• The Journal of Information Systems
• /
• v.30 no.1
• /
• pp.65-84
• /
• 2021

Purpose Based on the development of artificial intelligence and big data technologies, the RegTech has been emerged to reduce regulatory costs and to enable efficient supervision by regulatory bodies. The word RegTech is a combination of regulation and technology, which means using the technological methods to facilitate the implementation of regulations and to make efficient surveillance and supervision of regulations. The purpose of this study is to describe the recent adoption of RegTech and to provide basic examples of applying RegTech to capital market regulations. Design/methodology/approach English-based ontology and deep learning technologies are quite developed in practice, and it will not be difficult to expand it to European or Latin American languages that are grammatically similar to English. However, it is not easy to use it in most Asian languages such as Korean, which have different grammatical rules. In addition, in the early stages of adoption, companies, financial institutions and regulators will not be familiar with this machine-based reporting system. There is a need to establish an ecosystem which facilitates the adoption of RegTech by consulting and supporting the stakeholders. In this paper, we provide a simple example that shows a procedure of applying RegTech to recognize and interpret Korean language-based capital market regulations. Specifically, we present the process of converting sentences in regulations into a meta-language through the morpheme analyses. We next conduct deep learning analyses to determine whether a regulatory sentence exists in each regulatory paragraph. Findings This study illustrates the applicability of RegTech-based ontology and deep learning technologies in Korean-based capital market regulations.

• The Journal of Korean Philosophical History
• /
• no.43
• /
• pp.295-317
• /
• 2014

This is the issue of this paper: What was the reason for Daoxuejia(道學家) in Song Dynasty to interpret 'ke-ji(克己)' as 'removing private desire'? 'ke-ji-fu-li'(克 己復禮)' is a phrase presented by Confucius as a way of practicing Ren(仁). The interpretations of Ren(仁) concept by Daoxuejia(道學家) have been reviewed. They interpreted Ren(仁) as Tian-li(天理) and thought its contents as 'Tian-di-shengwu-zhi-xin(天地生物之心)'. Zhu xi(朱熹) associated the concepts of sheng-sheng (生生), Xu(虛), Rou(柔), etc. and provided philosophic explanations on the interpretation of Ren(仁) raised newly by Ercheng(二程) and the interpretation of 'ke-ji-fu-li' (克己復禮). It is fact that Zhu xi criticized ardently Daoism but did not think nothing was worth taking from it. The stands of Daoxuejia(道學家) scholars in Song Dynasty on "removing private desire(去私欲)" presented in this paper could be the grounds supported such opinion.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1193-1204
• /
• 2021

In information security, AI technology is used to detect unknown malware. Although AI technology guarantees high accuracy, it inevitably entails false positives, so we are considering introducing XAI to interpret the results predicted by AI. However, XAI evaluation studies that evaluate or verify the interpretation only provide simple interpretation results are lacking. XAI evaluation is essential to ensure safety which technique is more accurate. In this paper, we interpret AI results as features that have significantly contributed to AI prediction in the field of malware, and present an evaluation method for the interpretation of AI results. Interpretation of results is performed using two XAI techniques on a tree-based AI model with an accuracy of about 94%, and interpretation of AI results is evaluated by analyzing descriptive accuracy and sparsity. As a result of the experiment, it was confirmed that the AI result interpretation was properly calculated. In the future, it is expected that the adoption and utilization of XAI will gradually increase due to XAI evaluation, and the reliability and transparency of AI will be greatly improved.

• Education of Primary School Mathematics
• /
• v.24 no.2
• /
• pp.83-102
• /
• 2021

Curricular noticing is about how teachers understand the content and pedagogical opportunities inherent in curriculum materials. Since the enacted curriculum differs depending on which aspect of the curriculum material is paid attention to and how to interpret it, it is necessary to focus on Curricular Attending and Curricular Interpreting in Curricular Noticing for enhancing the teaching expertise of preservice teachers. First, this study categorized the objects that preservice elementary mathematics teachers attended when planning the lesson for rate. Second, in order to find out the reason for paying attention to those objects, it was analyzed what factors were related to interpret. By discussing the results, implications were drawn on how to use Curricular Noticing in preservice teacher education to enhance the pedagogical design competency of preservice elementary mathematics teachers.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1784-1789
• /
• 2021

Korean sentiment classification task is used in real-world services such as chatbots and analysis of user's purchase reviews. And due to the development of deep learning technology, neural network models with high performance are being applied. However, the neural network model is not easy to interpret what the input sentences are predicting due to which words, and recently, model interpretation methods for interpreting these neural network models have been popularly proposed. In this paper, we used the LIME algorithm among the model interpretation methods to interpret which of the words in the input sentences of the models learned with the korean sentiment classification dataset. As a result, the interpretation of the Bi-LSTM model with 85.24% performance included 25,283 words, but 84.20% of the transformer model with relatively low performance showed that the transformer model was more reliable than the Bi-LSTM model because it contains 26,447 words.

