• 제목/요약/키워드: Line-Clustering

검색결과 207건 처리시간 0.03초

공구파단 검출을 위한 ART2 신경회로망 (ART1 Neural Network for the Detection of Tool Breakage)

  • 고태조;김희술;조동우
    • 한국정밀공학회:학술대회논문집
    • /
    • 한국정밀공학회 1995년도 춘계학술대회 논문집
    • /
    • pp.451-456
    • /
    • 1995
  • This study investigates the feasibility of the real time detection of tool breadage in face milling operation. The proposed methodology using an ART2 neural network overcomes a cumbersome task in terms of the learning or determining a threshold value. The features taken in the researchare the AR parameters modelled from a RLS, and those are proven to be good features for tool breakage from experiments. From the results of the off line application, we can conclude that an ART2 neural network can be well applied to the clustering of tool states in real time regardless of the unsupervised learning.

  • PDF

Cosmic Web traced by ELGs and LRGs from the Multidark Simulation

  • 김도일
    • 천문학회보
    • /
    • 제41권1호
    • /
    • pp.72.1-72.1
    • /
    • 2016
  • Current and planned large-volume surveys such as the Sloan Digital Sky Survey extended Baryon Oscillation Spectroscopic Survey (SDSS IV-eBOSS) or the Dark Energy Spectroscopic Instrument (DESI) will use Luminous Red Galaxies (LRGs) and Emission Line Galaxies (ELGs) to map the cosmic web up to z~1.7, and will allow one to accurately constrain cosmological models and obtain crucial information on the nature of dark energy and the expansion history of the Universe in novel epochs - particularly by measuring the Baryon Acoustic Oscillation (BAO) feature with improved accuracy. To this end, we present here a study of the spatial distribution and clustering of a sample of LRGs and ELGs obtained from a sub-volume of the MultiDark simulation complemented by different semi-analytic prescriptions, and investigate how these two different populations trace the cosmic web at different redshift intervals - along with their synergy. This is the first step towards the interpretation of upcoming ELG and LRG data.

  • PDF

영상변형을 이용한 선행차량과의 충돌시간 및 법선벡터의 예측 (Estimation of time to contact and surface orientation of a leading vehicle using image deformation)

  • 이준웅;박성기;노경식;권인소
    • 제어로봇시스템학회논문지
    • /
    • 제4권3호
    • /
    • pp.334-341
    • /
    • 1998
  • This paper proposes an algorithm to obtain the time-to-contact between an observer and a target and surface orientation of the target. These two physical elements are computed from the image deformation of a known shape, which is extracted by supervised classification of detected line segments based on MAP and Mahalanobis distance. The proposed algorithm was applied to the natural outdoor traffic scene and would contribute to the development for a collision avoidance system.

  • PDF

경사조사(傾斜照射) 강판튜브 방사선영상 영역특성 분석 (Discrimination for Line-clustering Segmental Approach to Steel-tube X-ray Image)

  • 황중원;황재호
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2007년도 하계종합학술대회 논문집
    • /
    • pp.399-400
    • /
    • 2007
  • This paper proposes an regional analytic approach in image data space for radiographic image. Image is segmented into four regions, such as background, thickness, weld area and tube area, due to directional properties. Each region has its own gray level distribution, contrast range and noise property, originated from X-ray project mechanism and electric control system itself. Projection incorrectness and noise influence included on imaging quality is analyzed functionally and statistically. The experimental results shows not only segmental effects, but also visual edge evaluation.

  • PDF

한전 전력계통의 저주파 진동현상 요인분석;양수발전기 기동시 (Analysis of the Factors Affecting Low-Frequency Oscillations in KEPCO Power System` With Pumped-Storage Plant)

  • Kil Yeong Song;Sae Hyuk Kwon;Kyu Min Ro;Seok Ha Song
    • 대한전기학회논문지
    • /
    • 제41권8호
    • /
    • pp.841-849
    • /
    • 1992
  • In power system operation, the stability of synchronous machine has been recognized one of the most important things. AESOPS program developed by EPRI in U.S.A. is a frequency domain analysis program in power system stability and it computes the electro-mechanical oscillation mode. This paper presents how to analyze the power system small signal stability problem efficiently by uusing the AESOPS program and analyze the various factors affecting the damping characteristics of these oscillations in KEPCO power system of 1986 with pumped-storage plant. To reduce the computing time and efforts, selecting the poorly-damped oscillation mode and clustering technique have been used. The characteristics of load, the amount of power flow on the transmission line and the gain of exciter have a significant effects on the damping of the system while the governing system has only a minor one. With the Power System Stabilizers, the stability of the power system has been improved.

  • PDF

클러스터링 알고리즘을 이용한 SMT 검사기의 검사시간 단축 방법 (The Reduction Methods of Inspection Time for SMT Inspection Machines Using Clustering Algorithms)

  • 김화중;박태형
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2003년도 하계학술대회 논문집 D
    • /
    • pp.2453-2455
    • /
    • 2003
  • We propose a path planning method to reduce the inspection time of AOI (automatic optical inspection) machines in SMT (surface mount technology) in-line system. Inspection windows of board should be clustered to consider the FOV (field-of-view) of camera. The number of clusters is desirable to be minimized in order to reduce the overall inspection time. We newly propose a genetic algorithm to minimize the number of clusters for a given board. Comparative simulation results are presented to verify the usefulness of proposed algorithm.

