• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.

• Journal of International Area Studies (JIAS)
• /
• v.12 no.4
• /
• pp.395-420
• /
• 2009

Academic discourses on Swahili identity have been focused on either its Bantu or Arabic-originated theories. Both theories, nevertheless, have a common feature: a unilineal origin of Swahili identity. This paper questions on this Swahili identity and argues that Swahili identity has been developed through historical experience and discourses. For this, the paper utilizes Barth's theory of situationalism. Barth(1998(1969)) suggests that maintaining an ethnic identity is a personal or group choice out of multiple layers of social identities according to his or their social environments. Tanzanian Swahili identity is a good case for this analysis. Based on fieldwork conducted at Magomeni and Msasani in Dar es Salaam, a capital of Tanzania, the paper shows that residents in both areas hold strong Swahili identities although they have different social and historical experience. In case of Magomeni, most of the residents came from Zanzibar, a core Swahili cultural area. They trace their original genealogy from Arabia peninsular. Besides, they argue that they speak a proper kiSwahili(Swahili language) distinguishable from inland kiSwahili. On the contrary, residents of Msasani show variety of ethnic identities, far from a proper Swahili. They have adapted Swahili identities since the independence of Tanzania. With the help of strong socialist policies, including a language policy, most of Tanzanian ethnic groups have ignored their own identities and accommodated a national identity, Tanzanian(waTanzania) or Swahili people(waSwahili). Makonde immigrants from Mozambique who consists the majority of residents in Msasani also easily accommodate Swahili identity in the course. Therefore, Makonde have began to rebirth as waSwahili by claiming that they are living in Tanzania and speak kiSwahili as a mother tongue.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.3
• /
• pp.321-335
• /
• 2023

Monitoring sediment loads in natural rivers is the key process in river engineering, but it is costly and dangerous. In practice, suspended loads are directly measured, and total loads, which is a summation of suspended loads and bed loads, are estimated. This study proposes a real-time sediment discharge monitoring system using the horizontal acoustic Doppler current profiler (H-ADCP) and support vector regression (SVR). The proposed system is comprised of the SVR model for suspended sediment concentration (SVR-SSC) and for total loads (SVR-Q_TL), respectively. SVR-SSC estimates SSC and SVR-Q_TL mimics the modified Einstein procedure. The grid search with K-fold cross validation (Grid-CV) and the recursive feature elimination (RFE) were employed to determine SVR's hyperparameters and input variables. The two SVR models showed reasonable cross-validation scores (R²) with 0.885 (SVR-SSC) and 0.860 (SVR-Q_TL). During the time-series sediment load monitoring period, we successfully detected various sediment transport phenomena in natural streams, such as hysteresis loops and sensitive sediment fluctuations. The newly proposed sediment monitoring system depends only on the gauged features by H-ADCP without additional assumptions in hydraulic variables (e.g., friction slope and suspended sediment size distribution). This method can be applied to any ADCP-installed discharge monitoring station economically and is expected to enhance temporal resolution in sediment monitoring.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.5 no.4
• /
• pp.45-53
• /
• 2015

In this paper, an approach of temporal certification system that can be easily added on current character-based certification system is newly introduced. This technique enhances the security of the password certification process by exploiting temporal information for each character's stroke timing, and using them as another feature of certification information, on top of character comparison process. There are three different temporal conditions: maximum, minimum and no-option. The maximum condition along with a time number (usually 0.2 second or less) means that the next key input should be punched within the time limit, while the minimum condition means the next key stroke should be typed after the time lapse specified. With no-option condition chosen, user can punch the password without any timing constraints. Prototype was developed and tested with four number password case. In comparison with 104 cases, this new approach increases the cases more than 10 digits, enhancing the security of the certification process. One big advantage of this new approach is that user can update his/her password only with different timing constraints, still keeping the same characters, that will enhance the security system management efficiency in a very simple way. Figures and pictures along with process flow are included for the validity of the idea.

• Korea Trade Review
• /
• v.42 no.1
• /
• pp.257-281
• /
• 2017

It becomes a common feature of business practices in International Trade to use a standard terms for the formation of their contracts. However, because of differences in legal systems, business practices and so on in their own countries, there have been many conflicts and disputes happening between parties concerned in International Trade. The CISG, which has long been used as the governing law in many cases of International Trade, could not be free from those conflicting issues in its usage and application. This study analyzes the "Black Letter Rules" which was adopted by CISG Advisory Council in 2013 to provide an effective way of resolving the conflicting issues regarding the inclusion of standard terms in International Trade Contracts under the CISG. This study scrutinizes, the relevant rules and requirements for the inclusion of standard terms into a contract. It also deals with the offeror's duty of making clear reference to the standard terms, transmitting the contents of standard terms to the other party. As the other rules for the inclusion of standard terms, this study reviews the principle of denying the inclusion of standard terms after the formation of contracts, exclusion of surprising or unusual terms, preference of individually negotiated terms to the standard terms, contra preferentum rule and preference of the "knock-out rule" to "last-shot rule" in resolving the issue of so called, "Battle of Forms." Lastly, on the basis of analyzed opinion, this study suggests the practical implications for the people working at International Trade-related business sector to facilitate International Trade.

