• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.40 no.4
• /
• pp.15-31
• /
• 2022

This study interpreted the logical validity of the landscape restoration and maintenance patterns of Changgyeonggung Palace, where modern landscapes coexist. The results of the study are as follows; First, the changes in the landscape restoration and maintenance attitude concerning the Changgyeonggung management organization were identified. With the establishment of the Office of the Imperial Garden, an imperial property was nationalized. The Cultural Heritage Managing Department was opened in 1961, and Changgyeonggung Palace were preserved as designated as historical sites in 1963. An environmental purification was implemented by the Changgyeonggung Office as a follow-up measure for restoration in 1983. As the Cultural Heritage Administration promoted in 1999 and the Royal Palaces and Tombs Center was established in 2019, the palace has been managed professionally as a palace landscape to provide a viewing environment. Second, In the 'Purification Period of Changgyeongwon(1954~1977)', environmental purification was carried out to restore amusement facilities, install facilities for cherry blossom viewing, and develop the place into a national zoo. In the 'Reconstruction Period of Changgyeonggung(1983~1986)', restoring function as an urban park, reserving green areas, the outside space was recreated in the traditional feel, and the forest area was generally maintained. In the 'Supplementation Period of Traditional Landscape Architecture Space(1987~2009)', a uniform green landscape was created with pine trees and various vegetation landscapes centered on the flower beds. In the 'Improvement and Maintenance Period of Viewing Environment(2010~2022), a master plan was reestablished on the premise of utilization, but maintenance has been carried out in a small scale centering on unit space. Third, regarding the validity of the landscape restoration and maintenance, It was found in terms of 'originality' that the recovery of the palace system has not been expanded for over 40 years in existing areas. The 'characteristics of the times', which shows whether multi-layered history was taken into account, Changgyeongwon was excluded from the discussion in the process of setting the base year twice. In terms of 'integrity,' the area of the Grand Greenhouse where the historic states coexists needs a maintenance policy that binds the greenhouse, carpet flower bed, and Chundangji Pond. The 'utility' identified as the utilization of spaces suggests the establishment of a sense of place in the Grand Greenhouse area, which is concentrated with programs different from other areas.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.6
• /
• pp.815-824
• /
• 2022

Among the main facilities of the power plant, the circulating water used for cooling the power generation system is supplied through the Circulation Water Intake Basin (CWIB). The vortexes of various types generated in the Pump Sump (PS) of CWIB adversely affect the Circulation Water Pump (CWP) and pipelines. In particular, the free surface vortex accompanied by air intake brings about vibration, noise, cavitation etc. and these are the causes of degradation of CWP performance, damage to pipelines. Then power generation is interrupted by the causes. Therefore, it is necessary to investigate the hydraulic characteristics of CWIB through the hydraulic model experiment and apply an appropriate Anti Vortex Device (AVD) that can control the vortex to enable smooth operation of the power plant. In general, free surface vortex is controlled by Curtain Wall (CW) and the submerged vortex is by the anti vortex device of the curtain wall. The detailed specifications are described in the American National Standard for Pump Intake Design. In this study, the circulating water intake part of the Tripoli West 4×350 MW power plant in Libya was targeted, the actual operating conditions were applied, and the vortex reduction effect of the anti vortex device generated in the suction tank among the circulating water intake part was analyzed through a hydraulic model experiment. In addition, a floor splitter was basically applied to control the submerged vortex, and a new type of column curtain wall was additionally applied to control the vortex generated on the free surface to confirm the effect. As a result of analyzing the hydraulic characteristics by additionally applying the newly developed Column Curtain Wall (CCW) to the existing curtain wall, we have found that the vortex was controlled by forming a uniform flow. In addition, the vortex angle generated in the circulating water pump pipeline was 5° or less, which is the design standard of ANSI/HI 9.8, confirming the stability of the flow.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.50 no.1
• /
• pp.1-19
• /
• 2022

