• 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 Arthroscopy Society
• /
• v.5 no.2
• /
• pp.74-79
• /
• 2001

Purpose : The purpose of this study is to evaluate the clinical results after arthroscopic PCL reconstruction and to compare the clinical results after arthroscopic PCL reconstruction using BPTB(bone patellar tendon bone) autograft(Group I : 11 cases), Achilles tendon allograft(Group II : 7 cases) and BPTB allograft(Group 111.6 cases). Materials and Methods : We reviewed the result of 24 patients who had been managed with arthroscopic reconstruction using different graft materials such as BPTB autograft, Achilles tendon allograft and BPTB allograft. Twenty-four patients(average age, 37 years) with PCL rupture were retrospectively evaluated more than one year(average, 31 months) after having arthroscopic posterior cruciate ligament reconstruction. The clinical results were evaluated by IKDC ligament standard evaluation form, using $KT-2000^{TM}$ knee ligament arthrometer and also evaluated Lysholm knee scoring scale. Results : The final evaluation was nearly normal in 11 patients($45\%$ in Group I, $43\%$ in Group II, $50\%$ in Group III). The corrected posterior sagging was abnormal(side to side difference more than 6mm) in 8 patients($36\%$ in Group I, $29\%$ in Group II, $33\%$ in Group III). We could not find significant difference among three groups by IKDC scale. Conclusion : Comparing with other reports, our overall results were not satisfactory. And also, we could not find any remarkable difference among the three groups. Further research is necessary to evaluate new surgical approaches as well as improved techniques for capsular and collateral ligament injuries.

• Investigative Magnetic Resonance Imaging
• /
• v.22 no.1
• /
• pp.1-9
• /
• 2018

Purpose: This study was designed to optimize the flip angle (FA) and scan timing of the hepatobiliary phase (HBP) using the 3D T1-weighted, gradient-echo (GRE) imaging with controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA) technique on gadoxetic acid-enhanced 3T liver MR imaging. Materials and Methods: Sixty-two patients who underwent gadoxetic acid-enhanced 3T liver MR imaging were included in this study. Four 3D T1-weighted GRE imaging studies using the CAIPIRINHA technique and FAs of $9^{\circ}$ and $13^{\circ}$ were acquired during HBP at 15 and 20 min after intravenous injection of gadoxetic acid. Two abdominal radiologists, who were blinded to the FA and the timing of image acquisition, assessed the sharpness of liver edge, hepatic vessel clarity, lesion conspicuity, artifact severity, and overall image quality using a five-point scale. Quantitative analysis was performed by another radiologist to estimate the relative liver enhancement (RLE) and the signal-to-noise ratio (SNR). Statistical analyses were performed using the Wilcoxon signed rank test and one-way analysis of variance. Results: The scores of the HBP with an FA of $13^{\circ}$ during the same delayed time were significantly higher than those of the HBP with an FA of $9^{\circ}$ in all the assessment items (P < 0.01). In terms of the delay time, images at the same FA obtained with a 20-min-HBP showed better quality than those obtained with a 15-min-HBP. There was no significant difference in qualitative scores between the 20-min-HBP and the 15-min-HBP images in the non-liver cirrhosis (LC) group except for the hepatic vessel clarity score with $9^{\circ}$ FA. In the quantitative analysis, a statistically significant difference was found in the degree of RLE in the four HBP images (P = 0.012). However, in the subgroup analysis, no significant difference in RLE was found in the four HBP images in either the LC or the non-LC groups. The SNR did not differ significantly in the four HBP images. In the subgroup analysis, 20-min-HBP imaging with a $13^{\circ}$ FA showed the highest SNR value in the LC-group, whereas 15-min-HBP imaging with a $13^{\circ}$ FA showed the best value of SNR in the non-LC group. Conclusion: The use of a moderately high FA improves the image quality and lesion conspicuity on 3D, T1-weighted GRE imaging using the CAIPIRINHA technique on gadoxetic acid, 3T liver MR imaging. In patients with normal liver function, the 15-min-HBP with a $13^{\circ}$ FA represents a feasible option without a significant decrease in image quality.

