• 정보저장시스템학회논문집
• /
• 제6권2호
• /
• pp.74-78
• /
• 2010

In this paper, 2-axis driving mechanism, which uses voice coil motor (VCM), is proposed to measure the friction force. The proposed VCM actuator consists of two parts; structural part and magnetic circuit part. Structural part is simplified to perform the friction experiments. Magnetic circuit part is composed of two parts. The experiments are accomplished by changing the mass of moving part. Through the experiments, optimal dimension is selected. Finally, the experimental results are verified and the optimal case is applied to the 2-axis driving mechanism, optical image stabilization actuator.

• 정보처리학회논문지D
• /
• 제19D권2호
• /
• pp.147-150
• /
• 2012

클래스들 간의 거리를 최대화시키는 사영 방향을 구하는 감독차원감소 방법인 선형판별분석법(LDA)은 클래스 정보를 가진 데이터의 수가 매우 적을 때 성능이 급격히 저하되는 경향이 있다. 이러한 경우 상대적으로 저렴한 비용으로 얻을 수 있는 클래스 라벨 정보가 없는 데이터를 활용할 수 있는 반감독 차원 감소법이 사용될 수 있다. 그러나 통계적 차원 감소법에서 흔히 사용되는 행렬연산은 많은 양의 데이터를 사용하는데 메모리와 처리시간에서 한계가 있고, 적은 수의 라벨드 데이터(labeled data)에 비해 너무나 많은 언라벨드 데이터(unlabeled data)의 사용은 처리 시간의 증가에 비해 오히려 성능감소를 가져올 수 있다. 이러한 문제들을 극복하기 위해 앙상블 접근법을 이용한 반감독 차원 감소 방법을 제안한다. 문서분류 문제에서의 실험결과를 통해 제안한 방법의 성능을 입증한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2008년도 추계학술대회 논문집
• /
• pp.297-298
• /
• 2008

• 전기학회논문지
• /
• 제66권4호
• /
• pp.682-691
• /
• 2017

In this paper, we propose the fusion design methodology of both pedestrian detection and object tracking system realized with the aid of HOG-PCA based RBFNN pattern classifier. The proposed system includes detection and tracking parts. In the detection part, HOG features are extracted from input images for pedestrian detection. Dimension reduction is also dealt with in order to improve detection performance as well as processing speed by using PCA which is known as a typical dimension reduction method. The reduced features can be used as the input of the FCM-based RBFNNs pattern classifier to carry out the pedestrian detection. FCM-based RBFNNs pattern classifier consists of condition, conclusion, and inference parts. FCM clustering algorithm is used as the activation function of hidden layer. In the conclusion part of network, polynomial functions such as constant, linear, quadratic and modified quadratic are regarded as connection weights and their coefficients of polynomial function are estimated by LSE-based learning. In the tracking part, object tracking algorithms such as mean shift(MS) and cam shift(CS) leads to trace one of the pedestrian candidates nominated in the detection part. Finally, INRIA person database is used in order to evaluate the performance of the pedestrian detection of the proposed system while MIT pedestrian video as well as indoor and outdoor videos obtained from IC&CI laboratory in Suwon University are exploited to evaluate the performance of tracking.

• 환경생물
• /
• 제22권3호
• /
• pp.351-368
• /
• 2004

기아시와 포식시 버들치, Rhynchocypris oxycephalus(Sauvage and Dabry)에 미치는 영향을 파악하기 위하여 조직학적 및 생화학적 변화, 체절단면 계측형질 변화 그리고 계측형질 변화에 대하여 조사하였다. 기아에 따른 버들치의 생화학적, 조직학적 변화를 파악하기 위해, 간의 간중량지수, 단백질함량, RNA량 및 DNA량 조사와 더불어 간세포 및 중장 상피세포의 조직학적 조사를 실시한 결과, 기아군은 포식군에 비해 간의 단백질함량, RNA량 및 DNA량에서 높은 값을 보였지만, 먹이 공급 중단은 버들치의 간중량지수, 간세포 핵 크기 및 중장 상피세포 핵 높이에 있어서 감소를 나타내었다. 본 실험에서 조사된 RNA-DNA비는 버들치의 영양상태 파악 지수로 유용하였으며 또한, 버들치 표본 시기에서의 높은 성장 단계인지 혹은 낮은 성장 단계인지의 성장 활성 파악을 가능케 하였다. 본 연구 결과의 자료를 구체적으로 해석 하였으며, 아울러 다수의 생물학적 중요 연관 사항들을 고찰하였다. 버들치 기아시의 영양상태 평가를 위하여 비만도, 내장괴지수, Dressing 비를 비롯한 체횡단 절단면에서의 형태적변화를 조사하였다. 9주간의 기아시 비만도, 내장괴지수 및 대부분의 체횡단 절단면 계측형질들에서의 감소를 보였다(P<0.05). 본 연구 결과, 실험에 적용된 영양성 Parameter는 본 종의 영양상태 파악에 유용한 지표임을 시사한다. 연구 결과를 자세히 해석하여, 버들치에서의 주요 체 절단 형질의 산업성을 논의하였다. 버들치에서의 75일간 기아가 Classical dimension과 Truss dimension에 미치는 영향을 파악하였다. Truss dimension인 경우 포식시와 기아시 복강을 비롯한 머리 부위와 몸통부위가 유의하게 증가하였다(P< 0.05). Truss dimension의 꼬리부위 특히, 몸통의 뒷부분이 포식과 기아시 일반적으로 감소하였다. Classical dimension인 경우 포식시 꼬리부위가 감소한 반면, 기아시 몸통부위와 꼬리부위에서의 체고 관련 형질에 연관시 머리부위에서의 형질들이 유의하게 감소하였다. 본 연구 결과 Truss dimension은 Classical dimension을 보완하여 어체의 수직방향 연관 형질 파악도 가능케 하였다. Truss dimension과 Classical dimension인 경우 포식시와 기아시 머리 아랫부위는 거의 영향이 없어, 본 형질은 버들치속 어류의 분류학적측면에서 유용하게 사용될 수 있을 것이다. 버들치에서 체고와 연관된 몸통부위 형질들은 상이한 서식지에 기인된, 다양한 먹이공급 차이의 파악에 유용하리라 사료된다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집A
• /
• pp.609-615
• /
• 2001

