• Tuberculosis and Respiratory Diseases
• /
• v.43 no.2
• /
• pp.190-200
• /
• 1996

Background : Mechanical ventilation constitutes the last therapeutic method for acute respiratory failure when oxygen therapy and medical treatment fail to improve the respiratory status of the patient. This invasive ventilation, classically administered by endotracheal intubation or by tracheostomy, is associated with significant mortality and morbidity. Consequently, any less invasive method able to avoid the use of endotracheal ventilation would appear to be useful in high risk patient. Over recent years, the efficacy of nasal mask ventilation has been demonstrated in the treatment of chronic restrictive respiratory failure, particularly in patients with neuromuscular diseases. More recently, this method has been successfully used in the treatment of acute respiratory failure due to parenchymal disease. Method : We assessed the efficacy of Bilevel positive airway pressure(BiPAP) in the treatment of acute exacerbation of chronic obstructive pulmonary disease(COPD). This study prospectively evaluated the clinical effectiveness of a treatment schedule with positive pressure ventilation via nasal mask(Respironics BiPAP device) in 22 patients with acute exacerbations of COPD. Eleven patients with acute exacerbations of COPD were treated with nasal pressure support ventilation delivered via a nasal ventilatory support system plus standard treatment for 3 consecutive days. An additional 11 control patients were treated only with standard treatment. The standard treatment consisted of medical and oxygen therapy. The nasal BiPAP was delivered by a pressure support ventilator in spontaneous timed mode and at an inspiratory positive airway pressure $6-8cmH_2O$ and an expiratory positive airway pressure $3-4cmH_2O$. Patients were evaluated with physical examination(respiratory rate), modified Borg scale and arterial blood gas before and after the acute therapeutic intervention. Results : Pretreatment and after 3 days of treatment, mean $PaO_2$ was 56.3mmHg and 79.1mmHg (p<0.05) in BiPAP group and 56.9mmHg and 70.2mmHg (p<0.05) in conventional treatment (CT) group and $PaCO_2$ was 63.9mmHg and 56.9mmHg (p<0.05) in BiPAP group and 53mmHg and 52.8mmHg in CT group respectively. pH was 7.36 and 7.41 (p<0.05) in BiPAP group and 7.37 and 7.38 in cr group respectively. Pretreatment and after treatment, mean respiratory rate was 28 and 23 beats/min in BiPAP group and 25 and 20 beats/min in CT group respectively. Borg scale was 7.6 and 4.7 in BiPAP group and 6.4 and 3.8 in CT group respectively. There were significant differences between the two groups in changes of mean $PaO_2$, $PaCO_2$ and pH respectively. Conclusion: We conclude that short-term nasal pressure-support ventilation delivered via nasal BiPAP in the treatment of acute exacerbation of COPD, is an efficient mode of assisted ventilation for improving blood gas values and dyspnea sensation and may reduce the need for endotracheal intubation with mechanical ventilation.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.31 no.4
• /
• pp.569-578
• /
• 2004

The purpose of this study was to clarify the palatal arch length, width and height in the primary and permanent dentition. Samples were consisted of normal occlusions both in the primary dentition(50 males and 50 females) and in the permanent dentition(50 males and 50 females). With their upper plaster casts were used and through 3-dimensional laser scanning(3D Scanner, DS4060, LDI, U.S.A.), cloud data, polygonization, section curve and loft surface, fit and horizontal plane were based to measure the palatal arch length, width and height(Surfacer 10.0, Imageware, U.S.A.). T-tests were applied for the statistical analyze of the data. The results were as follows : 1. In the measurement values, the values of the male were higher than those of the female except primary anterior palatal height. There were not only statistically significant differences in anterior palatal width(p<0.05) and posterior palatal width(p<0.01) in primary dentition but palatal width(p<0.05), anterior palatal length(p<0.01), middle and posterior palatal length(p<0.05) in permanent dentition between male and female. 2. In the indices of palate, there were statistically significant differences in height-length index(p<0.05) and width-length index(p<0.01) between male and female in primary dentition. In permanent dentition, there was statistically difference between male and female. 3. In the measurement values, posterior palatal width was increased most greatly. Posterior palatal height, anterior palatal width and anterior palatal length were followed by descending order. On the other hand, anterior palatal height and posterior palatal length were decreased. 4. In the indices of palate, the height-length index, the width-length index and posterior height-width index were increased, but the others were decreased.

