• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.79-99
• /
• 2015

The prediction of bankruptcy has been extensively studied in the accounting and finance field. It can have an important impact on lending decisions and the profitability of financial institutions in terms of risk management. Many researchers have focused on constructing a more robust bankruptcy prediction model. Early studies primarily used statistical techniques such as multiple discriminant analysis (MDA) and logit analysis for bankruptcy prediction. However, many studies have demonstrated that artificial intelligence (AI) approaches, such as artificial neural networks (ANN), decision trees, case-based reasoning (CBR), and support vector machine (SVM), have been outperforming statistical techniques since 1990s for business classification problems because statistical methods have some rigid assumptions in their application. In previous studies on corporate bankruptcy, many researchers have focused on developing a bankruptcy prediction model using financial ratios. However, there are few studies that suggest the specific types of bankruptcy. Previous bankruptcy prediction models have generally been interested in predicting whether or not firms will become bankrupt. Most of the studies on bankruptcy types have focused on reviewing the previous literature or performing a case study. Thus, this study develops a model using data mining techniques for predicting the specific types of bankruptcy as well as the occurrence of bankruptcy in Korean small- and medium-sized construction firms in terms of profitability, stability, and activity index. Thus, firms will be able to prevent it from occurring in advance. We propose a hybrid approach using two artificial neural networks (ANNs) for the prediction of bankruptcy types. The first is a back-propagation neural network (BPN) model using supervised learning for bankruptcy prediction and the second is a self-organizing map (SOM) model using unsupervised learning to classify bankruptcy data into several types. Based on the constructed model, we predict the bankruptcy of companies by applying the BPN model to a validation set that was not utilized in the development of the model. This allows for identifying the specific types of bankruptcy by using bankruptcy data predicted by the BPN model. We calculated the average of selected input variables through statistical test for each cluster to interpret characteristics of the derived clusters in the SOM model. Each cluster represents bankruptcy type classified through data of bankruptcy firms, and input variables indicate financial ratios in interpreting the meaning of each cluster. The experimental result shows that each of five bankruptcy types has different characteristics according to financial ratios. Type 1 (severe bankruptcy) has inferior financial statements except for EBITDA (earnings before interest, taxes, depreciation, and amortization) to sales based on the clustering results. Type 2 (lack of stability) has a low quick ratio, low stockholder's equity to total assets, and high total borrowings to total assets. Type 3 (lack of activity) has a slightly low total asset turnover and fixed asset turnover. Type 4 (lack of profitability) has low retained earnings to total assets and EBITDA to sales which represent the indices of profitability. Type 5 (recoverable bankruptcy) includes firms that have a relatively good financial condition as compared to other bankruptcy types even though they are bankrupt. Based on the findings, researchers and practitioners engaged in the credit evaluation field can obtain more useful information about the types of corporate bankruptcy. In this paper, we utilized the financial ratios of firms to classify bankruptcy types. It is important to select the input variables that correctly predict bankruptcy and meaningfully classify the type of bankruptcy. In a further study, we will include non-financial factors such as size, industry, and age of the firms. Thus, we can obtain realistic clustering results for bankruptcy types by combining qualitative factors and reflecting the domain knowledge of experts.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.67-88
• /
• 2019