• Journal of agricultural medicine and community health
• /
• v.35 no.1
• /
• pp.56-66
• /
• 2010

Objectives: The study aimed to explore dental status and denture satisfaction in some rural elderly people. Methods: A total of 546 participants aged over 65 years was surveyed cross-sectionally. The subjects were surveyed with regard to their denture satisfaction by a structured questionnaire. The Wilcoxon or Kruskal-Wallis test was used for analysis. Results: As for respondents' satisfaction for dentures by the Likert scale of 5 score, aesthetic satisfaction (3.73) was highest, followed by general satisfaction (3.56) and masticatory functions satisfaction (3.45). In addition, the educational level, occupation, monthly income, the number of remaining teeth, use of denture variables have statistically significant difference in the denture satisfaction of those elderly people interviewed. Conclusions: The results showed that denture satisfaction in some rural elderly people was different in each categories. Consequently, providing tailor-made oral health education programs for the effective denture management of the elderly people should be needed in order to improve the quality of life of the aged.

• Journal of dental hygiene science
• /
• v.10 no.2
• /
• pp.109-116
• /
• 2010

Objective: The purpose of this study was oral health related quality of life among elderly population in some rural area, Korea. Methods: 546 participants (male 196, female 350) aged more than 65 years (mean $71.4{\pm}4.6\;years$) were surveyed cross-sectionally. All the subjects were examined short-form of Oral Health Impact Profile (OHIP-14) by face to face interview. Categorical responses of strata-adjusted Wilcoxon correlation and Kruskal-Willis test and multiple regression analysis after adjusting for socio-demographic variables were adapted for statistical analysis. Results: 1. As for sub-factors of the quality of living related to oral health, the drop in social ability was 4.61, the drop in mental ability 4.53, the drop in physical ability 3.99, mental inconvenience 3.98, social disadvantages 3.82, physical pains 3.77, and functional division 3.44, on the average. 2. As for the quality of living related to oral health, there were statistically significant differences in functional restrictions by gender, the educational level, and the presence of occupation, in physical pains by gender, the educational level, family members living together. mental inconvenience by gender, the educational level, the presence of occupation. and in the drop in physical ability by gender, the educational level, monthly incomes. There were statistically significant differences in the drop in physical ability by gender, the educational level. in the drop in social ability by the educational level, the presence of occupation, monthly income. and in social inconvenience by age, the presence of occupation, monthly income. 3. There were statistically significant differences in the general quality of living related to oral health by gender, the educational level, the presence of occupation.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.117-137
• /
• 2009

Recently, intelligent traffic information systems have enabled people to forecast traffic conditions before hitting the road. These convenient systems operate on the basis of data reflecting current road and traffic conditions as well as distance-based data between locations. Thanks to the rapid development of ubiquitous computing, tremendous context data have become readily available making vehicle route planning easier than ever. Previous research in relation to optimization of vehicle route planning merely focused on finding the optimal distance between locations. Contexts reflecting the road and traffic conditions were then not seriously treated as a way to resolve the optimal routing problems based on distance-based route planning, because this kind of information does not have much significant impact on traffic routing until a a complex traffic situation arises. Further, it was also not easy to take into full account the traffic contexts for resolving optimal routing problems because predicting the dynamic traffic situations was regarded a daunting task. However, with rapid increase in traffic complexity the importance of developing contexts reflecting data related to moving costs has emerged. Hence, this research proposes a framework designed to resolve an optimal route planning problem by taking full account of additional moving cost such as road traffic cost and weather cost, among others. Recent technological development particularly in the ubiquitous computing environment has facilitated the collection of such data. This framework is based on the contexts of time, traffic, and environment, which addresses the following issues. First, we clarify and classify the diverse contexts that affect a vehicle's velocity and estimates the optimization of moving cost based on dynamic programming that accounts for the context cost according to the variance of contexts. Second, the velocity reduction rate is applied to find the optimal route (shortest path) using the context data on the current traffic condition. The velocity reduction rate infers to the degree of possible velocity including moving vehicles' considerable road and traffic contexts, indicating the statistical or experimental data. Knowledge generated in this papercan be referenced by several organizations which deal with road and traffic data. Third, in experimentation, we evaluate the effectiveness of the proposed context-based optimal route (shortest path) between locations by comparing it to the previously used distance-based shortest path. A vehicles' optimal route might change due to its diverse velocity caused by unexpected but potential dynamic situations depending on the road condition. This study includes such context variables as 'road congestion', 'work', 'accident', and 'weather' which can alter the traffic condition. The contexts can affect moving vehicle's velocity on the road. Since these context variables except for 'weather' are related to road conditions, relevant data were provided by the Korea Expressway Corporation. The 'weather'-related data were attained from the Korea Meteorological Administration. The aware contexts are classified contexts causing reduction of vehicles' velocity which determines the velocity reduction rate. To find the optimal route (shortest path), we introduced the velocity reduction rate in the context for calculating a vehicle's velocity reflecting composite contexts when one event synchronizes with another. We then proposed a context-based optimal route (shortest path) algorithm based on the dynamic programming. The algorithm is composed of three steps. In the first initialization step, departure and destination locations are given, and the path step is initialized as 0. In the second step, moving costs including composite contexts into account between locations on path are estimated using the velocity reduction rate by context as increasing path steps. In the third step, the optimal route (shortest path) is retrieved through back-tracking. In the provided research model, we designed a framework to account for context awareness, moving cost estimation (taking both composite and single contexts into account), and optimal route (shortest path) algorithm (based on dynamic programming). Through illustrative experimentation using the Wilcoxon signed rank test, we proved that context-based route planning is much more effective than distance-based route planning., In addition, we found that the optimal solution (shortest paths) through the distance-based route planning might not be optimized in real situation because road condition is very dynamic and unpredictable while affecting most vehicles' moving costs. For further study, while more information is needed for a more accurate estimation of moving vehicles' costs, this study still stands viable in the applications to reduce moving costs by effective route planning. For instance, it could be applied to deliverers' decision making to enhance their decision satisfaction when they meet unpredictable dynamic situations in moving vehicles on the road. Overall, we conclude that taking into account the contexts as a part of costs is a meaningful and sensible approach to in resolving the optimal route problem.