• Korea journal of population studies
• /
• v.19 no.2
• /
• pp.77-105
• /
• 1996

The rural problems which we are facing start from the extremely small sized population and the skewed population structure by age and sex. Thus we analyzed the change of the rural population. And we analyzed the recent return migration to the rural areas by comparing the recent in-migrants with out-migrants to rural areas. And by analyzing the rural village survey data which was to show the current characteristics of rural population, we found out the effects of the in-migrants to the rural areas and predicted the futures of rural villages by characteristics. The changes of rural population composition by age was very clear. As the out-migrants towards cities carried on, the population composition of young children aged 0~4 years was low and the aged became thick. The proportion of the population aged 0~4 years was 45.1% of the total population in 1970 and dropped down to 20.4% in 1995, which is predicted to become under 20% from now on. In the same period(1970~1995), the population aged 65 years and over rose from 4.2% to 11.9%. In 1960, before industrialization, the proportion of the population aged 0~4 years in rural areas was higher than that of cities. As the rural young population continuously moves to cities it became lower than that in urban areas from 1975 and the gap grew till 1990. But the proportion of rural population aged 0~4 years in 1995 became 6.2% and the gap reduced. We can say this is the change of the characteristics of in-migrants and out-migrants in the rural areas. Also considering the composition of the population by age group moving from urban to rural area in the late 1980s, 51.8% of the total migrants concentrates upon age group of 20~34 years and these people's educational level was higher than that of out-migrants to urban areas. This fact predicted the changes of the rural population, and the results will turn out as a change in the rural society. However, after comparing the population structure between the pure rural village of Boeun-gun and suburban village of Paju-gun which was agriculture centered village but recently changed rapidly, the recent change of the rural population structure which the in-migrants to rural areas becomes younger is just a phenomenon in the suburban rural areas, not the change of the total rural areas in general. From the characteristics of the population structure of rural village from the field survey on these villages, we can see that in the pure rural villages without any effects from cities the regidents are highly aged, while industrialization and urbanization are making a progress in suburban villages. Therefore, the recent partial change of the rural population structure and the change of characteristics of the in-migrants toward rural areas is effecting and being effected by the population change of areas like suburban rural villages. Although there are return migrants to rural areas to change their jobs into agriculture, this is too minor to appear as a statistic effect.

• Journal of Preventive Medicine and Public Health
• /
• v.4 no.1
• /
• pp.77-87
• /
• 1971

A study of the knowledge, attitude and practices about the maternal and child health of 305 married women residing in apartments at the Yonsei Community Health area was conducted during the period from November to December 1970 using designed questionnaire with well trained interviewers. The results and findings obtained from the study are summarized as follows: A. Pregnancy and Birth Questions were asked about their last child. 1. 16.4% of the women were pregnant. 2. Among 281 women who had experienced delivery, 48.0% were assisted by doctor or midwisves for their last delivery, while the rest of women delivered their last baby at home without any professional's assistance. The higher the level of education or the greater exposure to mass communication, the more the deliveries were assisted by doctors or midwives. Those women who were born and raised in cities had more deliveries assisted by doctors and midwives than those who were not. 3. Kinds of delivery sheets used. Among 141 cases of home delivery 68% used cement bag paper or vinyl sheets. Three% used nothing and remained used unsterile materials. 4. Among 141 cases of home delivery, 70.2% used scissors. The rest of them used other methods. 5. 47.3% of the women had a rest for one month or more after birth. The higher the level of education, the longer the period of rest was observed. 6. 52.4% of the women fed the colostrum to their babies. This was not related to the mother's education. 7 About half(42.9%) of the women had poor knowledge about a proper diet for the pre and post natal period. B. Child Health 1. Knowledge and practice regarding to the immunization for their children: Most of the women (93.2%) could name at least one kind of immunization. 20.3% could name 6 kinds of immunization. Mothers education level did not influence their ability to name immunizations. 85.2% of children had been immunized at least once. 2. Morbidity of last born children: 48.1% of their last born children were found to have been sick during the last year. Less than half(41.5%) of the sick children were seen by doctor. 3. Counselling at well baby clinic: Most of the women(76.5%) had no counselling for their children. Registration rate at the well baby clinic at the Severance Hospital was 13.2%. 45.9% wanted to visit to the well baby clinic at the Severance Hospital. 4. Weaning Period: 44.6% said that the beginning of the weaning for their last born children was from 6 months to twelve months of age. The most important reason of weaning was the health of both mothers and children. 5. Knowledge and Practice regarding birth and death Registration: 64.6% of the women could name correctly the Ku-office as the place for the registration. Only 29.2% registered the birth of their last born children within 14 days. C. Knowledge, Attitude and Practice regarding to family planning Most: of the women accepted the idea of family planning. 97.7% could name at least one contraceptive method. 35.4% were found to be current users of contraceptive methods. The ideal number of children was 3.1 in average.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.73-85
• /
• 2013