• Journal of Conservation Science
• /
• v.38 no.4
• /
• pp.347-359
• /
• 2022

Gongsanseong Fortress was registered of a World Heritage Site in 2015 as a representative cultural heritage from the Woongjin Baekje period, and it has been used throughout the entire period from Baekje Kingdom to the Joseon Dynasty. Within Gongsanseong Fortress, the area around Ssangsujeong is presumed the site of royal palace of the Woongjin Baekje. Also, the excavated culture layers of the Baekje Kingdom, the Unified Silla period, and the Joseon Dynasty were confirmed. In this study, paleotopography was modeled by digitally converting the elevation data obtained through surveying the excavation process, and the use of the topography in the Ssangsujeong area was considered by examining the variations in the topography according to the periods. As a result, the topography of the slope around the peak changed by periods, and the topography did not change on the flat land. The topography between the Baekje Kingdom and the Unified Silla period appeared to be almost identical, and it seems that the space of the Baekje period was maintained as it is. Also, during the Joseon Dynasty, it is confirmed that flat surfaces in the previous period were used. However, sediments on the slopes flowed down, reducing the area of the flatland, and architectural techniques that could utilize the natural topography of the changed slope were applied to interpret it as having a different topography from the previous period. In order to model and interpret the paleotopography, excavation data, geological and topographic analysis, and digital data must be secured. It is expected that location conditions and ancient human life can be identified if the analysis technique in the study is applied to other archaeological sites in the future.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.48-56
• /
• 2022

The importance of data analysis in baseball has been increasing after the success of MLB's Oakland which applied Billy Beane's money ball theory, and the 2020 KBO winner NC Dinos. Various studies using data in baseball has been conducted not only in the United States but also in Korea, In particular, the models using deep learning and machine learning has been suggested. However, in the previous studies using deep learning and machine learning, the focus is only on predicting the win or loss of the game, and there is a limitation in that it is difficult to interpret the results of which factors have an important influence on the game. In this paper, to investigate which factors is important by position, the prediction model for the Golden Glove award which is given for the best player by position is developed. To develop the prediction model, XGBoost which is one of boosting method is used, which also provide the feature importance which can be used to interpret the factors for prediction results. From the analysis, the important factors by position are identified.

• Journal of Service Research and Studies
• /
• v.11 no.3
• /
• pp.31-42
• /
• 2021

This study is a study on theoretical considerations on industrial design data in the era of data economy. This study aims to illuminate the value of industrial design data, interpret the meaning of the transition from design management to the design data era, and highlight the importance of literacy to interpret data for designers. The scope of research approaches the R&D capability dimension of a company to explore the industrial value of design. It limits the scope of research from an industrial point of view rather than the humanistic basis and aesthetic value of design. As a result of the study, it was found that the value of industrial design data is not in ex post evaluation, but in customer-oriented market prediction, and that the design industry data-led strategy is important. The key point is that the industrial design data issues of large companies and SMEs are different, the direction of industrial design data should be to support customer-centered decision making in the product/service development of companies, and the core competency is the amount of data or tools and technologies to handle it. No, it should be in data literals. Lastly, if the use of industrial design data is to be strengthened, management of the public level rather than the personal level of data management should be preceded.

• Clinical Endoscopy
• /
• v.55 no.3
• /
• pp.426-433
• /
• 2022

Background/Aims: Cholangiogram interpretation is not used as a key performance indicator (KPI) of endoscopic retrograde cholangiopancreatography (ERCP) training, and national societies recommend different minimum numbers per annum to maintain competence. This study aimed to determine the relationship between correct ERCP cholangiogram interpretation and experience. Methods: One hundred fifty ERCPists were surveyed to appropriately interpret ERCP cholangiographic findings. There were three groups of 50 participants each: "Trainees," "Consultants group 1" (performed >75 ERCPs per year), and "Consultants group 2" (performed >100 ERCPs per year). Results: Trainees was inferior to Consultants groups 1 and 2 in identifying all findings except choledocholithiasis outside the intrahepatic duct on the initial or completion/occlusion cholangiogram. Consultants group 1 was inferior to Consultants group 2 in identifying Strasberg type A bile leaks (odds ratio [OR], 0.86; 95% confidence interval [CI], 0.77-0.96), Strasberg type B (OR, 0.84; 95% CI, 0.74-0.95), and Bismuth type 2 hilar strictures (OR, 0.81; 95% CI, 0.69-0.95). Conclusions: This investigation supports the notion that cholangiogram interpretation improves with increased annual ERCP case volumes. Thus, a higher annual volume of procedures performed may improve the ability to correctly interpret particularly difficult findings. Cholangiogram interpretation, in addition to bile duct cannulation, could be considered as another KPI of ERCP training.

• Applied Microscopy
• /
• v.50
• /
• pp.2.1-2.7
• /
• 2020

Electron energy loss spectroscopy (EELS) is an analytical technique that can provide the structural, physical and chemical information of materials. The EELS spectra can be obtained by combining with TEM at sub-nanometer spatial resolution. However, EELS spectral information can't be obtained easily because in order to interpret EELS spectra, we need to refer to and/or compare many reference data with each other. And in addition to that, we should consider the different experimental variables used to produce each data. Therefore, reliable and easily interpretable EELS standard reference data are needed. Our Electron Energy Loss Data Center (EELDC) has been designated as National Standard Electron Energy Loss Data Center No. 34 to develop EELS standard reference (SR) data and to play a role in dissemination and diffusion of the SR data to users. EELDC has developed and collected EEL SR data for the materials required by major industries and has a total of 82 EEL SR data. Also, we have created an online platform that provides a one-stop-place to help users interpret quickly EELS spectra and get various spectral information. In this paper, we introduce EEL SR data, the homepage of EELDC and how to use them.