• Journal of Biomedical Engineering Research
• /
• v.24 no.6 s.81
• /
• pp.487-494
• /
• 2003

The sleep stages provides the most basic evidence for diagnosing a variety of sleep diseases. for staging sleep by analysis of EEG(electroencephalogram), it is especially important to detect the characteristic waveforms from EEG. In this paper, sleep EEG signals were analyzed using Fourier transform and continuous wavelet transform as well as discrete wavelet transform. Proposeed system methods. Fourier and wavelet for detecting of important characteristic waves(hump, sleep spindles. K-complex, hill wave, ripple wave) in sleep EEG. Sleep EEG data were analysed using Daubechies wavelet transform method and FFT method. As a result of simulation, we suggest that our neural network system attain high performance in classification of characteristic waves.

• 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.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.3 s.309
• /
• pp.67-77
• /
• 2006

This thesis proposes an effi챠ent method for extracting a prostate volume from 3D ultrasound image by using wavelet transform and SVM classification. In the proposed method, a modulus image for each 2D slice is generated by averaging detail images of horizontal and vertical orientations at several scales, which has the sharpest local maxima and the lowest noise power compared to those of all single scales. Prostate contour vertices are determined accurately using a SVM classifier, where feature vectors are composed of intensity and texture moments investigated along radial lines. Experimental results show that the proposed method yields absolute mean distance of on average 1.89 pixels when the contours obtained manually by an expert are used as reference data.

• Journal of the Korean Society for Railway
• /
• v.13 no.3
• /
• pp.304-308
• /
• 2010

This paper presents a methodology for identifying track irregularity using a wavelet transfer function. An equivalent wavelet SISO (single-input single-output) transfer function is defined by the measured track geometry and the acceleration data measured at a bogie of a train. All the measured data with various sampling frequencies were rearranged according to the constant 25cm reference recording distance of the track recording vehicle used in the field. Before applying the wavelet transform, measured data were regressed by eliminating those out of the range. The inverse wavelet transfer function is also formulated to estimate track geometry. The closeness of the estimated track geometry to the actual one is evaluated by the coherence function and also by FRF (frequency response function). A track irregularity index is defined by comparing the variance of the estimation error from the intact condition and that from the current condition. A simulation study has been carried out to examine the proposed algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.397-404
• /
• 2002

In this paper, it is proposed wavelet neural network using the fuzzy concept with the fuzzy and the multi-resolution analysis(MRA) of wavelet transform. Also, it wishes to improve any nonlinear function learning approximation using this system. Here, the fuzzy concept is used the bell type fuzzy membership function. And the composition of wavelet has a unit size. It is used the backpropagation algorithm for learning of wavelet neural network using the fuzzy concept. It is used the multi-resolution analysis of wavelet transform, the bell type fuzzy membership function and the backpropagation algorithm for learning. This structure is confirmed to be improved approximation performance than the conventional algorithms from one dimension and two dimensions function through simulation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.349-351
• /
• 2001

본 논문에서는 원 영상의 영역 분류와 웨이브렛 변환을 이용하여 영상의 밝기 변화에 관계없이 영상 검색이 가능한 알고리즘을 제안하였다. 이러한 방식을 통해 영상 전체에 대해 검색이 수행되지 않고, 영역 분류 결과인 블록맵과 변환 대역에서의 분산값 등 매우 소량의 정보만을 저장하고 이를 기반으로 영상 검색이 수행되므로 매우 빠르고 효과적인 검색이 가능함을 실험을 통해 확인하였다.

• The KIPS Transactions:PartB
• /
• v.8B no.4
• /
• pp.395-402
• /
• 2001

본 논문에서는, 1차원 및 2차원 웨이브렛 함수를 전역통과필터(APF)와 지연기의 병렬접속에 위한 재귀형(IIR) 디지털 필터로 구성하는 방법을 제안한다. Mallat에 의하여 웨이브렛 변환과 필터뱅크가 밀접한 관계에 있다는 것이 알려졌고, 완전 재구성 필터뱅크로부터 웨이브렛 함수를 도출하는 다양한 방법이 알려져 있다. 그러나, 이러한 방법의 대부분은 비재귀형(FIR) 디지털 필터에 근거를 두는 것으로, 재귀형 디지털 필터에 의한 방법은 거의 제안되어 있지 않다. 재귀형 필터를 이용하는 장점은 비재귀형에 비하여 낮은 차수로 표현되는 점이다. 또 직교 웨이브렛 함수를 끌어내기 위한 직교조건을 용이하게 만족시킬 수 있다. 본 논문에서는 웨이브렛 함수에 요구되는 레귤레리티(Regularity)조건을 만족시키기 위하여, 최대 평탄성(Maximally Flat)을 부가한 새로운 1차원 및 2차원 재귀형 웨이브렛 함수의 도출법을 보인다.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.783-786
• /
• 2000

본 논문에서는 웨이브렛 변환을 적용한 광대역 음성부호화 알고리즘을 제안하였다. 제안한 음성부호화 알고리즘은 split-band 구조를 가지며, 16 kHz로 sampling된 입력신호를 QMF를 이용해서 동일한 대역폭을 갖는 두 개의 subband 신호로 나누고 이를 8kHz의 sampling율을 갖도록 downsampling 한다. 그리고 저대역 신호는 GSM-EFR 음성부호화 알고리즘을 이용하여 부호화하고, 고대역 신호는 DWT(Discrete Wavelet Transform)을 적용하여 subband로 나누어 부호화하였다. 각 subband에서 양자화 된 파라미터는 IDWT(Inverse DWT)과정을 거쳐서 upsampling되고 합성 QMF를 통과시켜 최종 합성음을 구하였다. 제안한 음성부호화기는 저대역 신호의 GSM-EFR 부호화에 12.2 kbps, 웨이브렛 변환을 이용한 고대역 신호의 부호화에 7.8 kbps로 전체 20 kbps의 전송율을 가지면서 G.722 표준안의 56 kbps에서의 합성음과 비슷한 음질을 나타내었다.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.5
• /
• pp.27-34
• /
• 2000

This paper deals with speech enhancement methods using the wavelet transform. A cycle-spinning scheme and undecimated wavelet transform are used for denoising of speech signals, and then their results are compared with that of the conventional wavelet transform. We apply soft-thresholding technique for removing additive background noise from noisy speech. The symlets 8-tap wavelet and pyramid algorithm are used for the wavelet transform. Performance assessments based on average SNR, cepstral distance and informal subjective listening test are carried out. Experimental results demonstrate that both cycle-spinning denoising(CSD) method and undecimated wavelet denoising(CWD) method outperform conventional wavelet denoising(UWD) method in objective performance measure as welt as subjective listening test. The two methods also show less "clicks" that usually appears in the neighborhood of signal discontinuities.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.15 no.4
• /
• pp.62-68
• /
• 2001

In this paper, As the wavelet transform has the properties of multi-resolution analysis and time-frequency domain localization, application of wavelet transform is used at partial discharge(PD) signal detected by electrical detection method to extract PD signal's various frequency component and its time domain. therefore we can analyzed PD signal's time-frequency domain simultaneously. On the other hand, using wavelet transform denoising process, included noise signal in detected PD signal is well eliminated. we can propose the true shine of PD signal.