Nowadays, in today's information society, the importance of the knowledge service using the information to creative value is getting higher day by day. In addition, depending on the development of IT technology, it is ease to collect and use information. Also, many companies actively use customer information to marketing in a variety of industries. Into the 21st century, companies have been actively using the culture arts to manage corporate image and marketing closely linked to their commercial interests. But, it is difficult that companies attract or maintain consumer's interest through their technology. For that reason, it is trend to perform cultural activities for tool of differentiation over many firms. Many firms used the customer's experience to new marketing strategy in order to effectively respond to competitive market. Accordingly, it is emerging rapidly that the necessity of personalized service to provide a new experience for people based on the personal profile information that contains the characteristics of the individual. Like this, personalized service using customer's individual profile information such as language, symbols, behavior, and emotions is very important today. Through this, we will be able to judge interaction between people and content and to maximize customer's experience and satisfaction. There are various relative works provide customer-centered service. Specially, emotion recognition research is emerging recently. Existing researches experienced emotion recognition using mostly bio-signal. Most of researches are voice and face studies that have great emotional changes. However, there are several difficulties to predict people's emotion caused by limitation of equipment and service environments. So, in this paper, we develop emotion prediction model based on vision-based interface to overcome existing limitations. Emotion recognition research based on people's gesture and posture has been processed by several researchers. This paper developed a model that recognizes people's emotional states through body gesture and posture using difference image method. And we found optimization validation model for four kinds of emotions' prediction. A proposed model purposed to automatically determine and predict 4 human emotions (Sadness, Surprise, Joy, and Disgust). To build up the model, event booth was installed in the KOCCA's lobby and we provided some proper stimulative movie to collect their body gesture and posture as the change of emotions. And then, we extracted body movements using difference image method. And we revised people data to build proposed model through neural network. The proposed model for emotion prediction used 3 type time-frame sets (20 frames, 30 frames, and 40 frames). And then, we adopted the model which has best performance compared with other models.' Before build three kinds of models, the entire 97 data set were divided into three data sets of learning, test, and validation set. The proposed model for emotion prediction was constructed using artificial neural network. In this paper, we used the back-propagation algorithm as a learning method, and set learning rate to 10%, momentum rate to 10%. The sigmoid function was used as the transform function. And we designed a three-layer perceptron neural network with one hidden layer and four output nodes. Based on the test data set, the learning for this research model was stopped when it reaches 50000 after reaching the minimum error in order to explore the point of learning. We finally processed each model's accuracy and found best model to predict each emotions. The result showed prediction accuracy 100% from sadness, and 96% from joy prediction in 20 frames set model. And 88% from surprise, and 98% from disgust in 30 frames set model. The findings of our research are expected to be useful to provide effective algorithm for personalized service in various industries such as advertisement, exhibition, performance, etc.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.125-140
• /
• 2013