The Geumgang Pine (Pinus densiflora) Forest in Sogwang-ri, Uljin has traditionally been a pine tree protection area (prohibited forest) for timber production purposes, and is now designated and managed as a protected area for forest genetic resource conservation by the Korea Forest Service. This study, we analyzed topographical characteristics, existing vegetation, tree age, and plant community structure, and proposed a sustainable management method for the Geumgang Pine (Pinus densiflora) Forest in Sogwang-ri, Uljin for timber havesting purposes. The topographical characteristics of the target area were 36.7% ridges and 38.7% valleys; the ratio of ridges to valleys was similar, and the slopes formed 24.7% of the total area. The types of pine forest communities are divided into six types based on the progress of pine forest renewal, the competition with other species such as deciduous broadleaf trees, and the formation of layered structures. It has been confirmed that the age of the large-diameter pine trees (40~60cm in diameter) is approximately 60~70 years, which is relatively low. As a result of the analysis of the relative importance percentage and layered structure, differences depended on the progress of the pine forest renewal project, and not only the maintenance of the pine forest, but also the creation of a secondary growth forest, the density adjustment of pine trees, and the active management of competitive trees. The average basal area by the community was 12,642.1~25,424.4cm² for the tree layer and 1.8~1,956.5cm² for the low tree layer based on a quadrat of 400m². The difference in the basal area appeared to depend on the size and number of trees forming the tree layer and the degree of pine forest renewal (the degree of time elapsed after thinning pine trees). The average number of species that appeared in each community was 8.7-20.3; there were many species located in valleys, and the type competes with deciduous broadleaf trees due to the lack of management. The diversity of species ranged from 0.6915-1.0942, and was evaluated as low compared to pine communities in central temperate zones. In this paper, we determined the management goals of Geumgang Pine (Pinus densiflora) Forest in Sogwang-ri, Uljin to produce timber with high economic value, and suggested efficient vegetation management for continuous afforestation, the establishment of a timber production system, and improvement of wood production as a management direction.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.157-177
• /
• 2022

Investors are trading stocks by keeping a close watch on the order information submitted by domestic and foreign investors in real time through Limit Order Book information, so-called price current provided by securities firms. Will order information released in the Limit Order Book be useful in stock price prediction? This study analyzes whether it is significant as a predictor of future stock price up or down when order imbalances appear as investors' buying and selling orders are concentrated to one side during intra-day trading time. Using classification algorithms, this study improved the prediction accuracy of the order imbalance information on the short-term price up and down trend, that is the closing price up and down of the day. Day trading strategies are proposed using the predicted price trends of the classification algorithms and the trading performances are analyzed through empirical analysis. The 5-minute KOSPI200 Index Futures data were analyzed for 4,564 days from January 19, 2004 to June 30, 2022. The results of the empirical analysis are as follows. First, order imbalance information has a significant impact on the current stock prices. Second, the order imbalance information observed in the early morning has a significant forecasting power on the price trends from the early morning to the market closing time. Third, the Support Vector Machines algorithm showed the highest prediction accuracy on the day's closing price trends using the order imbalance information at 54.1%. Fourth, the order imbalance information measured at an early time of day had higher prediction accuracy than the order imbalance information measured at a later time of day. Fifth, the trading performances of the day trading strategies using the prediction results of the classification algorithms on the price up and down trends were higher than that of the benchmark trading strategy. Sixth, except for the K-Nearest Neighbor algorithm, all investment performances using the classification algorithms showed average higher total profits than that of the benchmark strategy. Seventh, the trading performances using the predictive results of the Logical Regression, Random Forest, Support Vector Machines, and XGBoost algorithms showed higher results than the benchmark strategy in the Sharpe Ratio, which evaluates both profitability and risk. This study has an academic difference from existing studies in that it documented the economic value of the total buy & sell order volume information among the Limit Order Book information. The empirical results of this study are also valuable to the market participants from a trading perspective. In future studies, it is necessary to improve the performance of the trading strategy using more accurate price prediction results by expanding to deep learning models which are actively being studied for predicting stock prices recently.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.251-273
• /
• 2022