Webtoon is a Korean-style digital comics platform that distributes comics content produced using the characteristic elements of the Internet in a form that can be consumed online. With the recent rapid growth of the webtoon industry and the exponential increase in the supply of webtoon content, the need for effective webtoon content recommendation measures is growing. Webtoons are digital content products that combine pictorial, literary and digital elements. Therefore, webtoons stimulate consumer sentiment by making readers have fun and engaging and empathizing with the situations in which webtoons are produced. In this context, it can be expected that the sentiment that webtoons evoke to consumers will serve as an important criterion for consumers' choice of webtoons. However, there is a lack of research to improve webtoons' recommendation performance by utilizing consumer sentiment. This study is aimed at developing consumer sentiment pattern maps that can support effective recommendations of webtoon content, focusing on consumer sentiments that have not been fully discussed previously. Metadata and consumer sentiments data were collected for 200 works serviced on the Korean webtoon platform 'Naver Webtoon' to conduct this study. 488 sentiment terms were collected for 127 works, excluding those that did not meet the purpose of the analysis. Next, similar or duplicate terms were combined or abstracted in accordance with the bottom-up approach. As a result, we have built webtoons specialized sentiment-index, which are reduced to a total of 63 emotive adjectives. By performing exploratory factor analysis on the constructed sentiment-index, we have derived three important dimensions for classifying webtoon types. The exploratory factor analysis was performed through the Principal Component Analysis (PCA) using varimax factor rotation. The three dimensions were named 'Immersion', 'Touch' and 'Irritant' respectively. Based on this, K-Means clustering was performed and the entire webtoons were classified into four types. Each type was named 'Snack', 'Drama', 'Irritant', and 'Romance'. For each type of webtoon, we wrote webtoon-sentiment 2-Mode network graphs and looked at the characteristics of the sentiment pattern appearing for each type. In addition, through profiling analysis, we were able to derive meaningful strategic implications for each type of webtoon. First, The 'Snack' cluster is a collection of webtoons that are fast-paced and highly entertaining. Many consumers are interested in these webtoons, but they don't rate them well. Also, consumers mostly use simple expressions of sentiment when talking about these webtoons. Webtoons belonging to 'Snack' are expected to appeal to modern people who want to consume content easily and quickly during short travel time, such as commuting time. Secondly, webtoons belonging to 'Drama' are expected to evoke realistic and everyday sentiments rather than exaggerated and light comic ones. When consumers talk about webtoons belonging to a 'Drama' cluster in online, they are found to express a variety of sentiments. It is appropriate to establish an OSMU(One source multi-use) strategy to extend these webtoons to other content such as movies and TV series. Third, the sentiment pattern map of 'Irritant' shows the sentiments that discourage customer interest by stimulating discomfort. Webtoons that evoke these sentiments are hard to get public attention. Artists should pay attention to these sentiments that cause inconvenience to consumers in creating webtoons. Finally, Webtoons belonging to 'Romance' do not evoke a variety of consumer sentiments, but they are interpreted as touching consumers. They are expected to be consumed as 'healing content' targeted at consumers with high levels of stress or mental fatigue in their lives. The results of this study are meaningful in that it identifies the applicability of consumer sentiment in the areas of recommendation and classification of webtoons, and provides guidelines to help members of webtoons' ecosystem better understand consumers and formulate strategies.

• Journal of Soil and Groundwater Environment
• /
• v.10 no.4
• /
• pp.33-44
• /
• 2005

On the basis of a stepwise and careful integration of various field and laboratory methods the analysis of groundwater flow characterization was performed with five boreholes (BH-1, -2, -3, -4, -5) on a pilot site of Natural Forest Park in Guemsan-gun, Chungcheongbook-do, Korea. The regional lineaments of NW-SE are primarily developed on the area, which results in the development of many fractures of NW-SE direction around boreholes made in the test site for the study. A series of surface geological survey, core logging, geophysical logging, tomography, tracer tests, and heat-pulse flowmeter logging were carried out to determine fracture characteristics and fracture connectivity between the boreholes. In the result of fracture connectivity analysis BH-1 the injection well has a poor connectivity with BH-2 and BH-3, whereas a good with BH-4 and BH-5. In order to analyse the hydraulic connectivity between BH-1 and BH-5, in particular, a conspicuous groundwater outflux in the depth of 12 m and influx in the depth of 65 m and 70 m, but partly in/outflux occurred in other depths in BH-5 were observed as pumping from BH-1. On the other hand, when pumping from BH-5 the strong outflux in the depths of 17 m and 70 m was occurred. The spatial connectivity between the boreholes was examined in the depth of 15 m, 67 m, and 71 m in BH-1 as well as in the depth of 15 m, 17 m, 22 m, 72 m, and 83 m in BH-5.

• Korean Journal of Soil Science and Fertilizer
• /
• v.3 no.1
• /
• pp.49-54
• /
• 1970

In an effort of determine the metabolism and bio-synthesis of nitrogen, was studied at variance of souble nitrogens, free amino acids and total alcohol soluble amino acids during the growth of younger soybean plants, and saybean divides into cotyledon and embryonic organ (shoot and root system) in this experiment. 1. In the soluble nitrogen of soybean, ratio of increase and decrease in the amino acids of them was displayed the near phenomena both cotyledon and embryonic organ of soybean. But, in the 17th days after seed germination, that is the developmeatal stage of adult leaf of soybeans, was appear the maximum value. It has been suggested that the stage of first half period of growth as boundary the stage of adult leaf development which indicated clear morphologically, at the younger soybean plants, is the step that nitrogen assimilation. 2. It was investigated the amino acids of seventeen kinds in the seed state, but at the third days after seed germination, was investigated the amino acids of nineteen kinds. Ultimately, it appears the translocation from cotyledon to embryonic organ in the distribution of amino acid, the nineth day which differentiation begining day of embryonic organ, then after, it happen the variation of number of inspected amino acid in the cotyledon and embryonic organ but only the variance changes in the distribution and quantitative aspects. Especially, the most conspicuous fact was indicated the accumulation of Asparagine, that is the phenomena of Asparagine-accumulation was constitute, not with standing no fertilization from outside. It may be concluded from the results of this investigation that the difference of special phenomena of soybean from the embryo of other plans. 3. In the initial stage of differentiation at embryonic organ number of inspected amino acid was very few, and then, it was slightly appeared the increase-phenomena in the number of them. It was that the amino acid inspecting the initial stage was translocated from the cotyledon. It is suggested that the intermediate-metabolism of amino acid was constituted on the basis of above the result. 4. The phenomena of increase and decrease of total alcohol soluble amino acid were essentially identical to the water soluble amino acid of soybean, but it was appeared the severe difference of amounts in both of them.

