• Journal of Electrical Engineering and Technology
• /
• 제13권6호
• /
• pp.2485-2492
• /
• 2018

The rapid development of large-scale integrated circuits has brought great challenges to the circuit testing and diagnosis, and due to the lack of exact fault models, inaccurate analog components tolerance, and some nonlinear factors, the analog circuit fault diagnosis is still regarded as an extremely difficult problem. To cope with the problem that it's difficult to extract fault features effectively from masses of original data of the nonlinear continuous analog circuit output signal, a novel approach of feature extraction and dimension reduction for analog circuit fault diagnosis based on wavelet packet decomposition, local linear embedding algorithm, and clone selection algorithm (WPD-LLE-CSA) is proposed. The proposed method can identify faulty components in complicated analog circuits with a high accuracy above 99%. Compared with the existing feature extraction methods, the proposed method can significantly reduce the quantity of features with less time spent under the premise of maintaining a high level of diagnosing rate, and also the ratio of dimensionality reduction was discussed. Several groups of experiments are conducted to demonstrate the efficiency of the proposed method.

• 한국정밀공학회지
• /
• 제28권3호
• /
• pp.330-338
• /
• 2011

Odometry is the critical factor to estimate the location of the robot. In the mobile robot with wheels, odometry can be performed using the information from the encoder. However, the information of location in the encoder is inaccurate because of the errors caused by the wheel's alignment or slip. In general, visual odometer has been used to compensate for the kinetic errors of robot. In case of using the visual odometry under some robot system, the kinetic analysis is required for compensation of errors, which means that the conventional visual odometry cannot be easily applied to the implementation of the other type of the robot system. In this paper, the novel visual odometry, which employs only the single camera toward the ground, is proposed. The camera is mounted at the center of the bottom of the mobile robot. Feature points of the ground image are extracted by using median filter and color contrast filter. In addition, the linear and angular vectors of the mobile robot are calculated with feature points matching, and the visual odometry is performed by using these linear and angular vectors. The proposed odometry is verified through the experimental results of driving tests using the encoder and the new visual odometry.

• 한국정보처리학회논문지
• /
• 제7권5호
• /
• pp.1361-1369
• /
• 2000

For the implementation of 3D Sound Localization system, the binaural filtering by HRTFs is generally employed. But the HRTF filter is of high order and its coefficients for all directions have to be stored, which imposes a rather large memory requirement. To cope with this, research works have centered on obtaining low dimensional HRTF representations without significant loss of information and synthesizing the original HRTF efficiently, by means of feature extraction methods for multivariate dat including PCA. In these researches, conventional linear PCA was applied to the frequency domain HRTF data and using relatively small number of principal components the original HRTFs could be synthesized in approximation. In this paper we applied neural network based nonlinear PCA model (NLPCA) and the nonlinear PLS repression model (NLPLS) for this low dimensional HRTF modeling and analyze the results in comparison with the PCA. The NLPCA that performs projection of data onto the nonlinear surfaces showed the capability of more efficient HRTF feature extraction than linear PCA and the NLPLS regression model that incorporates the direction information in feature extraction yielded more stable results in synthesizing general HRTFs not included in the model training.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.209-212
• /
• 2005

Hyperspectral data consists of more than 200 spectral bands that are highly correlated. In order to utilize hyperspectral data for classification, dimensional reduction or feature extraction is desired. By applying feature extraction, computational complexity of classification can be reduced and classification accuracy may be improved. In this paper, a genetic algorithm based feature extraction technique is proposed. Measure from discriminant analysis is utilized as optimization criterion. A subset of spectral bands is selected by genetic algorithm. Dimension of feature space is further reduced by linear transformation. Feasibility of the proposed technique is evaluated with AVIRIS data.

• Journal of Computational Design and Engineering
• /
• 제3권2호
• /
• pp.102-111
• /
• 2016

In this paper, we study the problem of computing smooth feature curves from CAD type point clouds models. The proposed method reconstructs feature curves from the intersections of developable strip pairs which approximate the regions along both sides of the features. The generation of developable surfaces is based on a linear approximation of the given point cloud through a variational shape approximation approach. A line segment sequencing algorithm is proposed for collecting feature line segments into different feature sequences as well as sequential groups of data points. A developable surface approximation procedure is employed to refine incident approximation planes of data points into developable strips. Some experimental results are included to demonstrate the performance of the proposed method.

• 전자공학회논문지SC
• /
• 제48권5호
• /
• pp.7-12
• /
• 2011

본 논문에서는 자료패턴을 분류하기에 적합한 특징을 추출하는 방법인, 클래스가 부가된 커널 주성분분석(class-augmented kernel principal component analysis)를 새로이 제안하였다. 특징추출에 널리 이용되는 부분공간 기법 중, 최근 제안된 클래스가 부가된 주성분분석(class-augmented principal component analysis)은 패턴 분류를 위한 특징을 추출하기 위해 이용되는 선형분류분석(linear discriminant analysis)등에 비해 정확한 특징을 계산상의 문제 없이 추출할 수 있는 기법이다. 그러나, 추출되는 특징은 입력의 선형조합으로 제한되어 자료에 따라 적절한 특징을 추출하기 어려운 경우가 발생한다. 이를 해결하기 위하여 클래스가 부가된 주성분분석에 커널 트릭을 적용하여 비선형 특징을 추출할 수 있는 새로운 부분공간 기법으로 확장하고, 실험을 통하여 성능을 평가하였다.

