based indirect type and a-Selenium based direct type. The DRS of detectors is used to convert the x-ray to electron hole pairs. Image processing is described by specific image features: Latitude compression, Contrast enhancement, Edge enhancement, Look up table, Noise suppression. The image features are tuned independently. The final enhancement result is a combination of all image features. The parameters are altered by using specific image features in the different several hospitals. The image in a radiological report consists of two image evaluation processes: Clinical image parameters and MTF is a descriptor of the spatial resolution of a digital imaging system. We used the edge test phantom and exposure procedure described in the IEC 61267 to obtain an edge spread function from which the MTF is calculated. We can compare image in the processing parameters to change between original and processed image data. The angle of the edge with respect to the axes of detector was varied in order to determine the MTF as a function of direction. Each MTF is integrated within the spatial resolution interval of 1.35-11.70 cycles/mm at the 50% MTF point. Each image enhancement parameters consists of edge, frequency, contrast, LUT, noise, sensitometry curve, threshold level, windows. The digital device is also shown to have good uniformity of MTF and image parameters across its modality. The measurements reported here represent a comprehensive evaluation of digital radiography system designed for use in the DRS. The results indicate that the parameter enables very good image quality in the digital radiography. Of course, the quality of image from a parameter is determined by other digital devices in addition to the proper clinical image.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1222-1227
• /
• 2006

본 연구의 목적은 객체의 형상정보(3D mesh)와 색/질감정보(image)를 이용하여 텍스쳐 맵핑된 고품질의 가상모델을 생성하는데 있다. 3 차원 형상정보에 대응하는 이미지 상의 텍스쳐 좌표 관계를 구하기 위해 오브젝트 좌표계와 카메라 좌표계 사이의 변환행렬, 카메라의 초점거리, 카메라 CCD 와 프레임상의 이미지 사이의 aspect ratio 를 파라미터로 하는 3D-2D 정합을 수행한다. 이러한 3D-2D 정합을 효율적으로 수행하기 위하여, 카메라 내부파라미터 검정단계, 신뢰도가 높은 초기해 설정단계, 비선형 최적화(Newton method) 단계로 접근한다. 또한, 색/질감정보로 이용되는 객체의 이미지는 촬영조건에 의해 스펙큘러(specular)나 이미지 픽셀값의 포화상태(saturation) 등의 결점을 포함한다. 영상내의 스펙큘러 좌표와 3D-2D 정합의 결과를 이용하여 촬영 당시의 광원을 추정하고, 근사화된 빛반사도 함수(BRDF)를 이용하여, 텍스쳐의 픽셀값 변조를 통해 이미지 촬영 당시의 광원효과가 제거된 디퓨즈 텍스쳐를 획득한다. 본 연구에서는 퐁(Phong)의 모델을 근사화한 빛 반사도 함수 모델로 사용하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.3
• /
• pp.229-237
• /
• 2008

In this research, a MDO(multi-disciplinary design optimization) framework, which integrates aerodynamic and structural analysis to design an aircraft wing, is constructed. Whole optimization process is automated by a parametric-modeling approach. A CFD mesh is generated automatically from parametric modeling of CATIA and Gridgen followed by automatic flow analysis using Fluent. Finite element mesh is generated automatically by parametric method of MSC.Patran PCL. Aerodynamic load is transferred to Finite element model by the volume spline method. RSM(Response Surface Method) is applied for optimization, which helps to achieve global optimum. As the design problem to test the current MDO framework, a wing weight minimization with constraints of lift-drag ratio and deflection of the wing is selected. Aspect ratio, taper ratio and sweepback angle are defined as design variables. The optimization result demonstrates the successful construction of the MDO framework.