• 정보처리학회논문지B
• /
• 제10B권4호
• /
• pp.459-464
• /
• 2003

본 논문에서 제안한 위치 이동에 무관한 웨이블렛 변환을 이용한 홍채 인식 방법은 영상 획득 장비에 의해 획득한 사용자의 눈 영상에 대하여 홍채 영역만을 추출하기 위한 전처리를 수행하고 전처리를 거친 홍채 영상에 의하여 사용자의 신원을 식별하는데 있어서 홍채 영상의 기울어짐 및 이동 문제를 해결하였다. 이를 위해서 일반적인 웨이블렛을 사용하는 대신, 위치 이동에 무관한 웨이블렛 변환을 통하여 최적의 특징값을 추출한후, 이를 코드화하여 저장한 후, 비교하여 본인 여부를 식별하였다. 실험결과 제안된 방법으로 생성된 특징 벡터와 기존에 등록된 특징 벡터의 일치도 측정에 있어서 종래의 웨이블렛 변환 홍채 인식 방법보다 오인식률(FAR) 및 오거부율(FRR)이 현저하게 감소하였다.

• 대한전기학회논문지:전력기술부문A
• /
• 제51권9호
• /
• pp.417-424
• /
• 2002

This paper presents an industrial peak load management system for the peak demand control. Kohonen neural network and wavelet transform based techniques are adopted for industrial peak load forecasting that will be used as input data of the peak demand control. Firstly, one year of historical load data of a steel company were sorted and clustered into several groups using Kohonen neural network and then wavelet transforms are applied with Biorthogonal 1.3 mother wavelet in order to forecast the peak load of one minute ahead. In addition, for the peak demand control, composite fuzzy model is proposed and implemented in this work. The results are compared with those of conventional model, fuzzy model and composite model, respectively. The outcome of the study clearly indicates that the composite fuzzy model approach can be used as an attractive and effective means of the peak demand control.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.640-645
• /
• 2004

This paper proposes a direct adaptive control method using self-recurrent wavelet neural network (SRWNN) for stable path tracking of mobile robots. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). Unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN has the ability to store the past information of the wavelet. For this ability of the SRWNN, the SRWNN is used as a controller with simpler structure than the WNN in our on-line control process. The gradient-descent method with adaptive learning rates (ALR) is applied to train the parameters of the SRWNN. The ALR are derived from discrete Lyapunov stability theorem, which are used to guarantee the stable path tracking of mobile robots. Finally, through computer simulations, we demonstrate the effectiveness and stability of the proposed controller.

• Tribology and Lubricants
• /
• 제24권6호
• /
• pp.320-325
• /
• 2008

The recent industrial application requires technical methods to get the cutting fluid droplet surfaces in particular from the viewpoint of topography and micro texture. To characterize the surface topography of droplet, the combination of the confocal laser scanning microscope (CLSM) and wavelet filtering is well suited for obtaining the droplet geometry encountered in tribological research. This technique indicates a better agreement in obtaining an appropriate droplet surface obtained by the CLSM over a detail range of surface accuracy (resolution: $2{\mu}m$). And the results allow an excellent accuracy in a measurement of a droplet surface. The combination of extended focal depth measurement configured and multi-scale wavelet filtering has proven that it can construct a droplet surface in a successive and accurate way. A multi-scale approach of wavelet filtering was developed based on the decomposition and reconstruction of droplet surface by 2D wavelet transform using db9 (a mother wavelet of daubechies). Also this technique can be extended to characterize the quantification of droplet properties and other field in a wide range of scales. Finally this method is verified to be a better droplet surface modeling in a micro scale arising in a mist machining.

• Transactions on Electrical and Electronic Materials
• /
• 제18권4호
• /
• pp.221-224
• /
• 2017

This paper dealt with the extraction of series arc signals based on wavelet transform in order to improve the accuracy of arc detection in indoor wiring systems. Three types of arc sources including a cord-cord, a terminal-cord, and an outlet-plug were fabricated to simulate typical arc defects. An arc generator fabricated according to UL 1699 was used to generate arcs. The optimal mother wavelet was selected as bior1.5 by calculating the correlation coefficients between the detected single current pulse and the wavelet. The detected arc current signals were then decomposed into eight levels using the discrete wavelet transform that implements the multi-resolution analysis method. By analyzing the decomposed components, the detail components D6, D7, and D8 were associated with arc signals, which were used for signal reconstruction. From the result, it was verified that the proposed method can be used for the extraction of the series arc signal from the AC mains, which is expected to be applied to further analysis of arc signals in indoor wiring systems.

• 한국음향학회지
• /
• 제20권5호
• /
• pp.21-27
• /
• 2001

기어 시스템의 충격음과 충격 신호는 대개 기어의 결함과 관련이 있다. 그래서 이러한 충격음과 충격 신호는 기어 시스템의 건전성 감시의 주요 요소로 사용되어진다. 본 연구에서는 이런 충격음과 충격 신호를 효율적으로 추출해 내기 위해 스파이크 웨이블렛 변환을 이용하는 방법을 제안한다. 스파이크 웨이블렛 변환은 기존에 제안된 연속 웨이블렛 변환의 한계점인 임의의 영역에서의 시간-주파수 분해능의 스케일 변수에 대한 선형성을 보완하여 비 선형적으로 이것을 조절할 수 있게 하였다. 이로 인해서 스파이크 웨이블렛 변환은 관심 주파수를 기준으로 연속 웨이블렛 변환보다 고주파 영역에서는 시간 분해능이 향상되고 동시에 저주파 영역에서는 주파수 분해능이 향상되어 기어 결함에 대한 정보 손실 없이 기어의 결함 위치를 보다 명확히 판단할 수 있는 장점을 가진다. 또한 본 연구에서는 상단 절손의 결함을 갖는 기어에 대한 실험을 통해 본 연구에서 제안하는 스파이크 웨이블렛 변환의 유용성을 검증하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 D
• /
• pp.2209-2211
• /
• 2004

