• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• Korean Journal of Heritage: History & Science
• /
• v.50 no.2
• /
• pp.94-115
• /
• 2017

'Arirang folk song in the Democratic People's Republic of Korea' was inscribed to the Representative List of the Intangible Cultural Heritage of Humanity in 2014 and 'Tradition of kimchi-making in the Democratic People's Republic of Korea' followed in 2015. It is presumed that North Korea was influenced by the Republic of Korea inscribing 'Arirang, lyrical folk song in the Republic of Korea' to the list in 2012 as well as 'Kimjang, making and sharing kimchi in the Republic of Korea' in 2013. These cases show the necessity (or possibility) of cultural exchanges between the two Koreas through UNESCO ICH lists. The purpose of this article is to explore the possibility of inter-Korean cultural integration. Therefore, I would like to review UNESCO's ICH policy and examine the ways of cooperation and joint nominations to the Representative List of Intangible Cultural Heritage of Humanity between the two Koreas. First, I reviewed the amendments to the laws and regulations of the two Koreas and how the two countries applied the UNESCO Convention for the Safeguarding of the Intangible Cultural Heritage. Although the cultural exchange is a non-political field, given the situation between South and North Korea, it is influenced by politics. Therefore, we devised a stepwise development plan, divided into four phases: infrastructure development, cooperation and promotion, diversification, and policymaking and alternative development. First a target group will be needed. In this regard, joint nominations to the Representative List of the UNESCO Intangible Cultural Heritage of Humanity will be suitable for cooperation. Both countries have already started separate nominations on shared ICH elements to the UNESCO lists. Therefore, I have selected a few elements as examples that can be considered for joint nominations. The selected items are makgeolli (traditional liquor), jang (traditional soybean sauce), gayangju (homebrewed liquor), gudeul (Korean floor heating system), and jasu (traditional embroidery). Cooperation should start with sharing information on ICH elements. A pilot project for joint nomination can be implemented and then a mid-term plan can be established for future implementation. When shared ICH elements are inscribed on UNESCO ICH lists, various activities can be considered as follow-ups, such as institution visits, performances, exhibitions, and joint monitoring of the intangible cultural heritage. Mutual cooperation of the two Koreas' intangible cultural heritage will be a unique example between the divided countries, so its value will be recognized as a symbol of cultural cooperation. In addition, it will be a foundation for cultural integration of the two Koreas, and it will show the value of their unique ICH to the world. At the same time, it will become a good example for joint nominations to the Representative List recommended by UNESCO.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.3
• /
• pp.39-48
• /
• 2019

This research is based on the analysis of in-depth interviews of designers who participated in the design of the Yeonnam-dong section, which was completed in 2016. The case study site has received many domestic and foreign awards and is receiving very positive reviews from actual users. 53 concepts were derived from the open coding of the ground theory methodology. Thirty-four higher categories incorporated the concepts and 18 higher categories that reintegrated them. Later, the six categories of the ground theory were interpreted as the paradigm, and it was determined that the aspects of 'will of client' and 'work efficiency', 'site resources' and 'field manager's specialty' were the categories that had the greatest positive impact on the park construction. The key category of this park's construction was interpreted as "a park-construction model with active empathy and communication." The results of the study and are linked to the following research proposals. First, the need to improve the trust between the client and the landscape designer and the need to improve the customary administrative procedures; second, the importance of the input of landscape experts into the park construction process; third, the importance of all efforts to develop the design; fourth, the importance of on-site circular resources and landscape preservation; and fifth active social participation to increase the opportunity. This study, which seeks to grasp the facts that existed behind the park's construction, which received excellent internal and external evaluations, and has a qualitative, objective and structural interpretation of the social network related to the park's construction, in contrast to the conventional quantitative post-evaluation. It is expected that the administration and system improvements related to landscaping will be further improved through the continuation of in-depth post-evaluation studies.