We call a data set in which the number of records belonging to a certain class far outnumbers the number of records belonging to the other class, 'imbalanced data set'. Most of the classification techniques perform poorly on imbalanced data sets. When we evaluate the performance of a certain classification technique, we need to measure not only 'accuracy' but also 'sensitivity' and 'specificity'. In a customer churn prediction problem, 'retention' records account for the majority class, and 'churn' records account for the minority class. Sensitivity measures the proportion of actual retentions which are correctly identified as such. Specificity measures the proportion of churns which are correctly identified as such. The poor performance of the classification techniques on imbalanced data sets is due to the low value of specificity. Many previous researches on imbalanced data sets employed 'oversampling' technique where members of the minority class are sampled more than those of the majority class in order to make a relatively balanced data set. When a classification model is constructed using this oversampled balanced data set, specificity can be improved but sensitivity will be decreased. In this research, we developed a hybrid model of support vector machine (SVM), artificial neural network (ANN) and decision tree, that improves specificity while maintaining sensitivity. We named this hybrid model 'hybrid SVM model.' The process of construction and prediction of our hybrid SVM model is as follows. By oversampling from the original imbalanced data set, a balanced data set is prepared. SVM_I model and ANN_I model are constructed using the imbalanced data set, and SVM_B model is constructed using the balanced data set. SVM_I model is superior in sensitivity and SVM_B model is superior in specificity. For a record on which both SVM_I model and SVM_B model make the same prediction, that prediction becomes the final solution. If they make different prediction, the final solution is determined by the discrimination rules obtained by ANN and decision tree. For a record on which SVM_I model and SVM_B model make different predictions, a decision tree model is constructed using ANN_I output value as input and actual retention or churn as target. We obtained the following two discrimination rules: 'IF ANN_I output value <0.285, THEN Final Solution = Retention' and 'IF ANN_I output value ${\geq}0.285$, THEN Final Solution = Churn.' The threshold 0.285 is the value optimized for the data used in this research. The result we present in this research is the structure or framework of our hybrid SVM model, not a specific threshold value such as 0.285. Therefore, the threshold value in the above discrimination rules can be changed to any value depending on the data. In order to evaluate the performance of our hybrid SVM model, we used the 'churn data set' in UCI Machine Learning Repository, that consists of 85% retention customers and 15% churn customers. Accuracy of the hybrid SVM model is 91.08% that is better than that of SVM_I model or SVM_B model. The points worth noticing here are its sensitivity, 95.02%, and specificity, 69.24%. The sensitivity of SVM_I model is 94.65%, and the specificity of SVM_B model is 67.00%. Therefore the hybrid SVM model developed in this research improves the specificity of SVM_B model while maintaining the sensitivity of SVM_I model.

• Korean Journal of Poultry Science
• /
• v.32 no.4
• /
• pp.291-300
• /
• 2005

Two experiments were carried out to assess the appropriate incubation conditions namely; duration, moisture content and the ideal microbial inoculant for fermented dried food waste(EW) offered to broilers. The nutrient utilization of birds fed the FW diets at varying dietary inclusion rates was also compared with a control diet. In Experiment 1, different moisture contents(MC) of 30, 40, 50 and $60\%$ respectively were predetermined to establish the ideal duration of incubation and the microbial inoculant. A 1mL Aspergillus oryzae(AO) $(1.33\times10^5\;CFU/mL)$ was used as the seed inoculant in FW. This results indicated that the ideal MC for incubation was $40\~50\%$ while the normal incubation time was > 72 hours. Consequently, AO seeds at 0.25, 0.50, 0.75 and 1.00mL were inoculated in FW to determine its effect on AO count. The comparative AO count of FW incubated for 12 and 96 hours, respectively showed no significant differences among varying inoculant dosage rates. The FW inoculated with lower AO seeds at 0.10, 0.05 and 0.01mL were likewise incubated for 72 and 96 hours, respectively and no changes in AO count was detected(p<0.05). The above findings indicated that the incubation requirements for FW should be $%40\~50\%$ for 72 hours with an AO seed incoulant dosage rate of 0.10mL. Consequently, in Experiment II, after determining the appropriate processing condition for the FW, 20 five-week old male Hubbard strain were used in a digestibility experiment. The birds were divided into 4 groups with 5 pens(1 bird per pen). The dietary treatments were; Treatment 1 : Control(Basal diet), Treatment 2 : $60\%$ Basal+4$40\%$ FW, Treatment 3 : $60\%$ $Basal+20\%\;FW+20\%$ AFW(Aspergillus oryzae inoculate dried food-waste diet) and Treatment 4: $60\%$ Basal+$40\%$ Am. Digestibility of treatment 2 was lowed on common nutrients and amino acids compared with control(p<0.05) and on crude fat and phosphorus compared with AFW treatments(T3, T4)(plt;0.05). Digestibility of treatment 3 and 4 increased on crude fiber and crude ash compared treatment 2 (p<0.05). Digestibility of control was high on agrinine, leucine, and phenylalnine of essential amino acids compared with treatment 3 and 4(p<0.05), and diestibility of treatment 3 and 4 was improved on arginine, lysine, and threonine of essential amino acids. Finally, despite comparable nutrient utilization among treatments, birds fed the dietary treatment containing AO tended to superior nutrient digestion to those fed the $60\%$ Basa1+$40\%$ FW.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.141-166
• /
• 2019

