• Journal of Electrical Engineering and Technology
• /
• 제13권4호
• /
• pp.1549-1557
• /
• 2018

Optimizing the design of large-scale electric machines based on nonlinear finite element analysis (FEA) requires longer computation time than other applications of FEA, mainly due to the huge size of the machines. This paper addresses a new region decision method (RDM) with mesh adaptive direct search (MADS) for the optimal design of wind generators in order to reduce the computation time. The validity of the proposed algorithm is evaluated using Rastrigin and Goldstein-Price benchmark function. Moreover, the algorithm is employed for the optimal design of a 5.6MW interior permanent magnet synchronous generator to minimize the torque ripple. Additionally, mechanical stress analysis as well as electromagnetic field analysis have been implemented to prevent breakdown caused by large centrifugal forces of the modified design.

• 한국환경과학회지
• /
• 제15권9호
• /
• pp.871-880
• /
• 2006

Water management treatment of coastal region has been an important problem in Jeju city since the distributions of pipeline of the pumping system made a bad view in coastal region. To solve the problem, we observed the pipelines that are on the surface around the coastal region from Tapdong to Doduhang. From the observations, we found that Todong and Dodu areas were not unsightliness because the all pipelines were located in underground. However, the other areas, such area Yongdam, Handugi, Yongdam fishing village, had a serious problem for the coastal landscape view. To solve the problem, at we estimated coastal land color characteristics of Jeju city based on the observation of the pipelines. The estimated color panel shows that the green, blue and grey colors are a dominant factors of the Jeju coastal region. Based on the color panel, we proposed two methods, that is, one is a short time treatment, the other is a long time one. The short is based on the colour treatment, which is pipeline colour changing into surround natural one. The long time is the construction plan design method. Although the later method was very useful in Jeju island. However, it takes a lot of time and money. Therefore, in the situation, the short time is the better than the long time one.

• Journal of information and communication convergence engineering
• /
• 제15권4호
• /
• pp.250-255
• /
• 2017

In this paper, we propose a method of detecting the region for measuring intima-media thickness (IMT). The existing methods for IMT measurement are automatic, but the region used for measuring IMT is not detected automatically but often set by the user. Therefore, research on detecting the intima-media region is needed for fully automated IMT measurement. The proposed method uses a morphological feature of the carotid artery visible as two long high-brightness horizontal lines at the upper and lower parts. It uses Gaussian blurring, ends-in search stretching, color quantization using a color-importance-based self-organizing map, and morphological operations to emphasize and to detect the morphological feature. The experimental results for evaluating the performance of the proposed method showed a 97.25% (106/109) success rate. Therefore, the proposed method can be used to develop a fully automated IMT measurement system.

• 음성과학
• /
• 제12권2호
• /
• pp.171-182
• /
• 2005

An efficient GMM (Gaussian mixture modeling) method based on LPCA (local principal component analysis) with VQ (vector quantization) for speaker identification is proposed. To reduce the dimension and correlation of the feature vector, this paper proposes a speaker identification method based on principal component analysis. The proposed method firstly partitions the data space into several disjoint regions by VQ, and then performs PCA in each region. Finally, the GMM for the speaker is obtained from the transformed feature vectors in each region. Compared to the conventional GMM method with diagonal covariance matrix, the proposed method requires less storage and complexity while maintaining the same performance requires less storage and shows faster results.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.862-864
• /
• 2003

Thresholding is a popular image segmentation method that converts a gray-level image into a binary image. The selection of optimum threshold has remained a challenge over decades. Many image segmentation techniques are developed using information about image in other space rather than the image space itself. Most of the technique based on histogram analysis information-theoretic approaches. In this paper, the criterion function for finding optimal threshold is developed using an intensity-based classuncertainty (a histogram-based property of an image) and region-homogeneity (an image morphology-based property). The theory of the optimum thresholding method is based on postulates that objects manifest themselves with fuzzy boundaries in any digital image acquired by an imaging device. The performance of the proposed method is illustrated on experimental data obtained by W-band millimeter-wave radiometer image under different noise level.

• 한국산업정보학회논문지
• /
• 제17권6호
• /
• pp.59-72
• /
• 2012

단백질은 서열의 disorder 구역이 생물학적 반응을 일으켜 order로 변하는 과정에서 그 기능을 하게 되므로 서열 데이터에서 disorder 구역과 order 구역을 분리하는 것은 단백질의 3차 구조 및 특성을 예측하는데 반드시 필요하다. 따라서 이 논문에서는 효율적인 disorder와 order 구역 분류를 위해서 단백질의 특정 특징에 치우치지 않는 분류 결과를 얻으면서, 분류 속도를 향상 시킬 수 있도록 서열 데이터를 이용한 분류/예측 기법을 제안한다. 출현패턴 기반의 EPs-TFP 기법은 중복 출현패턴이 제거된 필수 출현패턴만을 이용하는 분류/예측 기법이다. 이 분류 기법은 disorder 구역의 서열 출현패턴들을 발견하며, 이러한 서열 출현패턴은 disorder 구역에서는 빈발하지만 order 구역에서는 상대적으로 빈발하지 않는 패턴들이다. 또한 제안 알고리즘의 성능 향상을 위해서 기존의 P-tree, T-tree 개념의 TFP 기법을 확장하여 분류/예측 기법으로 적용하였다. EPs-TFP 기법의 성능평가를 위해서 Disprot 4.9와 CASP 7 데이터를 활용하였고, disorder/order 구역을 분류한 결과, 민감도 73.6, 특이도 69.5, 정확도 74.2를 보였다.

