• Journal of Radiation Industry
• /
• v.17 no.4
• /
• pp.391-396
• /
• 2023

Currently, state-of-the-art devices such as SPECT, PET/CT, and PET/MRI are rapidly spreading nationwide, and the penetration rate of nuclear medical devices is also ranked fifth in the world. However, PET/MRI's system is slower and less common because it is more complex than PET/CT. The purpose of this study is to provide optimal information on PET/MRI according to the patient's disease. The subjects obtained information on head and neck cancer, pediatric patients, breast cancer patients, heart disease patients, lung cancer patients, and rectal cancer patients. We tried to accumulate protocols by obtaining a lot of information about each disease. In diagnosing head and neck cancer, it is believed that it is highly likely to be used in evaluating preoperative stage determination, recurrence and remote metastasis after treatment, and unclear primary cervical lymph node metastasis. Diagnosis and continuous follow-up of pediatric patients can increase patient benefits by minimizing radiation exposure. Breast cancer provides a comprehensive evaluation of the clinical need to determine the extent of disease in breast and local lymph nodes and the systematic stages of early diagnosis or recurrence. In diagnosing heart disease patients, MR-based PET motion correction helps to realize the full potential of PET images. For lung cancer patients, the clinical value and usefulness of the resolution and detection ability of integrated PET/MRI for soft tissues such as lung cancer will be sufficient. In diagnosing rectal cancer patients, the detection of missing residual diseases can change the clinical response evaluation for rectal cancer patients treated with TNT, and both the initial stage and treatment response evaluation are possible. Therefore, this literature study provided basic clinical data for PET/MRI tests.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1726-1748
• /
• 2024

Trajectory planning is vital for autonomous systems like robotics and UAVs, as it determines optimal, safe paths considering physical limitations, environmental factors, and agent interactions. Recent advancements in trajectory planning and future location prediction stem from rapid progress in machine learning and optimization algorithms. In this paper, we proposed a novel framework for Spatial-temporal transformer-based feed-forward neural networks (STTFFNs). From the traffic flow local area point of view, skip-gram model is trained on trajectory data to generate embeddings that capture the high-level features of different trajectories. These embeddings can then be used as input to a transformer-based trajectory planning model, which can generate trajectories for new objects based on the embeddings of similar trajectories in the training data. In the next step, distant regions, we embedded feedforward network is responsible for generating the distant trajectories by taking as input a set of features that represent the object's current state and historical data. One advantage of using feedforward networks for distant trajectory planning is their ability to capture long-term dependencies in the data. In the final step of forecasting for future locations, the encoder and decoder are crucial parts of the proposed technique. Spatial destinations are encoded utilizing location-based social networks(LBSN) based on visiting semantic locations. The model has been specially trained to forecast future locations using precise longitude and latitude values. Following rigorous testing on two real-world datasets, Porto and Manhattan, it was discovered that the model outperformed a prediction accuracy of 8.7% previous state-of-the-art methods.

• Journal of the Korean Institute of Rural Architecture
• /
• v.26 no.3
• /
• pp.29-36
• /
• 2024

The purpose of this study is to define the characteristics of regional architecture shown in the landscape paintings of Paul Cézanne, who is called the father of modern art, and then to think over the form of regional house in Korea modern architecture. The subject of the study focuses on landscape paintings depicting landscapes among Paul Cézanne's post-impressionist works. The research contents are, first, to understand the landscape structural and cubical characteristics of primary psyche-scene landscapes in his thoughts and insight, and second, to understand the characteristics of regional architecture depicted in his landscape paintings. In this study, characteristics of color in his pictures were excluded, and I attempted to find the origins of pure cube, then tried to pull out the cubical from from Korean regional architecture. The research results are summarized as follows. First, more than 54.7% of Paul Cézanne's paintings are post-impressionism, and the fact that he chose landscapes as the subject of his paintings can be explained to show the value of primary psycho-scene. Second, the building depicted in Paul Cézanne's painting is a pure cube as bastide and mas that are local houses in the Aix-en-Provence region in southern France. Third, Korean cubical flat style of house in the village comes from De Stijl that was provided the concept of Cubism and Mondrian's neo-plasticism.

• Korea Science and Art Forum
• /
• v.20
• /
• pp.255-265
• /
• 2015

When it comes to how to define history·culture streets, people think of the streets as street environments that would create local identity in association with this local community's particular historical and cultural resources as well as urban streets. In order to build such streets, any relevant fields first need to apply some original design based on understanding on historical and cultural resources. With Street of Gaya in Gimhae selected as a research subject, this study aims to look into components and color characteristics of the history·culture street and finds ways to create other streets of that kind. As a frame to understand the history·culture streets, what this study would come up with is considered significant in that it helps the value to be re-recognized and promoted. In order to achieve the research goal, the study (1) extracted components of streetscapes referring to relevant previous researches and then, (2) analyzed a current status of these components of Street of Gaya via field investigation. (3) The study examined color characteristics of each of the components. Findings of the research are summarized as follows. (1) From a comprehensive point of view, the study categorized and subdivided the components of the history·culture street into nonphysical and physical elements. (2) After analyzing the current status of the components, the study learned that Street of Gaya basically consists of historical and cultural remains and sculptures as well as street facilities. (3) Results of the color investigation reported that the plan on designing of Street of Gaya had been processed with a focus laid on harmony of historical remains and cultural remains which are told to be natural components. However, the study also figured out that as long as relevant fields want to create different identity in each section and to efficiently deliver information, they should first prepare this smart design system to integrate each pieces of a streetscape as a whole.

