• 한국통신학회논문지
• /
• 제28권8C호
• /
• pp.788-794
• /
• 2003

영상 잡음의 제거를 위해서는 영상에 대한 통계적 모델을 설정하고, 잡음이 섞인 영상에서 원 영상의 분산을 정확하게 추정하는 것이 매우 중요하다. 추정된 원 영상의 분산을 이용하여 잡음 영상에 Wiener 필터를 적용함으로써 영상의 잡음을 제거하는 것이 일반적이다. 본 논문에서는 영상의 잡음을 제거하기 위해 웨이블릿 계수의 새로운 통계적 혼합 모델링을 제안한다. 먼저 웨이블릿 계수의 중요한 특성을 획득할 수 있는 중요도(重要圖)를 작성하기 위해 간단한 분류 방법을 사용한다. 분류된 중요도에 혼합 모델의 상태 확률을 계산하고, 이를 이용하여 신호의 분산을 추정한다. 실험 결과를 통하여 제안 방법이 기존의 방법보다 0.1-0.2㏈ 정도 높은 PSNR을 보여준다는 것을 알 수 있다.

• 대한전자공학회논문지SP
• /
• 제48권4호
• /
• pp.76-85
• /
• 2011

본 논문에서는 Gabor 특징과 웨이브렛 영역의 BDIP와 BVLC 특징을 이용한 질감 특징 기반 언어 인식 방법을 제안한다. 제안된 방법에서는 먼저 시험 영상에 Gabor 변환과 웨이브렛 변환을 적용한다. 웨이브렛 영역의 상세 대역에는 Donoho의 연역치화를 적용하여 잡음을 제거한다. 이어서 Gabor 영상에는 크기 연산자를 적용하고 웨이브렛 부대역에는 BDIP와 BVLC 연산자를 적용한다. 그런 다음 Gabor 크기 영상과 BDIP, BVLC 부대역에 대하여 통계치를 계산하여 그 결과들을 벡터화하고 융합하여 특징 벡터로 사용한다. 분류 단계에서는 얼굴 인식에 주로 사용되는 WPCA를 분류기로 하여 시험 특징 벡터와 가장 유사한 학습 특징 벡터를 찾는다. 실험 결과 제안된 방법은 실험 문서 영상 DB에 대하여 비교적 낮은 특징 벡터 차원으로 매우 우수한 언어 인식 성능을 보여준다.

• 대한전자공학회논문지SP
• /
• 제39권2호
• /
• pp.87-95
• /
• 2002

반화소 단위 움직임 추정(half pixel accuracy motion estimation, HPAME)과 블록 분류(block classification)를 이용한 계층적 고속 움직임 추정 알고리듬을 제안하였다 제안한 알고리듬은 기존의 MRME(multi-resolution motion estimation)알고리듬보다 우수한 화질을 유지하면서 계산량 및 비트량을 크게 줄일 수 있는 장점을 갖는다. 제안한 알고리듬에서는 다해상도 영상에 대한 움직임 추정 시 고주파 부대역의 움직임 추정에 기준 움직임으로 사용되는 기저대역의 움직임 벡터를 정확하게 추정하기 위하여 HPAME을 행한다. 그리고 고주파 부대역에서는 기저대역에서의 HPAME로 인한 계산량 및 비트량의 증가를 보상하기 위하여 움직임 추정이 필요한 블록들에 대하여서만 선별적으로 미소 움직임을 추정한다. 이때 고주파 부대역에서의 미소 움직임 추정의 수행 여부는 대응되는 기저대역 블록의 움직임 벡터 특성과 블록 분류에 따른 클래스 정보를 이용하여 결정한다 제안한 알고리듬의 성능은 컴퓨터 모의 실험 결과로부터 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제21권2호
• /
• pp.137-144
• /
• 2000

Clustered microcalcifications in X-ray mammograms are an important sign for the diagnosis of breast cancer. A shape-based method, which is based on the morphological features of clustered microcalcifications, is proposed for classifying clustered microcalcifications into benign or malignant categories. To verify the effectiveness of the proposed shape features, clinical mammograms were used to compare the classification performance of the proposed shape features with those of conventional textural features, such as the spatial gray-leve dependence method and the wavelet-based method. Image features extracted from these methods were used as inputs to a three-layer backpropagation neural network classifier. The classification performance of features extracted by each method was studied by using receiver operating-characteristics analysis. The proposed shape features were shown to be superior to the conventional textural features with respect to classification accuracy.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 C
• /
• pp.1030-1032
• /
• 1998

In this paper, an efficient feature vector extraction method and MLP neural network are utilized to automatically detect and classify power quality disturbances, where the proposed classification procedure consists of the following three parts: i.e., (i) PQ disturbance detection using discrete wavelet transform. (ii) feature vector extraction from the detected disturbance. using several methods, such as FFT, DWT, Fisher's criterion. etc.. and (iii) classification of the corresponding type of each PQ disturbance by recognizing the pattern of the extracted feature vector. To demonstrate the performance and, applicability of the proposed classification algorithm. some test results obtained by analyzing 10-class PQ disturbances are also provided.