• 대한조선학회논문집
• /
• 제52권1호
• /
• pp.70-76
• /
• 2015

The ship hull is accomplished by assembling various curved surfaces. There are numerous existing methods for ship hull processing, which need certain appropriate processing methods to enable it to be more efficient. The curved hull plates can be divided into convex region and saddle region. It is common to use line heating method to form a saddle region, when it comes to a convex region, it will be triangle heating method to be utilized. A precise analysis for curvature domain is required for the application of proper processing method. There exist various problems on existing calculation methods of curvature domain. Therefore, a more powerful method is demanded to it more accurately. In this study, a method called Dual Contouring is applied to extract curved surfaces, which is able to improve accuracy of extracted area. Based on all above, a best-suited heat processing method should be selected.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권9호
• /
• pp.4386-4404
• /
• 2016

Most existing salient object detection algorithms commonly employed segmentation techniques to eliminate background noise and reduce computation by treating each segment as a processing unit. However, individual small segments provide little information about global contents. Such schemes have limited capability on modeling global perceptual phenomena. In this paper, a novel salient object detection algorithm is proposed based on region merging. An adaptive-based merging scheme is developed to reassemble regions based on their color dissimilarities. The merging strategy can be described as that a region R is merged with its adjacent region Q if Q has the lowest dissimilarity with Q among all Q's adjacent regions. To guide the merging process, superpixels that located at the boundary of the image are treated as the seeds. However, it is possible for a boundary in the input image to be occupied by the foreground object. To avoid this case, we optimize the boundary influences by locating and eliminating erroneous boundaries before the region merging. We show that even though three simple region saliency measurements are adopted for each region, encouraging performance can be obtained. Experiments on four benchmark datasets including MSRA-B, SOD, SED and iCoSeg show the proposed method results in uniform object enhancement and achieve state-of-the-art performance by comparing with nine existing methods.

• 방송공학회논문지
• /
• 제18권3호
• /
• pp.393-400
• /
• 2013

손 모양 인식은 자연스러운 인간-컴퓨터 상호작용을 위한 기반 기술이다. 본 논문에서는 Kinect 기반 손 모양 인식을 위해 효과적으로 손 영역을 검출하기 위한 방법에 대해 논의한다. Kinect는 컬러 영상과 적외선 영상(혹은 깊이 영상)을 동시에 획득할 수 있는 카메라이기 때문에, 손 영역을 검출하는 과정에서 컬러 정보와 깊이 정보를 활용할 수 있다. 즉, 손 영역은 스킨 컬러를 가지는 영역으로 검출될 수도 있으며, 일정한 깊이 값을 가지는 영역으로 검출될 수도 있다. 그러므로, 이러한 방법들의 성능을 분석하여, 손 영역의 실루엣이 깔끔하게 도출될 수 있도록 적절히 결합하는 방법이 마련되어야 한다. 이는 손 모양 인식률을 크게 좌우하기 때문이다. 최종적으로 일반적인 환경에서 손 영역 검출 방법의 차이에 따른 손 모양 인식률을 비교함으로써, 성능이 우수한 손 영역 검출 방법을 제안한다.

• 방송공학회논문지
• /
• 제6권1호
• /
• pp.108-118
• /
• 2001

본 논문에서는 압축 영상에서 블록현상을 제거하기 위한 여러 후처리 알고리듬을 영상의 영역별로 비교하였다. 또한 이를 통하여 시각 특성에 맞는 주관적 평가 뿐만 아니라 객관적인 PSNH도 향상시킬 수 있는 블록현상 제거방법을 제시하였다. 본 논문에서는 사람의 시각적 특성에 의하여 블록화 현상은 고주파 영역보다 저주파 영역에서 눈에 잘 띄인다는 사실에 근거하여 우선 최근의 여러 블록현상 제거 알고리듬의 저주파 영역, 고주파 영역에서의 영상 개선도를 비교하였다. 이 과정에서 블록현 상이 발생한 영상에서 고주파/저주파 영역을 간단하게 분류하는 방법을 제시하였고, 각 영역에 서로 다른 알고리듬을 적용하는 방법을 제안하였다. 실험 결과. 제시된 분류에 따른 저주파 영역에는 적응 LPF 방법의 성능이 주관, 객관적인 면 모두 가장 좋 은 것으로 나타났다 따라서 기존의 알고리듬들을 고주파 영역에 적용하고 저주파영역에는 적응 LPF 방법을 적용함으로써 모든 블록현상 제거 알고리듬들의 주관적 및 객관적 성능이 개선될 수 있음을 보였다 또한 고주파 영역에서 객관적인 성능은 DCT기반 POCS 알고리듬이 가장 좋았으며, 이 알고리듬과 적응 LPF를 혼합하여 사용하면 가장 좋은 객관적 성능을 얻을 수 있었다.