• Journal of the Korean Society of Radiology
• /
• v.15 no.6
• /
• pp.861-867
• /
• 2021

Since SBRT takes up to 1 hour from 30 minutes to treatment fraction once or three to five times, there is a possibility of setup error during treatment. To reduce these set-up errors and give accurate doses, we intend to evaluate the usefulness of pre-treatment and post-treatment error values by imaging CBCT again to determine postural movement due to pre-treatment coordinate values using pre-treatment CBCT. On average, the range of systematic errors was 0.032 to 0.17 on the X and Y,Z axes, confirming that there was very little change in movement even after treatment. Tumor centripetal changes (±SD) due to respiratory tuning were 0.11 (±0.12) cm, 0.27 (±0.15) cm, and 0.21 cm (±0.31 cm) in the X, Y and Z directions. The tumor edges ±SD were 0.21 (±0.18) cm, 0.30 (±0.23) cm, and 0.19 cm (±0.26) cm in the X, Y and Z directions. The (±SD) of tumor-corrected displacements were 0.03 (±0.16) cm, 0.05 (±0.26) cm, and 0.02 (±0.23) cm in RL, AP, and SI directions, respectively. The range of the 3D vector value was 0.11 to 0-.18 cm on average when comparing pre-treatment and CBCT, and it was confirmed that the corrected set-up error was within 0.3 cm. Therefore, it was confirmed that there were some changes in values depending on some older patients, condition on the day of treatment, and body type, but they were within the significance range.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Journal of fish pathology
• /
• v.31 no.2
• /
• pp.115-122
• /
• 2018

The Houttuynia cordata has been utilized for various beneficial purposes in humans mainly because of its potent antioxidant principle quercitrin present in this plant. This study examines the possibility of producing a functional sea food commodity containing active principle quercitrin by feeding H. cordata for a extended period. Spotted sea bass (Lateolabrax maculatus) were fed a diet containing H. cordata at 0.1-1.0% levels for 1 month and tissue concentrations of quercitrin were analyzed in serum, hepatopancreas and muscle. It was observed that quercitrin was found in the ranking order of hepatopancreas>muscle>serum. After a bolus administration of quercitrin (20 mg/kg, oral) to spotted sea bass and Nile tilapia (Oreochromis niloticus), idential rank order was observed after 48 hr. In contrast, the order was liver>serum>muscle in rat and mice, indicating that higher quercitrin distribution occurs to the muscle in fishes compared with in mammals tested. High residue concentration of qeurcitrin in the edible tissue can be an advantageous property in terms of functional food production. High level H. cordata extract inclusion of 1.0% seems to have detrimental effects in spotted sea bass leading to growth retardation and hepatic damage. It was concluded that incorporation of H. cordata extract into diet can be a way of producing healthy foods. However the level of active extract needs fine tuning to avoid toxicity to fishes.

• Journal of the Korean Applied Science and Technology
• /
• v.36 no.2
• /
• pp.645-655
• /
• 2019

In this study, colloidal microgel with viscoelasticity were prepared by using dispersion containing physical crosslinking agents and microgels with various strengths depending on the degree of cross-links.As the chemical crosslinking agent PEGDA400 content increased, hydrogels have various physical properties the swelling ratio decreased from $2.0{\times}10^4%$ to $6.0{\times}10^3%$ and increased viscosity by about 60%. The colloidal microgel was prepared with micro hydrogel grinded to $100{\mu}m$ size and the rheological behavior was confirmed with physical cross linking agent. A colloidal microgel having various viscosities was prepared by controlling starch and alginate based on micro-hydrogel containing 0.75% (w/v) of PEGDA400. In conclusion, these results would be highly useful for applying as a product that can give various physical properties to the colloidal suspensions, cosmetics, paint, and food industry.

• Korean Journal of Optics and Photonics
• /
• v.30 no.4
• /
• pp.142-145
• /
• 2019

Normally, a corner cube retroreflector (CCRR) sheet is used as a retroreflective mirror array (RRMA) in a volumetric display. Each CCRR unit reflects light in the retroreflective direction, which is parallel to the incident light, and it makes a blurred image, as it shifts the position of light within its dimensions. Adopting a "curved planar wall" and "parabolic focusing" (x-axis), a hybrid-t(transverse direction)-RRMA is proposed, to improve the image quality and brightness. The improvement of image contrast is achieved by tuning a "linear v-shaped groove" structure to a "parabolic v-shaped groove". Also, the system has been simplified and the brightness enhanced 4 times by removing the half mirror.

• Korean Journal of Optics and Photonics
• /
• v.30 no.4
• /
• pp.154-158
• /
• 2019

We have used a mid-IR (mid-infrared) continuous-wave (cw) optical parametric oscillator (OPO), developed previously and described in Ref. 12, to build a performance-evaluation setup for a mid-IR spectrometer. The used CW OPO had a wavelength tuning range of $ 2.5-3.6{\mu}m$ using a pump laser with a wavelength of 1064 nm and a fan-out MgO-doped periodically poled lithium niobate (MgO:PPLN) nonlinear crystal in a concentric cavity design. The OPO was combined with a near-IR integrating sphere and a Fourier-transform IR optical spectrum analyzer to build a performance-evaluation setup for mid-IR spectrometers. We applied this performance-evaluation setup to evaluating a mid-IR spectrometer developed domestically, and demonstrated the capability of evaluating the performance, such as spectral resolution, signal-to-noise ratio, spectral stray light, and so on, based on this setup.