• Tuberculosis and Respiratory Diseases
• /
• v.51 no.5
• /
• pp.409-415
• /
• 2001

Background : Multidrug-resistant tuberculosis(MDR-TB) in patients is mainly caused by acquired drug resistance. However, a small proportion of MDR-TB is caused by initial drug resistance(IDR), which may be somewhat different from acquired drug resistance. This study analyzed the clinical characteristics of IDR in MDR -TB patients to use the results as basic data in managing the disease. Methods : A retrospective study of 30 IDR cases in MDR-TB patients from Jan. 1995 to Dec. 1998 was performed. In order to analyze the clinical characteristics, the age, sex, family history, duration of negative conversion, number of resistant drugs, treatment regimens, duration of treatment, extent of disease and cavitary lesion on the chest X-ray was examined. In order to analyze the level of improvement, the extent of the disease and cavitary lesion on the chest X-ray, tested by Wilcoxon signed rank sum test, and the disease free interval rate of 1-year and 4-year was examined using the Kaplan-Meier method. Results : The mean age of the patients was 46.6 years and the sex ratio 1:1. Six(20%) patients had a family history. The mean negative conversion of the sputum AFB stain was 2.6 months. The number of resistant drugs was 7.6 and the number of used drugs 3.6. Twenty-three(67%) patients were treated for less than 12months and 28(93%) patients were treated with first-line drugs. The extent of the disease and the cavitary lesion on the chest X-ray improved after treatment(p<.05). Among 13 patients who were followed up for 22.6 months, 2(15%) patients relapsed and the disease free interval rate of I-year and 4-year was 85%. Conclusion: It is recommended that the duration of treatment of IDR in MDR-TB with first-line drugs be 9-12 months even if the extent of disease and cavitary lesion on the chest X-ray improves.

• Journal of Korea Port Economic Association
• /
• v.33 no.2
• /
• pp.53-82
• /
• 2017