• Korean Journal of Ecology and Environment
• /
• v.51 no.4
• /
• pp.268-286
• /
• 2018

The eutrophication and algal blooms by harmful cyanobacteria (CyanoHAs) and freshwater redtide (FRT) that severely experiencing in typical regulated weir system of the Nakdong River are one of the most rapidly expanding water quality problems in Korea and worldwide. To compare with the factors of rainfall, hydrology, and dominant algae, this study explored spatiotemporal variability of the major water environmental factors by weekly intervals in eight weir pools of the Nakdong River from January 2013 to July 2017. There was a distinct difference in rainfall distribution between upstream and downstream regions. Outflow discharge using small-scale hydropower generation, overflow and fish-ways accounted for 37.4%, 60.1% and 2.5%, respectively. Excluding the flood season, the outflow was mainly due to the hydropower release through year-round. These have been associated with the drawdown of water level, water exchange rate, and the significant impact on change of dominant algae. The mean concentration (maximum value) of chlorophyll-a was $17.6mg\;m^{-3}$ ($98.2mg\;m^{-3}$) in the SAJ~GAJ and $29.6mg\;m^{-3}$ ($193.6mg\;m^{-3}$) in the DAS~HAA weir pools reaches, respectively. It has increased significantly in the downstream part where the influence of treated wastewater effluents (TWEs) is high. Indeed, very high values (>50 or $>100mg\;m^{-3}$) of chlorophyll-a concentration were observed at low flow rates and water levels. Algal assemblages that caused the blooms of CyanoHAs and FRT were the cyanobacteria Microcystis and the diatom Stephanodiscus populations, respectively. In conclusion, appropriate hydrological management practices in terms of each weir pool may need to be developed.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.14 no.3
• /
• pp.73-84
• /
• 2019

Despite decades of work experience, workers at small- and medium-sized enterprises(SME) here have yet to make inroads into the self-employed sector that utilizes the job competency they have accumulated at work after retirement. Unlike large companies, SME do not have a proper system for improving the long-term job competency of their employees as they focus on their immediate performance. It is necessary to analyse the independent variables affecting the job competency of employees of SME to derive practical implications for the personnel of SME. In the preceding studies, there are independent variable analyses that affect job competency in specialized industries, such as health care, public officials and IT, but the analysis of workers at SME is insufficient. This study set the person-job fit and organizational justice based on the prior studies of the independent variables that affect the job competency of SME general workers as a dependent variable. The sub-variables of each variable derived knowledge, skills, experience, and desire for person-job fit, and distribution, procedural and deployment justice for organizational justice, respectively. The survey of employees of SME in Korea was conducted from February to March 2019 by Likert 5 scales, and the survey was retrieved from 323 people and analyzed in a demonstration using the SPSS and AMOS statistics package. Among the four sub-independent variables of person-job fit, knowledge, skills and experience were shown to have a significant impact on the job competency, and desire was not shown to be so. Among the three sub-independent variables of organizational justice, deployment justice has a significant impact on job competency, but distribution and procedural justices have not. Personnel managers of SME need to improve the job competency of their employees by appropriately utilizing independent variables such as knowledge, skills, experience and deployment at each stage, including recruitment, deployment, and promotion. Future job competency modeling studies are needed to overcome the limitations of this study, which fails to objectively measure job competency.

• The Korean Journal of Archival Studies
• /
• no.28
• /
• pp.35-81
• /
• 2011

Manhwa is a mass media (to expose all faces of an era such as politics, society, cultures, etc with the methodology of irony, parody, etc). Since the Manhwa records is primary culture infrastructure, it can create the high value-added industry by connecting with fancy, character, game, movie, drama, theme park, advertising business. However, due to lack of active and systematic aquisition system, as precious Manhwa manuscript is being lost every year and the contents hard to preserve such as Manhwa content in the form of electronic records are increasing, the countermeasure of Manhwa contents management is needed desperately. In this study, based on these perceptions, the need of Manhwa records management is examined, and the characteristics and the components of Manhwa records were analyzed. And at the same time, the functions of record management process reflecting the characteristics of Manhwa records were extracted by analyzing various cases of overseas Cartoon Archives. And then, the framework of record-keeping regime was segmented into each of acquisition management service areas and the general Manhwa records archiving strategy, which manages the Manhwa contents records, was established and suggested. The acquired Manhwa content records will secure the context among records and warrant the preservation of records and provide diverse access points by reflecting multi classification and multi-level descriptive element. The Manhwa records completed the intellectual arrangement will be preserved after the conservation in an environment equipped with preservation facilities or preserved using digital format in case of electronic records or when there is potential risk of damaging the records. Since the purpose of the Manhwa records is to use them, the information may be provided to diverse classes of users through the exhibition, the distribution, and the development of archival information content. Since the term of "Manhwa records" is unfamiliar yet and almost no study has been conducted in the perspective of records management, it will be the limit of this study only presenting acquisition strategy, management and service strategy of Manhwa contents and suggesting simple examples. However, if Manhwa records management strategy are possibly introduced practically to Manhwa manuscript repositories through archival approach, it will allow systematic acquisition, preservation, arrangement of Manhwa records and will contribute greatly to form a foundation for future Korean culture contents management.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.10
• /
• pp.261-268
• /
• 2021

