• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.11-20
• /
• 2024

This study presents TabNet, a novel deep learning method, to enhance corporate credit rating accuracy amidst growing financial market uncertainties due to technological advancements. By analyzing data from major Korean stock markets, the research constructs a credit rating prediction model using TabNet. Comparing it with traditional machine learning, TabNet proves superior, achieving a Precision of 0.884 and an F1 score of 0.895. It notably reduces misclassification of high-risk companies as low-risk, emphasizing its potential as a vital tool for financial institutions in credit risk management and decision-making.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.1-9
• /
• 2020

The study was conducted with funding from the government (Ministry of Agriculture, Food and Rural Affairs) in 2018 with support from the Agricultural, Food, and Rural Affairs Agency, 318069-03-HD040, and in based on artificial intelligence-based HPAI spread analysis and patterning. The model that is actively used in time series and text mining recently is LSTM (Long Short-Term Memory Models) model utilizing deep learning model structure. The LSTM model is a model that emerged to resolve the Long-Term Dependency Problem that occurs during the Backpropagation Through Time (BPTT) process of RNN. LSTM models have resolved the problem of forecasting very well using variable sequence data, and are still widely used.In this paper study, we used the data of the Call Detailed Record (CDR) provided by KT to identify the migration path of people who are expected to be closely related to the virus. Introduce the results of predicting the path of movement by learning the LSTM model using the path of the person concerned. The results of this study could be used to predict the route of HPAI propagation and to select routes or areas to focus on quarantine and to reduce HPAI spread.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.1
• /
• pp.1-8
• /
• 2016

In the recently, violent crime and accidental crime has been generated continuously. Consequently, people anxiety has been heightened. The Closed Circuit Television (CCTV) has been used to ensure the security and evidence for the crimes. However, the video captured from CCTV has being used in the post-processing to apply to the evidence. In this paper, we propose a flexible multi-level models for estimating whether dangerous behavior and the environment and context for pedestrians. The situation analysis builds the knowledge for the pedestrians tracking. Finally, the decision step decides and notifies the threat situation when the behavior observed object is determined to abnormal behavior. Thereby, tracking the behavior of objects in a multi-region, it can be seen that the risk of the object behavior. It can be predicted by the behavior prediction of crime.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.60-60
• /
• 2020

기후변화 및 지구온난화로 인한 자연재해 규모가 점차 대형화, 다양화되고 있어 이로 인한 피해도 증대되고 있다. 특히, 다양한 시설과 인구밀도가 높은 도심 지역은 집중호우, 태풍, 홍수 등 자연재해에 취약하여 인적·물적 피해 위험성이 매우 높다. 방재 시설확보 및 개선을 통한 더 높은 안정성 및 기상예보를 통한 대응, 대책을 통한 피해 저감이 이루어지고 있다. 그러나 일반적으로 제공되는 단일 수치모형 기반의 결정론적 기상예측정보는 기상 상태, 선행시간, 모형 매개변수 등으로 인한 불확실성이 매우 크며 이에 대한 정보가 제공되지 않다. 이러한 문제점을 보완하기 위해 앙상블 수치모델 정보와 기상레이더 자료 기반의 단기 예측정보가 활용이 가능하다. 그러나, 앙상블 수치모델의 불확실성, 기상레이더 기반 예측정보의 짧은 예측 선행시간으로 인해 수문학적 모형에 입력자료로 활용은 어려운 실점이다. 본 연구에서는 지점 관측자료의 시간적 연속성, 기상레이더 자료의 공간적 연속성, 앙상블 예측정보의 선행시간 정보를 융합하여 기상예측정보에 대한 불확실성 개선 및 선행시간에 따른 정확도를 높일 방법을 제안하였다. 기상청에서 제공하는 앙상블 예측자료인 LENS 자료, 레이더 강수량, ASOS 관측자료 기반으로 분석이 수행되었으며 분석결과는 예측강수량을 활용하는 분야에 긍정적 영향을 미칠 것으로 기대된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.137-138
• /
• 2016

본 연구에서는 기술수용모델과 혁신확산이론을 기반으로 스마트폰 혁신기술 저항에 관한 재사용 의도에 미치는 영향을 알아보고자 한다. 외부변수는 기술수용모델의 인지된 유용성과 인지된 사용 용이성 그리고 혁신확산이론의 적합성과 복잡성을 4개 변수를 두고자 한다. 예측변수는 혁신저항 변수를 두고 재사용의도에 미치는 영향으로 하여 개념모델을 완성하였다. 또한 혁신저항 변수가 인지된 위험 요인을 매개하여 재사용의도에 미치는 영향을 알아보고자 하였다. 연구대상은 부산 경남지역 및 전북지역에 거주하는 스마트폰 사용자를 대상으로 설문을 통해 자료를 수집하고자 한다. 인구통계학인 분석은 IBM SPSS Statistics 19로 하고 확인적 요인분석과 변수들 간의 인과관계에 대한 경로분석은 Smart PLS를 사용하여 분석하고자 한다. 분석결과를 바탕으로 이론적 실무적 시사점을 제시하고자 한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.427-427
• /
• 2018