  • PDF

온라인 텍스트문서의 계층적 트리 기반 주제탐색 기법 (A Novel Technique of Topic Detection for On-line Text Documents: A Topic Tree-based Approach)

  • 현만;김한준
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2012년도 추계학술발표대회
    • /
    • pp.396-399
    • /
    • 2012
  • Topic detection is a problem of discovering the topics of online publishing documents. For topic detection, it is important to extract correct topic words and to show the topical words easily to understand. We consider a topic tree-based approach to more effectively and more briefly show the result of topic detection for online text documents. In this paper, to achieve the topic tree-based topic detection, we propose a new term weighting method, called CTF-CDF-IDF, which is simple yet effective. Moreover, we have modified a conventional clustering method, which we call incremental k-medoids algorithm. Our experimental results with Reuters-21578 and Google news collections show that the proposed method is very useful for topic detection.

SLA Genetic Polymorphism and Large Scale Gene Expression Profiling of Cloned SNU Miniature Pigs Derived from Same Cell Line

  • Yeom, Su-Cheong;Koo, Ok Jae;Park, Chung-Gyu;Lee, Byeong-Chun;Lee, Wang-Jae
    • Reproductive and Developmental Biology
    • /
    • 제37권1호
    • /
    • pp.1-8
    • /
    • 2013
  • In order to investigate genetic stability and gene expression profile after cloning procedure, two groups of cloned pigs were used for swine leukocyte antigen (SLA) gene nucleotide alteration and microarray analyses. Each group was consist of cloned pigs derived from same cell line (n=3 and 4, respectively). Six SLA loci were analyzed for cDNA sequences and protein translations. In total, 16 SLA alleles were identified and there were no evidence of SLA nucleotide alteration. All SLA sequences and protein translations were identical among the each pig in the same group. On the other hand, microarray assay was performed for profiling gene expression of the cloned pigs. In total, 43,603 genes were analyzed and 2,150~4,300 reliably hybridized spots on the each chip were selected for further analysis. Even though the cloned pigs in the same group had identical genetic background, 18.6~47.3% of analyzed genes were differentially expressed in between each cloned pigs. Furthermore, on gene clustering analysis, some cloned pigs showed abnormal physiological phenotypes such as inflammation, cancer or cardiomyopathy. We assumed that individual environmental adaption, sociality and rank in the pen might have induced these different phenotypes. In conclusion, the results of the present study indicate that SLA locus genes appear to be stable following SCNT. However, gene expressions and phenotypes between cloned pigs derived from the same cell line were not identical even under the same rearing conditions.

대극속 Anthacantha절(대극과)과 근연분류군의 종자형태 (Seed Morphology of Euphorbia Section Anthacantha (Euphorbiaceae) and Related Taxa)

  • 나희정;박기룡
    • Applied Microscopy
    • /
    • 제40권4호
    • /
    • pp.219-228
    • /
    • 2010
  • 대극과 대극속 Anthacantha절의 한계와 근연 분류군과의 유연 관계를 규명하기 위해 Anthacantha절에 속한 8종과 근연 분류군을 포함하여 총 16종의 종자를 광학 및 주사전자현미경으로 연구하였다. 측정된 형질 중 6가지 정성형질만을 이용한 수리분석을 바탕으로 3가지 유형으로 구분되었다. Type I (sect. Anthacan 능선 주변에는 결절이 없이 표면이 매끈한 특징을 가진다. Type II (sect. Medusae+sect. Treisia-1군)는 사각형태로 배능선 주변에 돌출된 세포가 발달되어 있으며 표면에 결절이 있는 특징을 가진다. Type III (sect. Treisia-2군)는 전체적인 형태는 난형이며 배능선 주변에 돌출된 세포가 발달되어 Type II에 가까우나 세포표면에 종피세포가 여러 개 모여 솟아올라있어 Type I, II 에는 없는 특징을 보여준다. 본 연구를 통해 Anthacantha절에 속한 종과 Meleuphorbia절에 속한 종은 종자형태의 형질이 매우 유사하여 유연관계가 깊은 것으로 생각되며, 기존의 분자적, 화분분류학적 연구의 결과와 잘 일치하는 양상을 보였다. 또한 Treisia절과 Medusae절에 속하는 분류군은 종자 형태적으로 Anthacantha절의 종들과 차이를 보이고 있어 이들과는 상대적으로 유연관계가 먼 것으로 추정되며 이와 같은 결과는 최근에 수행된 분자적 연구의 결과와는 상반된 양상으로 나타났다.

한글필기체의 구조적 특징을 이용한 효율적 기울기 보정 (An Efficient Slant Correction for Handwritten Hangul Strings using Structural Properties)

  • 유대근;김경환
    • 한국정보과학회논문지:소프트웨어및응용
    • /
    • 제30권1_2호
    • /
    • pp.93-102
    • /
    • 2003
  • 본 논문에서는 한글의 구조적 특징이 반영된 획들의 통계적인 분포에 근거한 필기 문자열의 기울기 보정 방법을 제안한다. 기존의 기울기 보정 방법들은 대부분 영문위주의 보정 방법으로, 영문과 달리 2차원적 구조를 갖는 한글에 적용하는데는 많은 문제가 있다. 일반적인 보정 방법을 적용할 경우 한글에 내재하는 강한 대각선획의 영향으로 인한 역보정의 문제가 가장 많이 나타나며. 기울어진 문자열을 제대로 보정하지 못하는 경우도 빈번하다. 제안하는 방법에서는 추출된 획들의 기울기 분포를 K-평균 군집법을 적용하여 수직획과 대각선획의 두 개의 군집으로 분류하고, 가우시안 분포로의 모델링을 통해 대각선획을 제외하고 수직획만을 이용하여 기울기 보정을 수행하였다. 임의의 필기자에 의해 필기된 우편봉투 주소 문자열 1,300개에 대해 제안하는 방법과 기존의 방법들을 적용하여 실험한 결과 제안하는 방법이 기존방법들에 비해 역보정률을 크게 낮추고, 기울어진 문자열에 대해 완벽한 보정 성능을 보여 그 우수성이 입증되었다.