Recently, research on applying text analysis to deep learning has steadily continued. In particular, researches have been actively conducted to understand the meaning of words and perform tasks such as summarization and sentiment classification through a pre-trained language model that learns large datasets. However, existing pre-trained language models show limitations in that they do not understand specific domains well. Therefore, in recent years, the flow of research has shifted toward creating a language model specialized for a particular domain. Domain-specific pre-trained language models allow the model to understand the knowledge of a particular domain better and reveal performance improvements on various tasks in the field. However, domain-specific further pre-training is expensive to acquire corpus data of the target domain. Furthermore, many cases have reported that performance improvement after further pre-training is insignificant in some domains. As such, it is difficult to decide to develop a domain-specific pre-trained language model, while it is not clear whether the performance will be improved dramatically. In this paper, we present a way to proactively check the expected performance improvement by further pre-training in a domain before actually performing further pre-training. Specifically, after selecting three domains, we measured the increase in classification accuracy through further pre-training in each domain. We also developed and presented new indicators to estimate the specificity of the domain based on the normalized frequency of the keywords used in each domain. Finally, we conducted classification using a pre-trained language model and a domain-specific pre-trained language model of three domains. As a result, we confirmed that the higher the domain specificity index, the higher the performance improvement through further pre-training.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.35-43
• /
• 2023

The purpose of this study is to research digital twin policies for the use of administrative services. The study was conducted through a mobile survey of 1,000 participants, and the results are as follows. First, in order to utilize digital twin technology, it is necessary to first identify appropriate services that can be applied from the perspective of Gyeonggi Province. Efforts to identify digital twin services that are suitable for Gyeonggi Province's field work should be prioritized, and this should lead to increased efficiency in the work. Second, Gyeonggi Province's digital twin administrative services should prevent duplication with central government projects and establish a model that can be connected and utilized. It should be driven around current issues in Gyeonggi Province and the demands of citizens for administrative services. Third, to develop Gyeonggi Province's digital twin administrative services, a standard model development plan through participation in pilot projects should be considered. Gyeonggi Province should lead the project as the main agency and promote it through a collaborative project agreement. It is suggested that a support system for the overall project be established through the Gyeonggi Province Digital Twin Advisory Committee. Fourth, relevant regulations and systems for the construction, operation, and management of dedicated departments and administrative services should be established. To achieve the realization of digital twins in Gyeonggi Province, a dedicated organization that can perform various roles in project promotion and operation, as well as legal and institutional improvements, is necessary. To designate a dedicated organization, it is necessary to consider expanding and reorganizing existing departments and evaluating the operation of newly established departments. The limitation of this study is that it only surveyed participants from Gyeonggi Province, and it is recommended that future research be conducted nationwide. The expected effect of this study is that it can serve as a foundational resource for applying digital twin services to public work.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.131-154
• /
• 2022

Recently, researches on unstructured data analysis have been actively conducted with the development of information and communication technology. In particular, topic modeling is a representative technique for discovering core topics from massive text data. In the early stages of topic modeling, most studies focused only on topic discovery. As the topic modeling field matured, studies on the change of the topic according to the change of time began to be carried out. Accordingly, interest in dynamic topic modeling that handle changes in keywords constituting the topic is also increasing. Dynamic topic modeling identifies major topics from the data of the initial period and manages the change and flow of topics in a way that utilizes topic information of the previous period to derive further topics in subsequent periods. However, it is very difficult to understand and interpret the results of dynamic topic modeling. The results of traditional dynamic topic modeling simply reveal changes in keywords and their rankings. However, this information is insufficient to represent how the meaning of the topic has changed. Therefore, in this study, we propose a method to visualize topics by period by reflecting the meaning of keywords in each topic. In addition, we propose a method that can intuitively interpret changes in topics and relationships between or among topics. The detailed method of visualizing topics by period is as follows. In the first step, dynamic topic modeling is implemented to derive the top keywords of each period and their weight from text data. In the second step, we derive vectors of top keywords of each topic from the pre-trained word embedding model. Then, we perform dimension reduction for the extracted vectors. Then, we formulate a semantic vector of each topic by calculating weight sum of keywords in each vector using topic weight of each keyword. In the third step, we visualize the semantic vector of each topic using matplotlib, and analyze the relationship between or among the topics based on the visualized result. The change of topic can be interpreted in the following manners. From the result of dynamic topic modeling, we identify rising top 5 keywords and descending top 5 keywords for each period to show the change of the topic. Existing many topic visualization studies usually visualize keywords of each topic, but our approach proposed in this study differs from previous studies in that it attempts to visualize each topic itself. To evaluate the practical applicability of the proposed methodology, we performed an experiment on 1,847 abstracts of artificial intelligence-related papers. The experiment was performed by dividing abstracts of artificial intelligence-related papers into three periods (2016-2017, 2018-2019, 2020-2021). We selected seven topics based on the consistency score, and utilized the pre-trained word embedding model of Word2vec trained with 'Wikipedia', an Internet encyclopedia. Based on the proposed methodology, we generated a semantic vector for each topic. Through this, by reflecting the meaning of keywords, we visualized and interpreted the themes by period. Through these experiments, we confirmed that the rising and descending of the topic weight of a keyword can be usefully used to interpret the semantic change of the corresponding topic and to grasp the relationship among topics. In this study, to overcome the limitations of dynamic topic modeling results, we used word embedding and dimension reduction techniques to visualize topics by era. The results of this study are meaningful in that they broadened the scope of topic understanding through the visualization of dynamic topic modeling results. In addition, the academic contribution can be acknowledged in that it laid the foundation for follow-up studies using various word embeddings and dimensionality reduction techniques to improve the performance of the proposed methodology.

