• International Journal of Precision Engineering and Manufacturing
• /
• v.9 no.2
• /
• pp.75-80
• /
• 2008

The fabrication of complex three-dimensional electrodes for micro electrical discharge machining (micro-EDM) is an important issue in the field of micromachining Localized electrochemical deposition (LECD) is a simple and inexpensive technique for fabricating micro-EDM electrodes. This study presents a new process for manufacturing electrodes with complex cross-sections using masks of different shapes, In this process, a non-conductive mask is placed between an anode and cathode that are immersed in a plating solution of acidified copper sulfate. The LECD is achieved by applying a pulsed voltage between the anode and cathode, which are separated by a small distance. In this setup, the cathode is placed above the anode and the mask, so that the deposited electrode can be used directly for EDM without changing the tool orientation. We found that the microstructure of the deposited electrode is influenced by the concentration of the plating solution and organic additives. Moreover, the values of the voltage, frequency, and duty cycle of the pulsed input have significant effects on the microstructure of the fabricated electrode. Finally, the optimum values of the voltage, frequency, and duty cycle were determined for the most effective fabrication of complex-shaped electrodes.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.1
• /
• pp.49-59
• /
• 2019

Generative adversarial networks(GANs) have received great attention in the machine learning field for their capacity to model high-dimensional and complex data distribution implicitly and generate new data samples from the model distribution. This paper investigates the model training methodology, architecture, and various applications of generative adversarial networks. Experimental evaluation is also conducted for generating synthetic image dataset for defense using two types of GANs. The first one is for military image generation utilizing the deep convolutional generative adversarial networks(DCGAN). The other is for visible-to-infrared image translation utilizing the cycle-consistent generative adversarial networks(CycleGAN). Each model can yield a great diversity of high-fidelity synthetic images compared to training ones. This result opens up the possibility of using inexpensive synthetic images for training neural networks while avoiding the enormous expense of collecting large amounts of hand-annotated real dataset.

• Genomics & Informatics
• /
• v.20 no.1
• /
• pp.7.1-7.13
• /
• 2022

2-Methoxy-1,4-naphthoquinone (MNQ) has been shown to cause cytotoxic towards various cancer cell lines. This study is designed to investigate the regulatory effect of MNQ on the key cancer genes in mitogen-activated protein kinase, phosphoinositide 3-kinase, and nuclear factor κB signaling pathways. The expression levels of the genes were compared at different time point using polymerase chain reaction arrays and Ingenuity Pathway Analysis was performed to identify gene networks that are most significant to key cancer genes. A total of 43 differentially expressed genes were identified with 21 up-regulated and 22 down-regulated genes. Up-regulated genes were involved in apoptosis, cell cycle and act as tumor suppressor while down-regulated genes were involved in anti-apoptosis, angiogenesis, cell cycle and act as transcription factor as well as proto-oncogenes. MNQ exhibited multiple regulatory effects on the cancer key genes that targeting at cell proliferation, cell differentiation, cell transformation, apoptosis, reduce inflammatory responses, inhibits angiogenesis and metastasis.

• Journal of architectural history
• /
• v.31 no.1
• /
• pp.41-50
• /
• 2022

Traditional wooden buildings deform over time and are vulnerable to fire or earthquakes. Therefore, traditional wooden buildings require continuous management and repair, and securing architectural drawings is essential for repair and restoration. Unlike modernized CAD drawings, traditional wooden building drawings scan and store hand-drawn drawings, and in this process, many noise is included due to damage to the drawing itself. These drawings are digitized, but their utilization is poor due to noise. Difficulties in systematic management of traditional wooden buildings are increasing. Noise removal by existing algorithms has limited drawings that can be applied according to noise characteristics and the performance is not uniform. This study presents deep artificial neural network based noised reduction for architectural drawings. Front/side elevation drawings, floor plans, detail drawings of Korean wooden treasure buildings were considered. First, the noise properties of the architectural drawings were learned with both a cycle generative model and heuristic image fusion methods. Consequently, a noise reduction network was trained through supervised learning using training sets prepared using the noise models. The proposed method provided effective removal of noise without deteriorating fine lines in the architectural drawings and it showed good performance for various noise types.