• 한국음향학회지
• /
• 제42권3호
• /
• pp.262-269
• /
• 2023

본 논문에서는 선형 예측 분석을 기반으로 한 딱총새우 잡음 검출을 위한 특징을 제안한다. 딱총새우는 천해에 서식하는 종으로, 높은 진폭의 신호를 생성하고 빈번하게 발생하기 때문에 수중 잡음의 주된 원인 중 하나이다. 제안된 특징은 딱총새우 잡음이 갑작스럽게 발생하고 빠르게 소멸하는 특징을 활용하기 위해 선형 예측 분석을 이용하여 정확한 잡음 구간을 검출하고 딱총새우 잡음의 영향을 줄인다. 선형 예측 분석으로 예측한 값과 실제 측정값 사이의 오차가 크기 때문에 이를 통해 효과적으로 딱총새우 구간 검출이 가능해진다. 추가적으로 제안된 특징에 일정 오경보 확률 탐지기를 결합하여 잡음 구간 검출 성능을 추가적으로 개선한다. 제안한 방법을 딱총새우 잡음 구간 검출 최신 방법으로 알려진 다층 웨이블릿 패킷 분해와 비교한 결과, 제안한 방법이 수신자 조작 특성 곡선과 곡선 아래의 면적 측면에서 성능이 평균적으로 0.12만큼 우수하였고 계산량 측면에서도 계산 복잡도가 더 낮았다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3194-3216
• /
• 2018

Slow Feature Discriminant Analysis (SFDA) is a supervised feature extraction method inspired by biological mechanism. In this paper, a novel method called Two Dimensional Slow Feature Discriminant Analysis via $L_{2,1}$ norm minimization ($2DSFDA-L_{2,1}$) is proposed. $2DSFDA-L_{2,1}$ integrates $L_{2,1}$ norm regularization and 2D statically uncorrelated constraint to extract discriminant feature. First, $L_{2,1}$ norm regularization can promote the projection matrix row-sparsity, which makes the feature selection and subspace learning simultaneously. Second, uncorrelated features of minimum redundancy are effective for classification. We define 2D statistically uncorrelated model that each row (or column) are independent. Third, we provide a feasible solution by transforming the proposed $L_{2,1}$ nonlinear model into a linear regression type. Additionally, $2DSFDA-L_{2,1}$ is extended to a bilateral projection version called $BSFDA-L_{2,1}$. The advantage of $BSFDA-L_{2,1}$ is that an image can be represented with much less coefficients. Experimental results on three face databases demonstrate that the proposed $2DSFDA-L_{2,1}/BSFDA-L_{2,1}$ can obtain competitive performance.

• 대한지리학회지
• /
• 제40권4호
• /
• pp.441-453
• /
• 2005

본 연구의 목적은 지형자료에 대한 계층화 알고리즘을 개발하여 하계망을 일반화하고자 하였다. 하계망은 계층적인 구조를 갖기 때문에 일반화를 위해 선형사상들에 대한 지형자료의 계층화가 요구된다. 하계망 일반화의 절차는 하계망의 계층화, 차수별 선택과 제거, 그리고 알고리즘 적용으로 진행하였다. 계층화는 하계망의 고도에 따른 방향 결정, Stroke Segment 서열화. Strahler 차수화로 진행하였으며, 선형사상의 선택과 제거는 지리자료의 질의를 통해 차수와 선의 길이를 기준으로 처리하였다 개선된 Simoo 알고리즘은 선형사상의 곡률을 낮추고 완만화에 효과적이었다 연구결과는 공간적으로 다양한 계층구조를 갖는 사상들에 대한 일반화를 개선할 수 있을 것으로 기대된다.

• 전자공학회논문지
• /
• 제54권1호
• /
• pp.111-120
• /
• 2017

본 논문에서는 해저 퇴적물 분류를 위한 특징 추출 기법을 제안하고 검증한다. 기존 연구에서는 주파수의 영향이 없는 반사계수를 이용하여 퇴적물을 분류해 왔다. 그러나 해저 퇴적물의 음향 감쇠계수는 주파수의 함수이며 퇴적 성분에 따라 서로 다른 특성을 나타낸다. 따라서 주파수에 따른 감쇠계수 변화량을 이용하여 특징벡터를 생성하였다. 감쇠계수 변화량은 Chirp 신호에 의해 생성된 두 번째 층 반사신호를 이용하여 추정한다. Chirp 신호의 다중대역 특징이 다차원 벡터를 형성하기 때문에 기존의 방법에 비해 우수한 특성을 갖는다. 반사계수에 의한 분류 성능과 비교하기 위해 선형 판별 분석법 (LDA, Linear Discriminant Analysis)를 이용하여 차원을 축소하였다. Biot 모델을 이용하여 모의실험 환경을 구축하고 Fisher score와 MLD(Maximum Likelihood Decision)를 기반의 분류 정확도를 이용해 제안된 특징을 평가하였다. 그 결과, 제안된 특징은 반사계수에 비해 높은 변별력을 보이며, 측정 및 깊이 추정오차에도 강인한 특성을 보였다.