• (The) Research of the performance art and culture
• /
• no.35
• /
• pp.405-439
• /
• 2017

In this article, I suggest issues and tasks in transmission of Gyeonggi Province folk songs after thorough study of designation of Gyeonggi Province folk songs as intangible cultural asset, reproduction and transmission. Intangible cultural assets are classified into seasonal playing and songs. Originally, category or extension of folk songs is above mere songs and it also embraces personal lives as well as village communities. Intangible assets of folk songs are folk art, group events and non-stage events at the same time based on tradition, history, uniqueness, characters of field value. Gyeonggi Province has 9 intangible assets now because of the revocation of several assets (All Gyeonggi Province, Hwasung, Gwacheon) within five years after initial designation of 13 assets in 1998. They are mostly distributed in the north Gyeonggi region where is close to the DMZ and delay in development seems to have enabled the preservation. Most of the intangible cultural assets are farming songs and weeding which show characteristics of Gyeonggi Province. Most of the designees are who performed excavation, recovery, excluding a few cases without designees on designation, and almost all the designee passed away. Number of cases have been revoked because transmission was not completed or some cases were transmitted to groups rather than specific designees. Subscription concert, the biggest and most representative event, is performed once a year with all of the 9 intangible cultural assets in the original complete forms of the designation. Intangible cultural assets are classified into seasonal playing and songs. In general, current performance of the intangible cultural assets and folk songs are same as the originally designated forms and are not in varied forms other than folk songs like songs for rice-planting and weeding. Funeral songs are transmitted in Yangju and Yangpyeong. In terms of the operation, preservation societies having training centers have been performing more constant activities for preservation including lecture, performance and transmission. Members are quite aged and the societies are suffering from lack of support fund for reproduction and transmission. Problems in reproduction and tasks for the transmission I would like to suggest are like followings. First, preservation and value of the cultural assets. Second, new understanding of designation and revocation of the intangible cultural assets. Third, record of performance and sound source. Fourth, liaison with local communities. Fifth, organization of professional resources and establishment of systematic support and management.

• (The) Research of the performance art and culture
• /
• no.19
• /
• pp.221-280
• /
• 2009

This thesis is a study of the rise and the characteristic of 'Hyangto Gakeuk(literally Song drama of the country or local music drama)' in the Early 1940s. During the colonial period, there were attempts to incorporate traditional Korean music elements with Western operatic form. This type of music drama with librettos based on traditional tales came to be known as 'Hyangto Gakeuk'. Mostly 'Hyangto Gakeuk' has led this effort under the director Seo Hang-Suk, the composer Ahn Ki-Young and the lyricist Seol Eui-sik. In the first chapter, the study aims at arranging the performance history of 'Hyangto Gakeuk' composed by Ahn Ki-Young. Also, the study examined representative works after classifying 'Hyangto Gakeuk' performed by Lamila Music Drama Troupe, and Bando Music Drama Troupe. There is significant meaning to evaluate 'Hyangto Gakeuk' in the history of Korean music drama through this analysis of the performance history. In the second chapter, I will analyze with representative works composed by Ahn Ki-Young, a pioneer in the Korean art song. He tried to create the music that held the nationalism and tradition. His works which were called 'Kageuk' laid down the foundation of Korean original operatic style. This study demonstrated characteristics of 'Hyangto Gakeuk' as 'the beginning' in modern musical drama history and its effects on Korean musical drama developments. Namely, 'Hyangto Gakeuk' based on Korean traditions can be seen as examples of original modern musical in Korea. Practically, study on all the aspects of performance not only text generally studied, dramaturgy and criticism, but also performance concept and intention of creators in early period.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.43 no.5
• /
• pp.74-86
• /
• 2015

