• Proceedings of the KIEE Conference
• /
• 2005.05b
• /
• pp.2-3
• /
• 2005

국내 전기설비진단연구회에서 GIS 고장을 예방할 목적으로 고안한 예방진단 기술지도 초안을 바탕으로하여 결함의 종류와 진단기술의 종류, 년도별 기술 개발 목표, 기술지도 등을 제시하였다.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.370-372
• /
• 2006

본 논문에서 제안하는 방법은 영상에서 중심 객체를 추출하기 위해 에지와 색상 정보에서 추출한 특집 지도와 배경의 영향을 줄이기 위친 창조 지도(reference map)를 제안한 것이 특징이다. 특징 지도는 다른 영역과 현저하게 구분되는 영역을 검출하기 위해서 영상의 특징 값(feature)들을 이용해서 구성한 영상이라고 할 수 있다. 그리고 창조 지도는 배경의 영향을 최소화하면서, 객체가 존재할 확률이 높은 부분을 나타내는 지도이다. 제안하는 방법은 밝기 차 정보를 가지고 있는 에지와 YCbCr 컬러모델과 HSV 컬러모델의 색상 성분을 특징 값으로 사용한다. 이들 특징 값을 이용해서 특징 지도를 구성하는 방법으로 영상 내 색상 차에 의해서 나타나는 경계부분을 구하는 방법을 사용한다. 이 방법을 사용하여 에지 지도와 두 개의 색상 지도의 3가지 특징 지도를 생성한다. 다음으로, 영상 배경의 영향을 줄이기 위해 참조 지도를 구한다. 구해진 참조 지도와 특징 지도들을 이용해서 결합 지도(combination map)를 생성한다. 결함 지도로부터 다각형의 객체 후보 영역을 구하고, 객체 후보 영역에 영상분할을 적용하여 중심 객체를 추출한다. 실험에 사용된 영상들은 Corel DB를 사용하였으며, 실험결과로써 precision은 84.3%, recall은 81.3%의 성능을 보인다.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.12 no.2
• /
• pp.65-70
• /
• 2003

In this study, researchers developed the estimative algorithm for artificial defect in semiconductor packages and performed it by pattern recognition technology. For this purpose, the estimative algorithm was included that researchers made software with MATLAB. The software consists of some procedures including ultrasonic image acquisition, equalization filtering, Self-Organizing Map and Backpropagation Neural Network. Self-organizing Map and Backpropagation Neural Network are belong to methods of Neural Networks. And the pattern recognition technology has applied to classify three kinds of detective patterns in semiconductor packages : Crack, Delamination and Normal. According to the results, we were confirmed that estimative algerian was provided the recognition rates of 75.7% (for Crack) and 83.4% (for Delamination) and 87.2 % (for Normal).

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.11
• /
• pp.1759-1766
• /
• 2001

Vibration transient generated by developing localized fault in gear can be used as indicators in gear fault detection. In this paper, we propose the zoomed phase map for a fault signal using continuous wavelet transfers to detect this vibration transient. Local fault induces the abrupt fluctuation of load exciting tooth and phase lag in the vibration signal measured on the gearbox. The relatively large fault like "tip breakage" easily can be detected by the clear fluctuation of exciting load. However, minor fault like "initial pitting"cannot be detected using the load fluctuation. To defect this kind of minor fault, the phase map for a fault signal is taken into account. The phase lag by minor fault is observed well in the zoomed phase map.

• The Korean Society of Law and Medicine
• /
• v.21 no.3
• /
• pp.77-116
• /
• 2020

