• 한국정보통신학회논문지
• /
• 제13권2호
• /
• pp.407-412
• /
• 2009

최근 용접공정은 무인화 및 자동화 시스템의 구축이 급속하게 발전하고 있으며 정확한 용접현상의 해석을 위하여 여러 가지 신호처리 알고리즘을 적용하고 있다. 본 논문에서는 아크용접의 모니터링시스템 구성에 있어서 용접품질을 실시간으로 판단할 수 있는 효율적인 신경회로망을 제시하고, 학습 데이터의 선정을 위한 전처리 과정을 제시하며, 학습된 신경회로망을 이용하여 실제 용접이 이루어지는 파형에 대한 평가를 보다 정밀하고 정확하게 평가할 수 있는 방법을 제시한다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2001년도 추계학술대회 논문집 Vol.14 No.1
• /
• pp.270-273
• /
• 2001

Electrical tree is studied widely by manufacture state of insulating material fare and blazing fire diagnosis system of use in phenomenon of part discharge that happen for main cause of dielectric breakdown of equipment for electric power. Use process that draw tree pattern here measuring above zero to study special quality of this electricity tree, real-time processing by image processing is proposed because reproduction of tree blazing fire process drops and pattern of tree is difficult correct quantification of tree growth by existent visual observation by involution. This research presents general process that need in image processing of tree blazing fire, and that remove various noises that happen in above zero by measuring electrical tree dividing background and complete view in measured above zero taking advantage of specially proposed complete view object abstraction techniques effectively and quantification of tree becomes easy naturally, can apply to dielectric breakdown estimate because can chase growth process of tree.

• 한국통신학회논문지
• /
• 제21권3호
• /
• pp.576-586
• /
• 1996

이진 형태론적 골격(MS: morphology skeleton) 영상점들은 이들의 정보만으로 원영상을 그대로 복원시킬 수 있는 특징이 있기 때문에, 이 골격 정보를 패턴 인식 및 영상통신에 적용할 수 있다. 한편 기존의 MS는 처리시간이 많이 걸릴 뿐만 아니라 골격점들은 중복도가 높다. 이러한 결점을 해결하기 위하여 본 논문에서는 중복도가 영(zero)인 골격영상을 얻는 새로운 직접 총체적 최소 골격화 방법을 제안하고 이를 DGMS(direct globally minimal sketeton)로 정의한다. 이 방법으로 $256{\times}256$ 이진영상 GIRL에 대한 실험 결과 기존의 총체적 최소 골격화(GMS: globally minimal skeleton)보다 처리 시간이 감축되고, 골격점의 수에서 1.5~6.5% 정도 감소하는 결과를 얻었다.

• 산업기술연구
• /
• 제14권
• /
• pp.127-140
• /
• 1994

This study is concerned with the accuracy and the patterns when different methods was used in interpolation task. Although 3 methods employed the same modality for input (visual) and for output (manual responding), they differed in central processing, which method 1 is relatively more tendency of verbal processing, method 2 is realtively more tendency of spatial processing and method 3 needed a number of switching code (verbal/spatial) performing task. Split-plot design was adopted, which whole plot consisted of methods (3), orientations (horizon, vertical), base-line sizes (300, 500, 700 pixels) and split plot consisted of target locations (1-99). The results showed the anchor effect and the range effect. Method 2, method 3 and method 1 that order was better accuracy. ANOVA showed that the accuracy was significantly influenced by the method, the location of target, and its interactions ($method{\times}location$, $size{\times}location$). Analysis of error data, response time and frequency of under, just, over estimate indicated that a systematic error pattern was made in task and methods changed not only the performance but also the pattern. The results provided support for the importance of the multiple resources theory in accounting for S-C-R compatibility and task performance. They are discussed in terms of multiple resources theory and guidelines for system design is suggested by the S-C-R compatibility.

• 한국레이저가공학회지
• /
• 제1권1호
• /
• pp.39-44
• /
• 1998

Laser ablation system for microscopic defect in thin film pattern was developed in this study. For the varification of this study, several laser ablation tests were accomplished. The ablated shape of thin film and the surface of base glass were analyzed by use of microscopic tools and EPMA. After some tests of thin film, the specification of laser and optical unit(max. laser energy is 25mJ, wavelength is 532nm, Q-switched Nd-YAG laser, frequency is 20Hz, Auto-focus unit is LD type.)

• 한국생물환경조절학회:학술대회논문집
• /
• 한국생물환경조절학회 1999년도 정기총회 및 학술논문발표요지
• /
• pp.24-29
• /
• 1999

포도 수확기를 개발하기 위해서는 포도 형상과 위치를 정확하게 파악하는 것이 필요하다. 신경회로망(Neural network)의 연상메모리(Associative memory)를 이용하여 포도 형상 정보를 인식하고자 한다. 신경회로망을 이용한 연상메모리는 학습 패턴(Learning pattern)을 학습한 후에 입력 패턴(Input pattern)으로부터 출력패턴을 얻는다. (중략)

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2008년도 춘계학술대회 논문집
• /
• pp.629-630
• /
• 2008

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.699-701
• /
• 1987

This paper deals With the EMG signal processing to apply the EMG signal to the Prosthetic arm. The EMG signals are generated by the voluntary contractions of the subject's musculature and is coded into binary words by the pulse width modulation. Command strings or sentences are constructed by concatenating several words, and are syntactically described by a context free grammar in Chomsky normal form and is tried to classify the movement pattern by the CYK algorithm.

• 선박안전
• /
• 통권23호
• /
• pp.65-77
• /
• 2007

This study is about the survey technique and the development of measuring method about a wooden pattern of the small vessel made by CNC Machine. we will propose a survey method about processing grade, objectivity of survey, an external shape and a surface defect survey method, Furthermore, CMM(Coordinate Measuring Machine) and OMM(On Machine Measurement).

• 전자공학회논문지B
• /
• 제28B권12호
• /
• pp.59-67
• /
• 1991

In this paper, we aimed to develop associative pattern recognizer based on neural network for aircraft identification. For obtaining invariant feature space description of an object regardless of its scale change and rotation, Log-polar sampling technique recently developed partly due to its similarity to the human visual system was introduced with Fourier transform post-processing. In addition to the recognition results, image recall was associatively performed and also used for the visualization of the recognition reliability. The multilayer perceptron model was learned by backpropagation algorithm.