The purpose of this study was to deduce the landscape evaluation indices that can be applied from the preparation for the registration of major national farm/fishery heritages to post-management. For this purpose, the Delphi survey was performed on experts. From August to November in 2014, the primary open survey, secondary open survey, and tertiary closed survey were performed to gather opinions from 28 experts, 25 experts, and 29 experts, respectively. As a result, the landscape evaluation indices for farm/fishery heritage consisted of five areas of evaluation, ten items of evaluation, and 40 indices of evaluation. The areas of evaluation were rurality, authenticity, aesthetics, tourism potentials, and locality. Rurality was classified into rurality of farm/fishery towns and nostalgia. Authenticity was classified into objective authenticity and existential authenticity. Aesthetics was classified into attractiveness and harmony. Tourism potentials were classified into value of resources and value of usability. Locality was divided into physical originality and cultural identity. The study made the following findings: first, the general grounds of farm/fishery landscape evaluation cannot be applied when evaluating the quality of landscapes of farm/fishery heritage, as their value as a cultural heritage should be considered. Second, the new indices valued emotional factors in addition to the physical factors considered by the existing farm/fishery landscapes. The new indices involved a more expanded concept of landscapes as it also considers everyday or temporary activities, including the farm/fishery activities of local people or participation in festivals and experience programs. Third, farm/fishery heritage focuses on the lives of local people, as it involves both the synchronic and the diachronic perspectives to see what is currently visible and what is no longer visible. This brings into consideration not only the farms and the natural environments but also their relationships with the villages, especially the residential areas. Finally, the indices reflected both the farm/fishery heritage's value as cultural heritage and its value for tourism. They derived temporary and dynamic landscapes, including the trading activities of local specialty markets in relation to the production landscapes. However, further studies should be conducted as this study could not rate the relative importance of indices or compare the total scores of landscapes without the weight of each item.

• The Korean Journal of Air & Space Law and Policy
• /
• v.20 no.1
• /
• pp.211-253
• /
• 2005

Recently, the Korean Supreme Court released two important decisions concerning damages for the pain and suffering from Aircraft noise. The local people who are living near the Air Force practice site at Maehyang-ri and the Kimpo International Airport brought lawsuits against the Korean government requesting damages for their financial loss from the severe noise and the damages for their pain and suffering. Plaintiffs alleged that they suffered physical malfunctions, extreme disturbances and the reduction of property values from the extreme noises which were daily repeated. District Court of Seoul Province did not allow plaintiffs all but the damages for pain and suffering. Plaintiffs could not prove the causation between their financial loss and the noise. The Supreme Court confirmed the lower court's decision. Article V of the National Compensation Act (analogous to the Federal Tort Claims Act of the USA) reads, "the government shall be liable for any loss caused by the defect on establishment or maintenance of public facilities." In the two cases, the major issue was whether the government's establishment or maintenance of Air Force practice site and the airport was defective because they caused serious noise to surrounding neighbors. Previously, the Supreme Court interpreted the clause "defect on establishment or maintenance of public facilities" as failure of duty to provide safety measures to the degree generally required to ordinary manager. However the Court at this time interpreted differently that the defect could be found if the facility caused to any person loss to the degree intolerable. In the two cases the Court confirmed the lower court's finding that noise level at the site was severe enough to be intolerable. This standard is based on the severity of the loss rather than the failure of duty. It became easier for plaintiffs to prove the cause of action under this interpretation. The consequence of the ruling of these two cases is 'rush to the courtroom' by the local people at similar situations. The ruling of these two cases was not appropriate both in theory and in consequence. The Korean tort system is basically based on the theory of negligence. Strict liability is exceptional only when there is special legislation. The Court created strict liability rule by interpreting the Art. V of the National Compensation Act. This is against the proper role of the court. The result of the cases is also dismal. The government was already sued by a number of local people for damages. Especially the Department of Defense which is operating many airports nationwide has financial hardship, which will cause downsizing military practice by the Air Force in the long run, This is no good to anyone. Tens of millions of dollars which might be used for compensation might be better used to prevent further noise problem surrounding airports.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.34 no.3
• /
• pp.18-27
• /
• 2016

A 'flowered-wall,' which are also called a 'flower plant patterned wall,' or a 'flower patterned wall,' is a wall of a building or a fence with various patterns on it. A flowered-wall can be an external mean to look into the owner's authority and values while internally it possesses the symbolic meaning of wishing the well-being and peace of the household. In the research area of the flowered-wall, the walls located in the palace were well researched in various studies across architecture, horticulture, and art design, however, the walls belonging to the local regional traditional folk houses and temples have been involved in little to no research in the landscape architectural area. Taking notice of this perspective this study researched and analyzed the cases of the flowered-walls of the traditional folk houses and the temples that belonged to the national and municipal cultural properties of Jeollabuk-do Province from the landscape architectural perspective. The whole samples were examined and it was shown that there were 9 traditional folk houses with flowered-walls. Among the temples there were 7 cases. Therefore the research focusing on tracing the shape and symbolic meaning of the flowered-walls in the 16 cultural properties located in the Jeollabuk-do Province which consisted of traditional folk houses and temples resulted in the following. Flowered-walls displayed hierarchical differentiation revolving around the main space and its spacial characteristic. This differentiation is variously displayed across the flowered-wall, gable, crack plastering, and chimney. In the case of the folk houses the symbols have the meaning of the prosperity of the household and progeny, exorcism, longevity, number of fortune, harmony, and peace etc that prays for practical wishes such as long life and good health with the prosperity of their descendants. Meanwhile in the temples, symbols indicating an easy passage into eternity, perpetuation of the Buddha-nature, and three marks of existence are applied, differentiating from the folk houses by the appliance of the religious values in the patterns. In conclusion this research resulted in the rightful illumination on the local landscape culture, the possibility of expressing the Korean sentiment through flowered-walls in the contemporary space, the reassessment of flowered-walls, and the provision of basic data for a plan to success the cultural heritage.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.