Cloud computing is a computing paradigm in which users can utilize computing resources in a pay-as-you-go manner. In a cloud system, resources can be dynamically scaled up and down to the user's on-demand so that the total cost of ownership can be reduced. The Modeling and Simulation (M&S) technology is a renowned simulation-based method to obtain engineering analysis and results through CAE software without actual experimental action. In general, M&S technology is utilized in Finite Element Analysis (FEA), Computational Fluid Dynamics (CFD), Multibody dynamics (MBD), and optimization fields. The work procedure through M&S is divided into pre-processing, analysis, and post-processing steps. The pre/post-processing are GPU-intensive job that consists of 3D modeling jobs via CAE software, whereas analysis is CPU or GPU intensive. Because a general-purpose desktop needs plenty of time to analyze complicated 3D models, CAE software requires a high-end CPU and GPU-based workstation that can work fluently. In other words, for executing M&S, it is absolutely required to utilize high-performance computing resources. To mitigate the cost issue from equipping such tremendous computing resources, we propose HEMOS-Cloud service, an integrated cloud and cluster computing environment. The HEMOS-Cloud service provides CAE software and computing resources to users who want to experience M&S in business sectors or academics. In this paper, the economic ripple effect of HEMOS-Cloud service was analyzed by using industry-related analysis. The estimated results of using the experts-guided coefficients are the production inducement effect of KRW 7.4 billion, the value-added effect of KRW 4.1 billion, and the employment-inducing effect of 50 persons per KRW 1 billion.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.39 no.3
• /
• pp.33-41
• /
• 2021

This study identified the scale that traditional landscape design has taken up by analyzing a total of 1037 services for design of cultural heritage that had been ordered by the government agencies from 2018 to 2020, and has drawn characteristics of traditional landscape design focusing on major cases. The results are as follows. First, the number of order cases for traditional landscape design has shown differences annually in the services of design of cultural heritage, but the design amount has been found to have the similar average annually, which confirmed that the same level has been maintained each year. It was found that the number of cases of traditional landscape design requiring responsibilities or participations of landscape engineers for 3 years in the entire design had a high proportion of approximately 26%. Second, the traditional landscape design has required professional knowledge and experiences of landscape engineers that could not be replaced by the business operator for design of cultural heritage consisting of architects. The expertise has been shown differently depending on types of construction. First, the topographical design for the work to build a foundation has required understanding of ground shapes and its elevations and professional knowledge on calculation of the amount of the earth work and the remains maintenance technique etc. The plantation design has required basic knowledge on growth characteristics of trees and the environment for growth and understanding of the vegetation landscape of the past. Meanwhile, the design for traditional pavement and traditional landscape structures and facilities has required the expertise on traditional materials that are different from the modern ones and their processing and construction methods. The understanding of changes to water paths and ecosystem, the principles of fluids, and characteristics of each type of fluid was essential for the design for the ecological landscape work including the maintenance of a water system such as rivers etc. As such, the traditional landscape design has a scale accounting for approximately one fourth of the entire cultural heritage design and requires the expertise differentiated from other fields. This improves the provisions of the current law on limiting the actual design, suggesting the need for the establishment of a traditional landscape design company so that all traditional landscape designs can be carried out by landscape engineers.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Food Science and Industry
• /
• v.53 no.1
• /
• pp.2-32
• /
• 2020

In recent years, significant importance has been given to chitooligosaccharides (COS) due to its potent notable biological applications. COS can be derived from chitosan which is commonly produced by partially hydrolyzed products from crustacean shells. In order to produce COS, there are several approaches including chemical and enzymatic methods which are the two most common choices. In this regard, several new methods were intended to be promoted which use the enzymatic hydrolysis with a lower cost and desired properties. Hence, the dual reactor system has gained more attention than other newly developed technologies. Enzymatic hydrolysis derived COS possesses important biological activities such as anticancer, antioxidant, anti-hypersentive, anti-dementia (Altzheimer's disease), anti-diabeties, anti-allergy, anti-inflammatory, etc. Results strongly suggest that properties of COS can be potential materials for nutraceutical, pharmaceutical, and cosmeceutical product development.