• Korea Science and Art Forum
• /
• v.19
• /
• pp.405-415
• /
• 2015

Recently the development of China has attracted all over the world, many scholars of different areas are interested in Chinese Culture and Chinese Market. After sixties of last century development of the economic of the South Korea closer to modernization, but there are many problems, one of them is the urban living style boasts of the features of concentration. Because of this phenomenon the lack of housing space become more serious. It also come to be a social problems. Therefore narrow residential area become inevitability. At the same time, effective utilization of housing space become a demand. Especially for those families with limited living space, it's meaningful for them. Between the China and the South Korea. Chinese have the same situation too, the different is kitchen space of chinese is closed. It means they have to cook in limited space. With increased supplies and more small appliances, an inevitable requirement is opening out the kitchen space, but unreasonable furnishings and living space reduces the efficiency of the kitchen, which has led to the discontent of users. From this, base on the investigation and analysis of diet&living space of most chinese apartment, and through differences kinds and places of storage items. With them I would combine the food culture and feature of storage space of China to solve problems of the efficiency of the kitchen.

• Journal of Life Science
• /
• v.33 no.6
• /
• pp.490-497
• /
• 2023

Pregnant women may need to take medications to treat preexisting diseases or diseases that develop during pregnancy. However, some drugs may be fetotoxic and lead to, for example, teratogenicity and growth retardation. Predicting the fetotoxicity of drugs is thus important for the health of the mother and fetus. The fetotoxicity of many drugs has not been established because various challenges hinder the ability of researchers to determine their fetotoxicity. The need exists for in silico-based fetotoxicity assessment models, as they can modernize the testing paradigm, improve predictability, and reduce the use of animals and the costs of fetotoxicity testing. In this study, we collected data on the fetotoxicity of drugs and constructed fetotoxicity prediction models based on various machine learning algorithms. We optimized the models for more precise predictions by tuning the hyperparameters. We then performed quantitative performance evaluations. The results indicated that the constructed machine learning-based models had high performance (AUROC >0.85, AUPR >0.9) in fetotoxicity prediction. We also analyzed the feature importance of our model's predictions, which could be leveraged to identify the specific features of drugs that are strongly associated with fetotoxicity. The proposed model can be used to prescreen drugs and drug candidates at a lower cost and in less time. It provides a predictive score for fetotoxicity risk, which may be beneficial in the design of studies on fetotoxicity in human pregnancy.

• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.423-431
• /
• 2023

The purpose of this study is to analyze the factors affecting the classification of the severity of contrast media side effects based on the patient's body information using artificial intelligence techniques to be used as basic data to reduce the degree of contrast medium side effects. The data used in this study were 606 examiners who had no contrast medium side effects in the past history survey among 1,235 cases of contrast medium side effects among 58,000 CT scans performed at a general hospital in Seoul. The total data is 606, of which 70% was used as a training set and the remaining 30% was used as a test set for validation. Age, BMI(Body Mass Index), GFR(Glomerular Filtration Rate), BUN(Blood Urea Nitrogen), GGT(Gamma Glutamyl Transgerase), AST(Aspartate Amino Transferase,), and ALT(Alanine Amiono Transferase) features were used as independent variables, and contrast media severity was used as a target variable. AUC(Area under curve), CA(Classification Accuracy), F1, Precision, and Recall were identified through AdaBoost, Tree, Neural network, SVM, and Random foest algorithm. AdaBoost and Random Forest show the highest evaluation index in the classification prediction algorithm. The largest factors in the predictions of all models were GFR, BMI, and GGT. It was found that the difference in the amount of contrast media injected according to renal filtration function and obesity, and the presence or absence of metabolic syndrome affected the severity of contrast medium side effects.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.431-436
• /
• 2023

The film Aftersun(2022) is Scottish director Charlotte Wells' feature debut and is one of the films that received the most attention in the international art film scene that year. The overall structure of the film is a look back at a certain summer vacation that Sophie, now an adult, went to Turkey with Calum, a 30-year-old 'young dad', whom she lived apart after divorcing her mother when she was 11 years old. In fact, it can be said to be a reconstruction of memory, and Aftersun not only describes the contents remembered, but also reveals the process of reconstructing memories, making the film a process of post-action memory work. In this process, Aftersun proves Lev Manovich's words that cinema is an indexic art. Going back and forth between home video and cinematic diegesis, After Sun unleashes a new imaginary temporality through a two-hour conversation, traces of indexical signs engraved on home video and present times. The film urges involuntary memories in the chaotic time to the present, and makes meaning through traces and signs of intense gestures in the dialogue between media and media, past and present. The We think about the meaning through the time when the story is stopped and the implications of the gestures.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.155-164
• /
• 2023

In this paper, we examine the influence of Environmental, Social, and Governance (ESG)-related content on the success of online crowdfunding proposals. Along with the increasing significance of ESG standards in business, investment proposals incorporating ESG concepts are now commonplace. Due to the ESG trend, conventional wisdom holds that the majority of proposals with ESG concepts will have a higher rate of success. We investigate by analyzing over 9000 online business presentations found in a Kickstarter dataset to determine which characteristics of these proposals led to increased investment. We first utilized lexicon-based measurement and Feature Engineering to determine the relationship between environment and society scores and financial indicators. Next, Logistic Regression is utilized to determine the effect of including environmental and social terms in a project's description on its ability to obtain funding. Contrary to popular belief, our research found that microentrepreneurs were less likely to succeed with proposals that focused on ESG issues. Our research will generate new opportunities for research in the disciplines of information science and crowdfunding by shedding new light on the environment of online micro-entrepreneurship.