Recently, channels like social media and SNS create enormous amount of data. In all kinds of data, portions of unstructured data which represented as text data has increased geometrically. But there are some difficulties to check all text data, so it is important to access those data rapidly and grasp key points of text. Due to needs of efficient understanding, many studies about text summarization for handling and using tremendous amounts of text data have been proposed. Especially, a lot of summarization methods using machine learning and artificial intelligence algorithms have been proposed lately to generate summary objectively and effectively which called "automatic summarization". However almost text summarization methods proposed up to date construct summary focused on frequency of contents in original documents. Those summaries have a limitation for contain small-weight subjects that mentioned less in original text. If summaries include contents with only major subject, bias occurs and it causes loss of information so that it is hard to ascertain every subject documents have. To avoid those bias, it is possible to summarize in point of balance between topics document have so all subject in document can be ascertained, but still unbalance of distribution between those subjects remains. To retain balance of subjects in summary, it is necessary to consider proportion of every subject documents originally have and also allocate the portion of subjects equally so that even sentences of minor subjects can be included in summary sufficiently. In this study, we propose "subject-balanced" text summarization method that procure balance between all subjects and minimize omission of low-frequency subjects. For subject-balanced summary, we use two concept of summary evaluation metrics "completeness" and "succinctness". Completeness is the feature that summary should include contents of original documents fully and succinctness means summary has minimum duplication with contents in itself. Proposed method has 3-phases for summarization. First phase is constructing subject term dictionaries. Topic modeling is used for calculating topic-term weight which indicates degrees that each terms are related to each topic. From derived weight, it is possible to figure out highly related terms for every topic and subjects of documents can be found from various topic composed similar meaning terms. And then, few terms are selected which represent subject well. In this method, it is called "seed terms". However, those terms are too small to explain each subject enough, so sufficient similar terms with seed terms are needed for well-constructed subject dictionary. Word2Vec is used for word expansion, finds similar terms with seed terms. Word vectors are created after Word2Vec modeling, and from those vectors, similarity between all terms can be derived by using cosine-similarity. Higher cosine similarity between two terms calculated, higher relationship between two terms defined. So terms that have high similarity values with seed terms for each subjects are selected and filtering those expanded terms subject dictionary is finally constructed. Next phase is allocating subjects to every sentences which original documents have. To grasp contents of all sentences first, frequency analysis is conducted with specific terms that subject dictionaries compose. TF-IDF weight of each subjects are calculated after frequency analysis, and it is possible to figure out how much sentences are explaining about each subjects. However, TF-IDF weight has limitation that the weight can be increased infinitely, so by normalizing TF-IDF weights for every subject sentences have, all values are changed to 0 to 1 values. Then allocating subject for every sentences with maximum TF-IDF weight between all subjects, sentence group are constructed for each subjects finally. Last phase is summary generation parts. Sen2Vec is used to figure out similarity between subject-sentences, and similarity matrix can be formed. By repetitive sentences selecting, it is possible to generate summary that include contents of original documents fully and minimize duplication in summary itself. For evaluation of proposed method, 50,000 reviews of TripAdvisor are used for constructing subject dictionaries and 23,087 reviews are used for generating summary. Also comparison between proposed method summary and frequency-based summary is performed and as a result, it is verified that summary from proposed method can retain balance of all subject more which documents originally have.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.83-102
• /
• 2021

