http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Kidong Lee(이기동),Sung Yi(이성),Soongkeun Hyun(현승균),Cheolhee Kim(김철희) 대한용접·접합학회 2021 대한용접·접합학회지 Vol.39 No.1
During machine learning algorithms, deep learning refers to a neural network containing multiple hidden layers. Welding research based upon deep learning has been increasing due to advances in algorithms and computer hardwares. Among the deep learning algorithms, the convolutional neural network (CNN) has recently received the spotlight for performing classification or regression based on image input. CNNs enables end-to-end learning without feature extraction and in-situ estimation of the process outputs. In this paper, 18 recent papers were reviewed to investigate how to apply CNN models to welding. The papers was classified into 5 groups: four for supervised learning models and one for unsupervised learning models. The classification of supervised learning groups was based on the application of transfer learning and data augmentation. For each paper, the structure and performance of its CNN model were described, and also its application in welding was explained.
Effects of anesthetic protocol on normal canine brain uptake of 18F-FDG assessed by PET/CT.
Lee, Min Su,Ko, Jeff,Lee, Ah Ra,Lee, In Hye,Jung, Mi Ae,Austin, Brenda,Chung, Hyunwoo,Nahm, Sangsoep,Eom, Kidong The College 2010 Veterinary Radiology and Ultrasound Vol.51 No.2
<P>The purpose of this study was to assess the effects of four anesthetic protocols on normal canine brain uptake of 2-deoxy-2-[18F]fluoro-D-glucose (FDG) using positron emission tomography/computed tomography (PET/CT). Five clinically normal beagle dogs were anesthetized with (1) propofol/isoflurane, (2) medetomidine/pentobarbital, (3) xylazine/ketamine, and (4) medetomidine/tiletamine-zolazepam in a randomized cross-over design. The standard uptake value (SUV) of FDG was obtained in the frontal, parietal, temporal and occipital lobes, cerebellum, brainstem and whole brain, and compared within and between anesthetic protocols using the Friedman test with significance set at P < 0.05. Significant differences in SUVs were observed in various part of the brain associated with each anesthetic protocol. The SUV for the frontal and occipital lobes was significantly higher than in the brainstem in all dogs. Dogs receiving medetomidine/tiletamine-zolazepam also had significantly higher whole brain SUVs than the propofol/isoflurane group. We concluded that each anesthetic protocol exerted a different regional brain glucose uptake pattern. As a result, when comparing brain glucose uptake using PET/CT, one should consider the effects of anesthetic protocols on different regions of the glucose uptake in the dog's brain.</P>
Kidong Lee(이기동),Sung Yi(이성),Soongkeun Hyun(현승균),Cheolhee Kim(김철희) 대한용접·접합학회 2021 대한용접·접합학회지 Vol.39 No.1
With the development of deep learning technology, research on classification and regression models on welding phenomena using convolution neural networks (CNNs) are gradually increasing. Part 1 of this study introduced the characteristics of deep learning models using CNNs and their application to welding studies. In this paper, we reviewed recent welding research papers to analyze how to evaluate CNN models and visualize the modeling output, and details of evaluation index, comparison models, and visiualization methods were explained.
A Study of Data Mining Techniques in Banktuptcy Prediction
Lee, Kidong 한국경영과학회 2003 韓國經營科學會誌 Vol.28 No.2
In this paper, four different data mining techniques, two neural networks and two statistical modeling techniques, are compared in terms of prediction accuracy in the context of bankruptcy prediction. In business setting, how to accurately detect the condition of a firm has been an important event in the literature. In neural networks, Backpropagation (BP) network and the Kohonen self-organizing feature map, are selected and compared each other while in statistical modeling techniques, discriminant analysis and logistic regression are also performed to provide performance benchmarks for the neural network experiment. The findings suggest that the BP network is a better choice among the data mining tools compared. This paper also identified some distinctive characteristics of Kohonen self-organizing feature map.