최근 집중호우나 극한 강우사상으로 인하여 산사태나 토석류와 같은 산지재해가 빈번하게 발생하고 있으며 특히 우리나라는 지형 특성상 주거지역이 산지와 인접해 있는 경우가 많아 재해발생 시 피해를 가중시키는 원인이 되고 있다. 산지재해는 예측하기가 어렵고 산지에서 발생한 토석류가 계곡을 따라 흘러 내려와 도심지 및 산지와 인접한 도로나 주택지에 많은 피해를 발생 시키고 있다. 본 연구에서는 해마다 반복적으로 발생하고 있는 산사태나 토석류와 같은 재해의 피해저감과 원인분석을 위하여 강원도 삼척시 도계읍 일대를 대상지역으로 선정하고 산지유역의 위험성 분석을 위하여 사면안정성 예측 모델인 SINMAP 모형을 사용하여 산지재해가 발생 가능한 위험지역 및 안전한 구간을 분석하고 지형분류기법 중의 하나인 Topographic Position Index(TPI) 분석방법을 통해 대상지역의 지형위치지수를 계산하여 위험지형을 분류하였다.

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.685-692
• /
• 2018

The purpose of this study is to develop a prediction model of hypertension in middle-aged adults using Statistical analysis. Statistical analysis and prediction models were developed using the National Health and Nutrition Survey (2013-2016).Binary logistic regression analysis showed statistically significant risk factors for hypertension, and a predictive model was developed using logistic regression and the Naive Bayes algorithm using Wrapper approach technique. In the statistical analysis, WHtR(p<0.0001, OR = 2.0242) in men and AGE (p<0.0001, OR = 3.9185) in women were the most related factors to hypertension. In the performance evaluation of the prediction model, the logistic regression model showed the best predictive power in men (AUC = 0.782) and women (AUC = 0.858). Our findings provide important information for developing large-scale screening tools for hypertension and can be used as the basis for hypertension research.

• Proceedings of the KAIS Fall Conference
• /
• 2012.05b
• /
• pp.812-816
• /
• 2012

본 논문은 산사태 감지 및 붕괴예측을 위한 현장에 USN(Ubiquitous Sensor Network)을 적용한 실시간 모니터링 시스템 모델을 개발하였다. 이 시스템의 성능을 검증하기 위해 USN기반의 상시모니터링시스템모델을 제작하고 실험적 평가를 수행하였다. 성능평가는 지표변위 센서모듈 동작특성 실험적 평가, USN은 Data 수집 전송 효율성 실험적 평가, 개발한 상시감시모니터링 프로그램 동작성능 실험적 평가 등을 수행하였다. 성능평가 결과 지표변위 측정센서모듈은 변위각도에 일치성을 확인하고, USN은 지표변위 센서모듈로부터 측정된 Data를 상시모니터링시스템에 오류 없이 전송되는지를 확인하였으며, 개발한 상시모니터링 프로그램 동작기능은 실시간 모니터링 그래프, 임계동작 알고리즘, 위험성 통보 문자서비스(SMS)기능, 알람서비스기능, 현장 감시카메라 등 동작기능의 우수성을 실험으로 증명하였다. 따라서 본 연구에서 개발된 산사태 감지 예측을 위한 USN기반 실시간 모니터링 시스템 모델은 산사태위험성노출 지역에 원격 실시간 모니터링 시스템으로 널리 사용될 것으로 사료된다.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.5
• /
• pp.527-534
• /
• 2019

Several types of mathematical analysis methods are used for port waterway risk assessment based on marine traffic volume. In Korea, a marine traffic congestion model that standardizes the size of the vessels passing through the port waterway is applied to evaluate the risk of the waterway. For example, when marine traffic congestion is high, risk situations such as collisions are likely to occur. However, a scientific review is required to determine if there is a correlation between high density of maritime traffic and a high risk of waterway incidents. In this study, IWRAP Mk2(IALA official recommendation evaluation model) and a marine traffic congestion model were used to analyze the correlation between port waterway risk and marine traffic congestion in the same area. As a result, the linear function of R2 was calculated as 0.943 and it was determined to be significant. The Pearson correlation coefficient was calculated as 0.971, indicating a strong positive correlation. It was confirmed that the port waterway risk and the marine traffic congestion have a strong correlation due to the influence of the common input variables of each model. It is expected that these results will be used in the development of advanced models for the prediction of port waterway risk assessment.