The purpose of this study is to show the clustering trend and compare empirical results, as well as to choose the clustering ports for 3 Korean ports (Busan, Incheon, and Gwangyang) by using meta-frontier DEA (Data Envelopment Analysis) and integer models on 38 Asian container ports over the period 2005-2014. The models consider 4 input variables (birth length, depth, total area, and number of cranes) and 1 output variable (container TEU). The main empirical results of the study are as follows. First, the meta-frontier DEA for Chinese seaports identifies as most efficient ports (in decreasing order) Shanghai, Hongkong, Ningbo, Qingdao, and Guangzhou, while efficient Korean seaports are Busan, Incheon, and Gwangyang. Second, the clustering results of the integer model show that the Busan port should cluster with Dubai, Hongkong, Shanghai, Guangzhou, Ningbo, Qingdao, Singapore, and Kaosiung, while Incheon and Gwangyang should cluster with Shahid Rajaee, Haifa, Khor Fakkan, Tanjung Perak, Osaka, Keelong, and Bangkok ports. Third, clustering through the integer model sharply increases the group efficiency of Incheon (401.84%) and Gwangyang (354.25%), but not that of the Busan port. Fourth, the efficiency ranking comparison between the two models before and after the clustering using the Wilcoxon signed-rank test is matched with the average level of group efficiency (57.88 %) and the technology gap ratio (80.93%). The policy implication of this study is that Korean port policy planners should employ meta-frontier DEA, as well as integer models when clustering is needed among Asian container ports for enhancing the efficiency. In addition Korean seaport managers and port authorities should introduce port development and management plans accounting for the reference and clustered seaports after careful analysis.

• Journal of Korean Academy of Nursing
• /
• v.25 no.3
• /
• pp.597-607
• /
• 1995

1960년대 이후 인공호흡기(mechanical ventilator)의 보급과 최근 의료과학의 발달, 간호의 질적 향상의 결과로 저체중출생아를 포함한 고위험 신생아의 생존율이 높아져왔다. 호흡장애증후군(RDS)은 일차적으로 폐포의 완전한 확장을 위해 필요한 계면활성물질(surfactant)의 부족, 미발달된 심폐기능에 의한 병리적 현상으로 저체중아의 가장 큰 원인이 되어왔다. RDS로 인해 인공호흡기에 의존해 있는 저체중아의 경우 적절한 산소공급과 이를 위한 호흡의 유지는 치료의 가장 큰 핵심이 되며, 이를 위한 기관내 흑은 비인두 흡인 (nasopharyngeal suction)은 신생아 중환자실(NICU)의 가장 중요한 간호행위가 되어왔다. 인공호흡기를 위한 기관삽관은 그 자체가 기도의 성모운동을 방해하고 기침반사를 억제시켜 폐 분비물의 효과적 배출을 억제하며, 특히 저체중아의 경우 조산과 관련하여 미발달된 흥곽운등과 심폐기능은 폐분비물의 이동을 저해하는 요소이다. 따라서 기도내의 분비물의 이동을 효과적으로 하여 흡인 시에 최대한의 효과를 돕기 위해 흥곽 물리요법(chest physiotheraphy : CPT)의 한 형태인 흉곽진동법 (Chest Vibration : CV)가 행해져 왔다. 그러나 저체중아를 위한CV의 임상적 적용은 그 대상의 생리적 특성, CV의 적용부위(site)와 기간(duration)에 대한 과학적 근거 없이 만성감염이나 폐질환을 가진 성인이나 cystic fibrosis환자를 위한 CV protocol을 무분별하게 채택하여 저체중아에게 행하여져 왔다 이에 본 연구자는 저체중아에 대한 CV의 안전성을 평가하고, 이에 기초하여 저체중아에게 바람직한CV의 형태를 알아보고자 본 연구를 시작하였다. 연구설계는 CV의 안전성을 평가하기 위한 실험연구이다. CV의 안전성은 RDS치료의 가장 일차적 목표인 oxygenation변화에 의해 평가될 수 있으므로, 본 실험 연구에서는 Pulse oximeter에 의해 계속적으로 측정된 산소포화 변화(oxygen saturation change)를 측정하였다. 실험대상은 미국동부에 위치한 대학병원의 NICU에 입원하여 RDS와 관련된 호흡장애로 인공호흡기에 의존해 있는 10명의 저체중아였다. 인공호흡기에 의존된 모든 저체중아는 Pulse oximeter와 심폐기능 측정기(cardiopulmonary monitor)에 의해 산소공급과 호흡상태가 계속 측정되고 있었다. 실험대상의 평균 출생시 몸무게는 평균 1,3050gm(SD=580.6)이었고, 임신월령 은 평균 28.6주(SD=3.1)였다. RDS가 그들의 일차적 진단명이었고, 그중 4명은 pneumonia, atelectasis의 합병증을 가지고 있었다. 10명중 6명은 intermittent mandatory ventilation(IMV)의 형태로, 4명은 continuous positive airway pressure(CPAP)의 형태로 인공호흡기에 의존되어 있었고 CV시의 FiO2는 평균 42.3(SD=21.2)였다. CV는 중환아용 소형진동기 (minivibrator)를 이용해 가각 10명 의 간호사에 의해 행하여 졌고, 최소 22초에서 최대 100초 동안 실시되었다. 50%의 간호사는 30초에서 40초간 CV를 실시하였으며, CV의 적용부위도, 전후 흉곽부위, 혹은 병변이 있는 좌 우측, 흑은 양쪽 흉벽 등으로 다양했고, 적용방법도 원형으로 돌려가며(circular motion), 혹은 아래에서 위로, 혹은 아무런 기준없이 간호사의 기호에 따라 다양하게 적용되었다. 산소포화의 변화는 CV가 행해지기 전.후로 5초동안 관찰되었다. 연구의 결과, 산소포화 변화는 비 모수통계(non parametric statistics)의 일종인 Matched Paired Wilcoxon test로 분석 한 결과 CV후에 3%의 감소를 보였다(P<.05). 저체중아에 있어 산소포화의 3%감소는 임상적으로 중요한 의미가 없다고 사료되어지며, 실제 흡인전의 과도호흡에 의해 CV를 행하기 이전의 산소공급수준으로 돌아 왔다. CV실시 기간과 산소포화와의 상관관계는 비 모수통계인 Spearman rho correlation coefficient를 이용하여 분석하였는데, 이 두 변수는 서로 관계가 없는 것으로 나타났다(P>.05) 또한 CV와 흡인 후에 각각의 간호사들에게 CV를 필요로 한 저체중아의 기준, 적용부위, 기간, 방법등에 대한 기준을 물었으나 대상의 특성에 따른 간호사정에 의존하기보다는 간호사 각자의 선호하는 방법이나 습관에 라 행하는 것으로 나타났다. 결론적으로 CV와 산소포화 변화와의 관계, NICU에서 관찰된 CV의 임상적 적용을 기초로 저체중아에게 안전한 CV protocol은 신생아용 소형 진동기를 이용하여, 양쪽 흉곽의 늑골하측 변연 부위(low lateral costal margin)에서 시작하여 흉골 중앙부위 방향으로 30초 동안 진동기를 적용하는 것이 좋은 것으로 나타났다. 이에 CV의 효과를 평가하기 위한 보다 과학적인 접근방법으로, CV와 흡인의 결과인 가래(sputum)에 대한 연구를 제언하는 바이다.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.46 no.4
• /
• pp.369-381
• /
• 2019

