• International Journal of Control, Automation, and Systems
• /
• v.4 no.3
• /
• pp.365-371
• /
• 2006

This paper presents an algorithm based on a combination of Discrete Wavelet Transforms and neural networks for detection and classification of internal faults in a two-winding three-phase transformer. Fault conditions of the transformer are simulated using ATP/EMTP in order to obtain current signals. The training process for the neural network and fault diagnosis decision are implemented using toolboxes on MATLAB/Simulink. Various cases and fault types based on Thailand electricity transmission and distribution systems are studied to verify the validity of the algorithm. It is found that the proposed method gives a satisfactory accuracy, and will be particularly useful in a development of a modern differential relay for a transformer protection scheme.

• Proceedings of the KIPE Conference
• /
• 2005.07a
• /
• pp.487-489
• /
• 2005

This paper presents a wavelet-based neural network technology for the detection and classification of the short durations type of power quality disturbances. Transients happen during very short durations to the nano- and microsecond. Thus, a method for detecting and classifying transient signals at the same time and In an automatic combines the properties of the wavelet transform and the advantages of neural networks. Especially, the additional feature extraction to improve the recognition rate is considered. The configuration of the hardware of TMS320C6711 DSP based with 16 channel 20Mhz sampling rate A/D(Analog to Digital) converter and some case studies are described.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.195-196
• /
• 2008

ECG 기반의 부정맥 자동 분류에 관한 연구는 지난 수십 년간 다양한 방법으로 연구되어 왔다. 많은 연구들이 부정맥을 구별해 낼 수 있는 특징 벡터를 찾아내기 위해 연구하였으나, 피험자의 ECG 특징이 각기 다르기 때문에 부정맥으로 인한 차이와 개인 간 차이를 구별하기 어려웠다. 생체데이터는 그 특성상 서로 다른 특징을 갖고 있으며, 다양한 특징을 가진 사람들에게 적용하기 위한 범용성과 부정맥 검출의 정확성 사이에 교환적 관계를 갖게 된다. 특히 ECG 데이터의 경우 사람 식별 데이터로 사용하고자 하는 연구가 있을 정도로 개인 간 편차가 분명하다. wavelet 분석방법은 다양한 mother wavelet을 사용할 수 있다는 점을 큰 장점으로 가지고 있으며, wavelet parameterization 기법을 사용하여 임의의 직교 wavelet basis를 발생시킬 수 있다. 본 논문은 wavelet parameterization을 사용하여 개인 간의 ECG 파형의 차이를 상쇄시키고, 부정맥의 차이만을 부각시킴으로써 ECG 기반의 부정맥 자동 분류 성능을 높이고자 하는데 목적이 있다.

• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.369-372
• /
• 2000

An overview on applications of wavelet transform in power systems presented in this paper. Wavelet transform is capable of making trade-offs between time and frequency resolutions, which is a property that makes it appropriate for the analysis of non stationary signal. In recent years, wavelet transform is widely accepted as a technology offering an alternative way due to its flexibility in representation of non-stationary signal even in power systems. This paper presents various applications of wavelet transform in power systems. Wavelet transform has been used by the authors in the field of power system protection for the classification of transient signals, and forecasting of short term loads and system marginal price and so on. Various research works carried out by many researchers in power systems are summarized.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.340-342
• /
• 2001

본 논문은 유방질환 중에서 Duct(관)에 발생하는 유방 종양을 benign(양성종양)/DCIS (Ductal Carcinoma In Situ)/NOS(Invasive ductal carcinoma)로 자동 분류하기 위한 분류방법을 제안한다. 분류기 생성에서 가장 중요한 단계인 특징 추출단계에서는 wavelet 변환을 적용하였으며, wavelet 변환의 각 depth에 따라 분류기를 생성하여, depth와 생성된 분류기의 분류 정확도와의 상관관계를 비교.분석하였다. 현미경 100배 배율과 400배 배율의 유방 질환 영상을 1, 2, 3, 4단계(depth)의 wavelet 변환을 적용한 후, 분할된 서브밴드에서 GLCM을 이용하여 질감 특징(Entropy, Energy, Contrast, Homogeneity)을 추출하여, 이 특징값들을 조합하여 판별분석에 의해 분류기(classifier)를 생성한 후, 분류 정확도를 검증하였다. Benign/DCIS/NOS를 분류하려면 최소 3단계 이상의 wavelet 변환을 적용해야 하고, 400배 배율 영상보다는 100배 배율의 영상이 더 나은 결과를 보였다.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2000.07a
• /
• pp.645-650
• /
• 2000

The discrete wavelet transform is utilized as processing of neural network(NN) to identifying aging state of internal partial discharge in transformer. The discrete wavelet transform is used to produce wavelet coefficients which are used for classification. The mean values of the wavelet coefficients are input into an back-propagation neural network. The networks, after training, can decide if the test signals is aging early state or aging last state, or normal state.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.178-181
• /
• 2005

Support vector machines is a powerful learning algorithm and attempt to separate belonging to two given sets in N-dimensional real space by a nonlinear surface, often only implicitly dened by a kernel function. We described breast tissue images analyses using texture features from Haar wavelet transformed images to classify breast lesion of ductal organ Benign, DCIS and CA. The approach for creating a classifier is composed of 2 steps: feature extraction and classification. Therefore, in the feature extraction step, we extracted texture features from wavelet transformed images with $10{\times}$ magnification. In the classification step, we created four classifiers from each image of extracted features using SVM(Support Vector Machines). In this study, we conclude that the best classifier in histological sections of breast tissue in the texture features from second-level wavelet transformed images used in Polynomial function.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.609-612
• /
• 1999

In this paper, we propose wavelet transform image compression method such that an image is decomposed into multiresolutions using biorthogonal wavelet transform with linear phase response property and decomposed subbands are classified by maximum classification gain. The classified data is quantized by allocating bits in accordance with classified class informations within subbands through arbitrary set bit allocation algorithm. And then, quantized data in each subband are entropy coded. The proposed coding method is that the quantized data perform shuffling before entropy coding in order to remove sign bit plane. And the context is assigned by maximum correlation direction for bit plane coding.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.263-264
• /
• 2008

A method for high impedance fault(HIF) detection based on wavelet transform is presented in this paper. HIF is detected and classified by obtaining the energy distribution curve from the wavelet coefficients at each level. The energy distribution of each transient disturbance has unique deviation from sinusoidal wave in particular energy level, which is adopted to provide reliable classification of the type of transient.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.55-59
• /
• 2008

For effective mobility control of UGV(unmanned ground vehicle), the terrain cover classification is an important component as well as terrain geometry recognition and obstacle detection. The vision based terrain cover classification algorithm consists of pre-processing, feature extraction, classification and post-processing. In this paper, we present a method to classify terrain covers based on the color and texture information. The color space conversion is performed for the pre-processing, the wavelet transform is applied for feature extraction, and the SVM(support vector machine) is applied for the classifier. Experimental results show that the proposed algorithm has a promising classification performance.