• Journal of Information Processing Systems
• /
• 제15권2호
• /
• pp.422-432
• /
• 2019

A hybrid kernel function of support vector machine is proposed to improve the classification performance of power quality disturbances. The kernel function mathematical model of support vector machine directly affects the classification performance. Different types of kernel functions have different generalization ability and learning ability. The single kernel function cannot have better ability both in learning and generalization. To overcome this problem, we propose a hybrid kernel function that is composed of two single kernel functions to improve both the ability in generation and learning. In simulations, we respectively used the single and multiple power quality disturbances to test classification performance of support vector machine algorithm with the proposed hybrid kernel function. Compared with other support vector machine algorithms, the improved support vector machine algorithm has better performance for the classification of power quality signals with single and multiple disturbances.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 1999년도 추계학술대회-지능형 정보기술과 미래조직 Information Technology and Future Organization
• /
• pp.365-373
• /
• 1999

Recently, numerous studies have demonstrated that artificial intelligence such as neural networks can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. In building neural network model, the selection of independent and dependent variables should be approached with great care and should be treated as a model construction process. Irrespective of the efficiency of a learning procedure in terms of convergence, generalization and stability, the ultimate performance of the estimator will depend on the relevance of the selected input variables and the quality of the data used. Approaches developed in statistical methods such as correlation analysis and stepwise selection method are often very useful. These methods, however, may not be the optimal ones for the development of neural network models. In this paper, we propose a genetic algorithms approach to find an optimal or near optimal input variables for neural network modeling. The proposed approach is demonstrated by applications to bankruptcy prediction modeling. Our experimental results show that this approach increases overall classification accuracy rate significantly.

• 한국지능시스템학회논문지
• /
• 제16권3호
• /
• pp.378-382
• /
• 2006

본 논문은 가중 퍼지소속함수 기반 신경망(neural network with weighted fuzzy membership functions, NEWFM)을 이용하여 심전도(ECG) 신호로부터 조기심실수축(premature ventricular contractions, PVC)을 자동 탐지하는 방안을 제시하고 있다. NEWFM은 MIT-BIH 데이터베이스의 부정맥 심전도를 웨이블릿 변환(wavelet transform, WT)한 계수로부터 학습하여 정상 파형과 PVC 파형을 구분한다. 비중복면적 분산 측정법을 적용하여 중요도가 가장 높은 계수 2개를 추출하여 분류규칙을 최소화하였고, 이를 사용하여 99.90%의 PVC 분류성능을 나타내었다. 또한 추출된 두 계수의 R파를 기준으로 한 위치를 제시함으로써 두 위치의 정보만으로 PVC를 탐지할 수 있음을 보여주었다.

• Smart Structures and Systems
• /
• 제22권2호
• /
• pp.175-183
• /
• 2018

Time-series data often contain one of the most valuable pieces of information in many fields including manufacturing. Because time-series data are relatively cheap to acquire, they (e.g., vibration signals) have become a crucial part of big data even in manufacturing shop floors. Recently, deep-learning models have shown state-of-art performance for analyzing big data because of their sophisticated structures and considerable computational power. Traditional models for a machinery-monitoring system have highly relied on features selected by human experts. In addition, the representational power of such models fails as the data distribution becomes complicated. On the other hand, deep-learning models automatically select highly abstracted features during the optimization process, and their representational power is better than that of traditional neural network models. However, the applicability of deep-learning models to the field of prognostics and health management (PHM) has not been well investigated yet. This study integrates the "residual fitting" mechanism inherently embedded in the wavelet transform into the convolutional neural network deep-learning structure. As a result, the architecture combines a signal smoother and classification procedures into a single model. Validation results from rotor vibration data demonstrate that our model outperforms all other off-the-shelf feature-based models.

• 한국지구물리탐사학회:학술대회논문집
• /
• 한국지구물리탐사학회 2009년도 특별 심포지엄
• /
• pp.35-45
• /
• 2009

Reservoir Characterization (RC) using 3-D seismic attributes analysis can provide properties of the oil sand reservoirs, beyond seismic resolution. For example, distributions and temporal bed thicknesses of reservoirs could be characterized by Spectral Decomposition (SD) and additional seismic attributes such as wavelet classification. To extract physical properties of the reservoirs, we applied 3-D seismic attributes analysis to the oil sand reservoirs in McMurray formation, in BlackGold Oilsands Lease, Alberta Canada. Because of high viscosity of the bitumen, Enhanced Oil Recovery (EOR) technology will be necessarily applied to produce the bitumen in a steam chamber generated by Steam Assisted Gravity Drainage (SAGD). To optimize the application of SAGD, it is critical to identify the distributions and thicknesses of the channel sand reservoirs and shale barriers in the promising areas. By 3-D seismic attributes analysis, we could understand the expected paleo-channel and characteristics of the reservoirs. However, further seismic analysis (e.g., elastic impedance inversion and AVO inversion) as well as geological interpretations are still required to improve the resolution and quality of RC.