The aim of this study was to analyze the changes and improvements in symptoms of sleep-disordered breathing (SDB) using semi-rapid maxillary expansion (SRME) in children with narrow maxilla and SDB symptoms. Subjects were 15 patients with sleep disorder (apnea-hypopnea index, AHI ≥ 1) and narrow maxillary arch between 7 and 9 years of age. Before the SRME was applied, all subjects underwent pediatric sleep questionnaires (PSQ), lateral cephalometry, and portable sleep monitoring before expansion (T0). All subjects were treated with SRME for 2 months, followed by maintenance for the next 3 months. All subjects had undergone PSQ, lateral cephalometry, and portable sleep monitoring after expansion (T1). Adenoidal-nasopharyngeal ratio (ANR), upper airway width and hyoid bone position were measured by lateral cephalometry. The data before and after SRME were statistically analyzed with frequency analysis and Wilcoxon signed rank test. As reported by PSQ, the total PSQ scale was declined significantly from 0.45 (T0) to 0.18 (T1) (p = 0.001). Particularly, snoring, breathing, and inattention hyperactivity were significantly improved (p = 0.001). ANR significantly decreased from 0.63 (T0) to 0.51 (T1) (p = 0.003). After maxillary expansion, only palatopharyngeal airway width was significantly increased (p = 0.035). There was no statistically significant difference in position of hyoid bone after expansion (p = 0.333). From analysis of portable sleep monitoring, changes in sleep characteristics showed a statistically significant decrease in AHI and ODI, and the lowest oxygen desaturation was significantly increased after SRME (p = 0.001, 0.004, 0.023). In conclusion, early diagnosis with questionnaires and portable sleep monitoring is important. Treatment using SRME will improve breathing of children with SDB.