Unlike the wavelet neural network, since a mother wavelet layer of the self-recurrent wavelet neural network (SRWNN) is composed of self-feedback neurons, it has the ability to store past information of the wavelet. Therefore we propose the prediction method for the nonlinear chaotic time series model using a SRWNN. The SRWNN model is learned for the modeling of a function such that the inputs arc known values of the time series and the output is the value in the future. The parameters of the network are tuned to minimize the difference between the nonlinear mapping of the chaotic time series and the output of SRWNN using the gradient-descent method for the adaptive backpropagation algorithm. Through the computer simulations, we demonstrate the feasibility and the effectiveness of our method for the prediction of the logistic map and the Mackey-Glass delay-differential equation as a nonlinear chaotic time series.

• Smart Structures and Systems
• /
• 제18권5호
• /
• pp.1063-1085
• /
• 2016

Taking advantage of the high sensitivity and long-distance detection capability of acoustic emission (AE) technique, this paper focuses on the crack detection in rail head, which is one of the most vulnerable parts of rail track. The AE source location and noise cancellation were studied on the basis of practical rail profile, material and operational noise. In order to simulate the actual AE events of rail head cracks, field tests were carried out to acquire the AE waves induced by pencil lead break (PLB) and operational noise of the railway system. Wavelet transform (WT) was first utilized to investigate the time-frequency characteristics and dispersion phenomena of AE waves. Here, the optimal mother wavelet was selected by minimizing the Shannon entropy of wavelet coefficients. Regarding the obvious dispersion of AE waves propagating along the rail head and the high operational noise, the wavelet transform-based modal analysis location (WTMAL) method was then proposed to locate the AE sources (i.e. simulated cracks) respectively for the PLB-induced AE signals with and without operational noise. For those AE signals inundated with operational noise, the Hilbert transform (HT)-based noise cancellation method was employed to improve the signal-to-noise ratio (SNR). Finally, the experimental results demonstrated that the proposed crack detection strategy could locate PLB-simulated AE sources effectively in the rail head even at high operational noise level, highlighting its potential for field application.

• Journal of Biosystems Engineering
• /
• 제33권5호
• /
• pp.317-325
• /
• 2008

The electrocardiogram (ECG) measurement system consists of I/O interface to input the ECG signals from two electrodes, FPGA (Field programmable gate arrays) module to process the signal conditioning, and real time module to control the system. The algorithms based on wavelet transform were developed to remove the noise of the ECG signals and to determine the QRS-waves. Triangular wave tests were conducted to determine the optimal factors of the wavelet filter by analyzing the SNRs (signal to noise ratios) and RMSEs (root mean square errors). The hybrid rule, soft method, and symlets of order 5 were selected as thresholding rule, thresholding method, and mother wavelet, respectively. The developed wavelet filter showed good performance to remove the noise of the triangular waves with 10.98 dB of SNR and 0.140 mV of RMSE. The ECG signals from a total of 6 subjects were measured at different measuring postures such as lying, sitting, and standing. The durations of QRS-waves, the amplitudes of R-waves, the intervals of RR-waves were analyzed by using the finite impulse response (FIR) filter and the developed wavelet filter. The wavelet filter showed good performance to determine the features of QRS-waves, but the FIR filter had some problems to detect the peaks of Q and S waves. The measuring postures affected accuracy and precision of the ECG signals. The noises of the ECG signals were increased due to the movement of the subject during measurement. The results showed that the wavelet filter was a useful tool to remove the noise of the ECG signals and to determine the features of the QRS-waves.

• 한국통신학회논문지
• /
• 제24권12B호
• /
• pp.2369-2381
• /
• 1999

본 논문에서는 웨이브렛 변환을 이용하여 블록기반 변환 부호화 영상에서의 블록화 현상을 반복적으로 제거하는 방법을 제안하였다. 제안된 방법에서는 블록화 현상이 수직, 수평 방향의 블록 경계를 따라 수직, 수평으로만 나타나는 점에 착안하여, 블록화 현상이 있는 영상 신호를 수직, 수평 방향의 분리적인 1차원 신호의 집합으로 간주하고 Gaussian 형태 함수의 1차 도함수를 모 웨이브렛으로 하는 1차원 웨이브렛 영역에서의 평균 자승 오차를 최소화시키는 필터로써 첫 번째 스케일 웨이브렛 영역의 블록 경계 위치에서의 분산이 다른 위치에 비하여 유달리 크게 나타나도록 하는 블록화 현상에 의한 신호 성분을 제거하는 과정과 양자화에 관한 블록 집합으로 투영하는 과정을 반복적으로 수행하여 블록화 현상이 제거된 영상을 얻는다. 실험결과, 제안된 방법은 0.56 - 1.07dB의 PSNR 성능 향상뿐만 아니라 에지 몽롱화가 없이 블록화 현상이 거의 제거된 주관적 화질 개선을 보였다.