This study proposes analysis and evaluation method of time series ultrasonic signal using attractor analysis for fusion joint part of polyethylene piping. Quantitatively characteristics of fusion joint part is analysed features extracted from time series. Trajectory changes in the attractor indicated a substantial difference in fractal characteristics. These differences in characteristics of fusion joint part enables the evaluation of unique characteristics of fusion joint part. In quantitative fractal feature extraction, feature values of 4.291 in the case of debonding and 3.694 in the case of bonding were proposed on the basis of fractal dimensions. In quantitative quadrant feature extraction, 1,306 point in the case of bonding(one quadrant) and 1,209 point(one quadrant) in the case of debonding were proposed on the basis of fractal dimensions. Proposed attractor feature extraction can be used for integrity evaluation of polyethylene piping material which is in case of bonding or debonding.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.950-953
• /
• 2002

Trepan prevents wear of an inside part of a bearing when the initial shaft rotates. It continuously contacts with the eccentric part of the shaft in rotation and is loaded repeatedly. Therefore, even if an early crack of a trepan part is small, a crack progresses by a repeated load. If a crack progresses, very small chips come out. This is pill in the rotor and prevents rotation of the compressor. There can be leaks in a microgroove and extreme wear can occur due to lack of oil on the surface contact pan. Therefore, this study was carried out to compare and investigate trepan strength and deflection characteristics between trepan locations and dimension changes using a finite element method and search a motor bearing for a model with bigger stiffness of a trepan part and the same deflection. And then. five different types of the oil groove model were chosen to prevent small crack and considered also machining ability and the analysis was carried out on oil feeding flow.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.106-110
• /
• 2002

4S-Van is being developed in order to provide the spatial data rapidly and accurately. 4S-Van technique is a system for spatial data construction that is heart of 4S technique. Architecture of 4S-Van system consists of hardware integration part and post-processing part. Hardware part has GPS, INS, color CCD, camera, B/W CCD camera, infrared rays camera, and laser. Software part has GPS/INS integration algorithm, coordinate conversion, lens correction, camera orientation correction, and three dimension position production. In this paper, we suggest that adequate 4S-Van design is needed according to application environment from various test results.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2575-2577
• /
• 2000

We experimented on AGV driving test with color CCD camera which is setup on it. This paper can be divided into two parts. One is image processing part to measure the condition of the guideline and AGV. The other is part that obtains the reference steering angle through using the image processing parts. First, 2 dimension image information derived from vision sensor is interpreted to the 3 dimension information by the angle and position of the CCD camera. Through these processes, AGV knows the driving conditions of AGV. After then using of those information, AGV calculates the reference steering angle changed by the speed of AGV. In the case of low speed, it focuses on the left/right error values of the guide line. As increasing of the speed of AGV, it focuses on the slop of guide line. Lastly, we are to model the above descriptions as the type of PID controller and regulate the coefficient value of it the speed of AGV.

• 한국안전학회지
• /
• 제26권5호
• /
• pp.17-22
• /
• 2011

This study proposes feature extraction method of pattern recognition by evaluation of weld defects in weld zone of titanium. For this purpose, analysis objectives in this study are features of attractor quadrant and fractal dimension. Trajectory changes in the attractor indicated a substantial difference in fractal characteristics resulting from distance shifts such as porosity of weld zone. These differences in characteristics of weld defects enables the evaluation of unique characteristics of defects in the weld zone. In quantitative fractal feature extraction, feature values of 0.87 and 1.00 in the case of part of 0.5 skip distance and 0.72 and 0.93 in the case of part of 1.0 skip distance were proposed on the basis of fractal dimensions. Attractor quadrant point, feature values of 1.322 and 1.172 in the case of ${\phi}1{\times}3mm$ porosity and 2.264 and 307 in the case of ${\phi}3{\times}3mm$ porosity were proposed on the basis of distribution value. The Proposed feature extraction of pattern recognition in this study can be used for safety evaluation of weld zone in titanium.