한국사상(韓國思想)(철학(哲學)) : 하서(河西)김인후의 삶과 철학
이기동 ( Kidong Lee ) 한국사상문화학회 2015 韓國思想과 文化 Vol.77 No.-
현대인들은 온갖 물질적 풍요를 누리면서도 마음이 황폐해지고 영혼이 고달프게 되었다. 마음이 각박해진 현대인들은 정신적으로는 옛사람 들보다 더 불행한 것으로 보인다. 우울증에 시달리는 사람이 늘어가고 자살율도 점점 증가한다. 현대인들은 지나친 경쟁과 이익추구로 인해인간사이의 따뜻한 마음이 고갈되었다. 이처럼 차가워진 마음으로 시행하는 어떤 정책이나 일들이 제대로 될 리가 없다. 오늘날 세계적으로 불어 닥치고 있는 경제위기도 근본적으로는 이러한 마음에서 기인하는 것으로 보인다. 현대인들의 이러한 문제를 해결하는 근본 방식은 인간의 마음을 바로잡는 일에서부터 시작하지 않으면 안 된다. 이러한 시점에서 우리는 옛날 조선시대에 한 점의 욕심도 없이 깨끗이 살았던 한 선비의 삶을 돌아보는 것은 큰 의미가 있다. 하서 김인후 선생의 삶과 사상은 삶의 올바른 방향을 잃고 욕심을 따라 우왕좌왕하는 오늘날의 사람들에게 삶의 지표를 제공하는 한 기준이 될 것이다. 하서선생은 지상천국을 건설하려는 꿈을 가졌다가 좌절했지만, 거기에 머물지 않고 더 큰 실천을 위한 수양철학을 강화했다. 수양철학이 완성되면 지상천국의 건설은 저절로 되는 것이기 때문이다. 하서선생은 지성천국의 소쇄원이라는 정원을 통해서 보여주기도 했다. 하서선생의 이러한 노력은 오늘날 우리들에게 삶의 기준이 되기에 충분하다. People in modern society are materially rich but are spiritually and socially poor. People look mentally unhappier than people in old days. More people are suffering from depression and more people are killing themselves. People have only been seeking for economic profits and they are exhausted by competition. As a result, there is so space left for peace and comfort in their mind. Based on this situation, no polices and plans are likely to succeed. The economic crisis over the world seem to result from the same reason. In order to solve the problems that modern people are facing with, we should start from letting go of our greed and purifying our mind. Therefore, it would be meaningful to look back upon the life of Haseo Inhoo Kim who had lived a pure unselfish life. His life will be an indicator for us to rebuild our lives in a positive way. Haseo got discouraged after having failed in creating heaven on earth. Nevertheless, he did not back down and fortified his philosophy to cultivate his mind. He believed that the heaven on earth would be automatically made once he consummated his philosophy. He also made a garden called ``Soswaewon`` to give people the image of heaven on earth. Haseo`s such effort and his philosophy will let us think about how to live a good life and find an answer to the question.
머신러닝을 이용한 레이저 용접부의 모델링 Part I: Al/Cu 이종재료 겹치기 레이저용접부의 용입깊이
이기동(Kidong Lee),강상훈(Sanghoon Kang),강민정(Minjung Kang),이성(Sung Yi),현승균(Soongkeun Hyun),김철희(Cheolhee Kim) 대한용접·접합학회 2021 대한용접·접합학회지 Vol.39 No.1
Thin sheets of Al/Cu dissimilar materials are overlap welded for the electrical connection of secondary battery electrodes by laser welding. The weld penetration depth is an important joint quality to ensure strength and electrical conductance. It is difficult to predict the penetration depth using analytical methods because of the high laser reflection and small thickness of the base materials. Several machine learning algorithms were investigated to develop regression models for the penetration depth. The models included linear regression, decision tree, supported vector regression, Gaussian process regression, and decision tree ensemble model groups. The regression models with high degrees of freedom showed excellent mean absolute percentage errors (MAPE) and coefficients of determination (R²). In particular, the Gaussian process regression model with exponential kernels had an MAPE of 0.2% and an R² of unity.