• Bulletin of the Korean Chemical Society
• /
• v.25 no.8
• /
• pp.1121-1122
• /
• 2004

• Proceedings of the Korean Powder Metallurgy Institute Conference
• /
• 2006.09a
• /
• pp.306-307
• /
• 2006

The sinter-bonding behavior of iron based powder mixtures was investigated. To produce the green compacts to be joined the following powders based on $H{\ddot{o}}gan{\ddot{a}}s$ AB grade NC 100.24 plain iron powder were used: NC 100.24 as delivered, PNC 30, PNC 60 and NC 100.24 + 4%Cu powder mixtures. Dimensional behaviour of all those materials during the sintering cycle was monitored by dilatometry. Simple ring shaped specimens as the outer parts and cylindrical as the inner parts were pressed. The influence of parts' composition on joining strength was established. Diffusion of alloying elements: copper and phosphorous, across the bonding surface was controlled by metallography, SEM and microanalysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.475-478
• /
• 2019

Although the work of neural style transfer has shown successful applications in transferring the style of a certain type of artistic painting, it is less effective in transferring Oriental paintings. In this paper, we explore three methods which are effective in transferring Oriental paintings. Then, we take a typical network from each method to carry on the experiment, in view of three different methods to Oriental paintings style transfer effect has carried on the discussion.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.395-399
• /
• 2019

생성 모델은 최근 단순히 기존 데이터를 증강 시키는 것이 아니라 원하는 속성을 가지도록 스타일을 변화시키는 연구가 활발히 진행되고 있다. 스타일 변화 연구에서 필요한 병렬 데이터 세트는 구축하는데 많은 비용이 들기 때문에 비병렬 데이터를 이용하는 연구가 주를 이루고 있다. 이러한 방법론으로 이미지 분야에서 대표적으로 cycleGAN[1]이 있으며 최근 자연어 처리 분야에서도 많은 연구가 진행되고 있다. 많은 논문들이 사용하는 데이터도메인은 긍정 문장과 부정 문장 사이를 변화시키는 것이다. 본 연구에서는 한국어 영화리뷰 데이터 세트인 NSMC[2]를 이용한 감성 변화를 하는 문장생성에 대한 연구로 자연어 처리에서 좋은 성능을 보여주는 BERT[8]를 생성모델에 이용하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.171-182
• /
• 2022

The safe use of a structure requires it to be maintained in an undamaged state. Thus, a typical factor that determines the safety of a structure is a crack in it. In addition, cracks are caused by various reasons, damage the structure in various ways, and exist in different shapes. Making matters worse, if these cracks are unattended, the risk of structural failure increases and proceeds to a catastrophe. Hence, recently, methods of checking structural damage using deep learning and computer vision technology have been introduced. These methods usually have the premise that there should be a large amount of training image data. However, the amount of training image data is always insufficient. Particularly, this insufficiency negatively affects the performance of deep learning crack detection algorithms. Hence, in this study, a method of augmenting crack image data based on the image translation technique was developed. In particular, this method obtained the crack image data for training a deep learning neural network model by transforming a specific case of a asphalt crack image into a concrete crack image or vice versa . Eventually, this method expected that a robust crack detection algorithm could be developed by increasing the diversity of its training data.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.1-9
• /
• 2020

In this paper, we propose a model that performs more natural facial attribute editing by utilizing mask information in the hair and hat region. STGAN, one of state-of-the-art research of facial attribute editing, has shown results of naturally editing multiple facial attributes. However, editing hair-related attributes can produce unnatural results. The key idea of the proposed method is to additionally utilize information on the face regions that was lacking in the existing model. To do this, we apply three ideas. First, hair information is supplemented by adding hair ratio attributes through masks. Second, unnecessary changes in the image are suppressed by adding cycle consistency loss. Third, a hat segmentation network is added to prevent hat region distortion. Through qualitative evaluation, the effectiveness of the proposed method is evaluated and analyzed. The method proposed in the experimental results generated hair and face regions more naturally and successfully prevented the distortion of the hat region.