• Journal of Popular Narrative
• /
• v.25 no.1
• /
• pp.349-392
• /
• 2019

In the 1960s of Korea, the normalization of diplomatic relations between Korea and Japan led to a sense of a vigorous anxiety and fear that "Japan will once again come to the Korean peninsula". As a reaction to this, the discourse on the criticism of 'Japanese Style' strongly emerged. If the prior discourse of criticism was to express the national antipathy toward the colonial remnants that had not yet been disposed of, the critical discourse of the 1960s was the wariness of the newly created 'Japanese Style' in popular culture, and to grasp it as a symptomatic phenomenon that 'evil-minded Japan' was revealed. Thus, this new logic of criticism of the 'Japanese Style' had a qualitative difference from the existing ones. It was accompanied by a willingness to inspect and censor the 'masses' that grew up as consumers of transnational 'mass culture' that flowed and chained in the geopolitical order under the Cold War system. Therefore, the topology of 'popular things=Japanese things=consuming things' reveals the paradox of moral demands that existed within Korean society in the 1960s. This was to solidify the divisive circulation structure that caused them to avoid direct contact with the other called 'Japan', but at the same time, get as close to it as ever. It is a repetitive obsession that pushes the other to another side through the moral segregation that strictly draws a line of demarcation between oneself and the other, but on the other hand is attracted to the object and pulls it back to its side. This paper intends to listen to the different voices that have arisen in the repetitive obsession to understand the significance of the dissonance that has been repeated in the contemporary era. This will be an examination of the paradoxical object of Japan that has been repeatedly asked to build the internal control principle of Korean society, or to hide the oppressive and violent side of the power, and that can neither be accepted nor destroyed completely as part of oneself.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.171-187
• /
• 2023

When a person's face is recognized through a recording device such as a low-pixel surveillance camera, it is difficult to capture the face due to low image quality. In situations where it is difficult to recognize a person's face, problems such as not being able to identify a criminal suspect or a missing person may occur. Existing studies on face recognition used refined datasets, so the performance could not be measured in various environments. Therefore, to solve the problem of poor face recognition performance in low-quality images, this paper proposes a method to generate high-quality images by performing image quality improvement on low-quality facial images considering various environments, and then improve the performance of facial feature point detection. To confirm the practical applicability of the proposed architecture, an experiment was conducted by selecting a data set in which people appear relatively small in the entire image. In addition, by choosing a facial image dataset considering the mask-wearing situation, the possibility of expanding to real problems was explored. As a result of measuring the performance of the feature point detection model by improving the image quality of the face image, it was confirmed that the face detection after improvement was enhanced by an average of 3.47 times in the case of images without a mask and 9.92 times in the case of wearing a mask. It was confirmed that the RMSE for facial feature points decreased by an average of 8.49 times when wearing a mask and by an average of 2.02 times when not wearing a mask. Therefore, it was possible to verify the applicability of the proposed method by increasing the recognition rate for facial images captured in low quality through image quality improvement.