The government recently announced various policies for developing big-data and artificial intelligence fields to provide a great opportunity to the public with respect to disclosure of high-quality data within public institutions. KSURE(Korea Trade Insurance Corporation) is a major public institution for financial policy in Korea, and thus the company is strongly committed to backing export companies with various systems. Nevertheless, there are still fewer cases of realized business model based on big-data analyses. In this situation, this paper aims to develop a new business model which can be applied to an ex-ante prediction for the likelihood of the insurance accident of credit guarantee. We utilize internal data from KSURE which supports export companies in Korea and apply machine learning models. Then, we conduct performance comparison among the predictive models including Logistic Regression, Random Forest, XGBoost, LightGBM, and DNN(Deep Neural Network). For decades, many researchers have tried to find better models which can help to predict bankruptcy since the ex-ante prediction is crucial for corporate managers, investors, creditors, and other stakeholders. The development of the prediction for financial distress or bankruptcy was originated from Smith(1930), Fitzpatrick(1932), or Merwin(1942). One of the most famous models is the Altman's Z-score model(Altman, 1968) which was based on the multiple discriminant analysis. This model is widely used in both research and practice by this time. The author suggests the score model that utilizes five key financial ratios to predict the probability of bankruptcy in the next two years. Ohlson(1980) introduces logit model to complement some limitations of previous models. Furthermore, Elmer and Borowski(1988) develop and examine a rule-based, automated system which conducts the financial analysis of savings and loans. Since the 1980s, researchers in Korea have started to examine analyses on the prediction of financial distress or bankruptcy. Kim(1987) analyzes financial ratios and develops the prediction model. Also, Han et al.(1995, 1996, 1997, 2003, 2005, 2006) construct the prediction model using various techniques including artificial neural network. Yang(1996) introduces multiple discriminant analysis and logit model. Besides, Kim and Kim(2001) utilize artificial neural network techniques for ex-ante prediction of insolvent enterprises. After that, many scholars have been trying to predict financial distress or bankruptcy more precisely based on diverse models such as Random Forest or SVM. One major distinction of our research from the previous research is that we focus on examining the predicted probability of default for each sample case, not only on investigating the classification accuracy of each model for the entire sample. Most predictive models in this paper show that the level of the accuracy of classification is about 70% based on the entire sample. To be specific, LightGBM model shows the highest accuracy of 71.1% and Logit model indicates the lowest accuracy of 69%. However, we confirm that there are open to multiple interpretations. In the context of the business, we have to put more emphasis on efforts to minimize type 2 error which causes more harmful operating losses for the guaranty company. Thus, we also compare the classification accuracy by splitting predicted probability of the default into ten equal intervals. When we examine the classification accuracy for each interval, Logit model has the highest accuracy of 100% for 0~10% of the predicted probability of the default, however, Logit model has a relatively lower accuracy of 61.5% for 90~100% of the predicted probability of the default. On the other hand, Random Forest, XGBoost, LightGBM, and DNN indicate more desirable results since they indicate a higher level of accuracy for both 0~10% and 90~100% of the predicted probability of the default but have a lower level of accuracy around 50% of the predicted probability of the default. When it comes to the distribution of samples for each predicted probability of the default, both LightGBM and XGBoost models have a relatively large number of samples for both 0~10% and 90~100% of the predicted probability of the default. Although Random Forest model has an advantage with regard to the perspective of classification accuracy with small number of cases, LightGBM or XGBoost could become a more desirable model since they classify large number of cases into the two extreme intervals of the predicted probability of the default, even allowing for their relatively low classification accuracy. Considering the importance of type 2 error and total prediction accuracy, XGBoost and DNN show superior performance. Next, Random Forest and LightGBM show good results, but logistic regression shows the worst performance. However, each predictive model has a comparative advantage in terms of various evaluation standards. For instance, Random Forest model shows almost 100% accuracy for samples which are expected to have a high level of the probability of default. Collectively, we can construct more comprehensive ensemble models which contain multiple classification machine learning models and conduct majority voting for maximizing its overall performance.