The use of drugs that reflect the experiences and achievements of modern science has given human being the benefits of treating diseases and improving health conditions. However, in addition to the benefits of those, medicines have inherently inevitable adverse reactions. Many countries are taking measures such as market entry regulations or post-marketing surveillance to minimize damage caused by drug side effects, but the occurrence of side effects cannot be eliminated. Although the damage is force majeure, in some cases, the doctor who prescribed the drug or the pharmacist who administered the drug may have to compensate for the damage. The liability depends on whether the side effects were known in advance, the type of medicine, etc. On the other hand, in some cases, drug manufacturer may have to take liability for the side effect itself. As it is not easy for victims to be compensated for damages in those cases, many countries, including Korea, are setting to protect victims through the Product Liability Act. Drugs are also one of the product, so liability set by the Product Liability Act may apply. Even before the enactment and enforcement of the Product Liability Act, damage caused by drug has occurred. To resolve them, precedents have developed case law, which have many similarities with the Product Liability Act, but also have differences. Damage caused by drug manufactured prior to the enforcement of the Product Liability Act may occur in the future. In this context, the legal principles of the case laws will remain valid and be applied. This is an important reason to review the case law of precedents.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.171-179
• /
• 2020

Recently, studies have shown that convolution neural networks are achieving the best performance in image classification, object detection, and image generation. Vision based defect inspection which is more economical than other defect inspection, is a very important for a factory automation. Although supervised anomaly detection algorithm has far exceeded the performance of traditional machine learning based method, it is inefficient for real industrial field due to its tedious annotation work, In this paper, we propose ADGAN, a unsupervised anomaly detection architecture using the variational autoencoder and the generative adversarial network which give great results in image generation task, and demonstrate whether the proposed network architecture identifies anomalous images well on MNIST benchmark dataset as well as our own welding defect dataset.

• Communications of Mathematical Education
• /
• v.12
• /
• pp.67-82
• /
• 2001

발생적 원리는 수학을 공리적으로 전개된 완성된 것으로 가르치는 형식주의의 결함을 극복하기 위하여 제기되어온 교수학적 원리로, 수학을 발생된 것으로 파악하고 그 발생을 학습과정에서 재성취하게 하려는 것이다. 특히, 수학을 지도함에 있어서 역사적으로 발생, 발달한 순서를 지켜 지도해야 한다는 것이 역사-발생적 원리로, 수학이 역사적으로 발생, 발달 되어온 역동적인 과정을 학생들이 재경험해 보게 하기 위해서는 이러한 일련의 과정을 효과적으로 설명할 수 있는 교수-학습 방법이 필요하다. 변증법적인 방법론은 헤겔에 의해서 꽃을 피운 철학으로, 정일반일합(正一反一合)의 원리에 따라 사물의 발생과 진화 과정을 역동적으로 설명할 수 있는 방법론이다. 따라서, 본 연구는 초등학교에서 역사-발생적 원리에 따라 수학을 지도할 수 있는 방법으로 변증법적인 방법을 고찰하여, 역사-발생적 원리의 수학 교수-학습 방법에 대한 시사점을 얻고자 한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2016.05a
• /
• pp.295-296
• /
• 2016

UAV를 이용하여 정사영상과 수치지도제작을 위해서는 촬영계획대로 촬영해야 한다. 그러나 풍속, 풍향 및 시스템의 결함으로 촬영정확도가 저하된다. 저가 UAV의 waypoint기능을 활용한다면 다소 실수를 줄일 수 있다. 본 연구에서는 waypoint기능을 이용하여 비행정확도를 평가하고 모의촬영을 통해 촬영정확도를 확인하고자 한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.92-99
• /
• 2004

The formation degree of sustain (ITO pattern) decides quality of PDP (Plasma Display Panel). For this reason, it makes efforts in searching defects more than 30 un as 100%. Now, the existing inspection is dependent upon naked eye or microscope in off-line PDP manufacturing process. In this study developed prototype inspection system of PDP 170 glass is based on line-scan mechanism. Developed system creates information that detects and sorts kinds of defect automatically. Designed inspection technology adopts multi-vision method by slip-beam formation for the minimum of inspection time and detection algorithm is embodied in detection ability of developed system. Designed algorithm had to make good use of kernel matrix that draws up an approach to geometry. A characteristic of defects, as pin hole, substance, protrusion, are extracted from blob analysis method. Defects, as open, short, spots and et al, are distinguished by line type inspection algorithm. In experiment, we could have ensured ability of inspection that can be detected with reliability of up to 95% in about 60 seconds.