• International Area Studies Review
• /
• v.22 no.3
• /
• pp.255-292
• /
• 2018

This paper evaluates the new food policy adopted by the European Union to enhance the food safety after the mad cow crisis occurred in 1990's. Newly introduced rules at the EU level are characterized by two features. Firstly, an important part of them have the form of Regulation which is a binding legislative to all member countries. Secondly, most of them are horizontally applied to the whole food industry, irrespective of their kinds of performance, hygiene or labelling. According to theoretical studies on this topic, any food safety regulation for solving adverse selection problem or reducing negative externality in food consumption should be fine-tuning depending on the concrete demand and costs conditions of the food sector concerned. In this theoretical perspective, the food safety laws introduced at EU level after mad cow crisis have been over-regulated for improving social welfare. The true motivation for the transfer of the policy competence on food safety to the Union level is political rather than economic. Our analysis with a political economic perspective shows that how the EU food regulations have been embraced not only by the governments of member countries, but also by diverse interest groups like food processor & distributors, consumers and agro-livestock groups, and that they have been used as protectionist purpose specially against non-member developing countries. Taking into account the fact that the basic aim to form the Union is to establish a single market to enhance economic efficiency at the Union level, the EU is required to adopt some policy actions to reduce negative effects of too restrictive food safety regulations.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.453-463
• /
• 2021

The purpose of this study is to establish the most severe impacts of Covid-19 in the field of the performing arts and to explore countermeasures taken both at home and abroad. This study has been conducted through literature surveys. The conclusion is as follows. First, since the outbreak of Covid-19, theater venues around the world have actively taken part in uploading recorded performances to streaming services. Secondly, these performance visualizings are generally considered as being complimentary goods rather than a substitute for live performance. Thirdly, although more audiences are tuning into watch on-line performances, consumption is concentrated on a few theaters which have a worldwide reputation and a broad range of content. Fourthly, to tackle the impact that Covid-19, the UK government announced a series of job protection schemes in the field of the Arts. In addition, Arts Council England prepared an emergency response package. In Korea, some countermeasures such as government support for artists and cultural establishments have also been implemented. Lastly, some suggestions for the sector. I conclude that there is an need for domestic companies to secure core contents of significant quality and to make strategic alliances with leading overseas performance companies so that they may cooperate together.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.228-239
• /
• 2022

In this paper, we propose an unmanned vehicle scratch detection deep learning model for car sharing services. Conventional scratch detection models consist of two steps: 1) a deep learning module for scratch detection of images before and after rental, 2) a manual matching process for finding newly generated scratches. In order to build a fully automatic scratch detection model, we propose a one-step unmanned scratch detection deep learning model. The proposed model is implemented by applying transfer learning and fine-tuning to the deep learning model that detects changes in satellite images. In the proposed car sharing service, specular reflection greatly affects the scratch detection performance since the brightness of the gloss-treated automobile surface is anisotropic and a non-expert user takes a picture with a general camera. In order to reduce detection errors caused by specular reflected light, we propose a preprocessing process for removing specular reflection components. For data taken by mobile phone cameras, the proposed system can provide high matching performance subjectively and objectively. The scores for change detection metrics such as precision, recall, F1, and kappa are 67.90%, 74.56%, 71.08%, and 70.18%, respectively.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.101-125
• /
• 2022

Recently, with the development of computing technology and the improvement of the cloud environment, deep learning technology has developed, and attempts to apply deep learning to various fields are increasing. A typical example is anomaly detection, which is a technique for identifying values or patterns that deviate from normal data. Among the representative types of anomaly detection, it is very difficult to detect a contextual anomaly that requires understanding of the overall situation. In general, detection of anomalies in image data is performed using a pre-trained model trained on large data. However, since this pre-trained model was created by focusing on object classification of images, there is a limit to be applied to anomaly detection that needs to understand complex situations created by various objects. Therefore, in this study, we newly propose a two-step pre-trained model for detecting abnormal situation. Our methodology performs additional learning from image captioning to understand not only mere objects but also the complicated situation created by them. Specifically, the proposed methodology transfers knowledge of the pre-trained model that has learned object classification with ImageNet data to the image captioning model, and uses the caption that describes the situation represented by the image. Afterwards, the weight obtained by learning the situational characteristics through images and captions is extracted and fine-tuning is performed to generate an anomaly detection model. To evaluate the performance of the proposed methodology, an anomaly detection experiment was performed on 400 situational images and the experimental results showed that the proposed methodology was superior in terms of anomaly detection accuracy and F1-score compared to the existing traditional pre-trained model.