• Korean Journal of Soil Science and Fertilizer
• /
• v.6 no.2
• /
• pp.75-81
• /
• 1973

The morphological, physical, and chemical properties of Sonjeong series derived from acidic crystalline rocks are presented. Also it deals with the genesis and classification of the Songjeong series. Morphologically these soils have brown to dark brown loam A horizons and yellowish red to red clay loam Bt horizons with moderate, medium subangular blocky structure and thin patchy clay cutans on the ped faces. C horizons are very deep, yellowish red to yellowish brown fine sandy loam or sandy loam with original rock structure. Physically distribution of particle size indicates that clay increases with depth up to argillic horizons but below the argillic horizons clay content decrease. The moisture holding capacity is fairly good in Songjeong soils. Chemically soil reaction is strongly to very strongly acid throughout the profile and content of organic matter is less than 1 per cent except A horizons. Cation exchange capacity ranges from 5 to 9 me/100g of soils and base saturation is less than 35 per cent throughout the profile. The natural fertility of Songjeong soils are usually low. It needs lime, organic matter, and heavy application of fertilizer for the crop land. These soils occur temperate and humid climate under coniferous, deciduous, and mixed forest vegetation. Songjeong soils are classified as Red-Yellow Soils. Characteristically Songjeong soils are similar to Red-Yellow Podzolic soils in the United States but lack of A2 horizons and are quite liket Red-Yellow Soils of the Japan. According to new classification system which is 7th approximation of USDA Songjeong soils can be classified as fine loamy, mesic family of Typic Hapludults and in the FAO/UNESCO project World Soil Map as Orthic Acrisols.

• Journal of Korean Society of Transportation
• /
• v.22 no.6
• /
• pp.133-144
• /
• 2004

A model and a measure which can evaluate the risk of rear end collision are developed. Most traffic accidents involve multiple causes such as the human factor, the vehicle factor, and the highway element at any given time. Thus, these factors should be considered in analyzing the risk of an accident and in developing safety models. Although most risky situations and accidents on the roads result from the poor response of a driver to various stimuli, many researchers have modeled the risk or accident by analyzing only the stimuli without considering the response of a driver. Hence, the reliabilities of those models turned out to be low. Thus in developing the model behaviors of a driver, such as reaction time and deceleration rate, are considered. In the past, most studies tried to analyze the relationships between a risk and an accident directly but they, due to the difficulty of finding out the directional relationships between these factors, developed a model by considering these factors, developed a model by considering indirect factors such as volume, speed, etc. However, if the relationships between risk and accidents are looked into in detail, it can be seen that they are linked by the behaviors of a driver, and depending on drivers the risk as it is on the road-vehicle system may be ignored or call drivers' attention. Therefore, an accident depends on how a driver handles risk, so that the more related risk to and accident occurrence is not the risk itself but the risk responded by a driver. Thus, in this study, the behaviors of a driver are considered in the model and to reflect these behaviors three concepts related to accidents are introduced. And safe stopping distance and accident occurrence probability were used for better understanding and for more reliable modeling of the risk. The index which can represent the risk is also developed based on measures used in evaluating noise level, and for the risk comparison between various situations, the equivalent risk level, considering the intensity and duration time, is developed by means of the weighted average. Validation is performed with field surveys on the expressway of Seoul, and the test vehicle was made to collect the traffic flow data, such as deceleration rate, speed and spacing. Based on this data, the risk by section, lane and traffic flow conditions are evaluated and compared with the accident data and traffic conditions. The evaluated risk level corresponds closely to the patterns of actual traffic conditions and counts of accident. The model and the method developed in this study can be applied to various fields, such as safety test of traffic flow, establishment of operation & management strategy for reliable traffic flow, and the safety test for the control algorithm in the advanced safety vehicles and many others.

• Korean Journal of Soil Science and Fertilizer
• /
• v.17 no.2
• /
• pp.147-154
• /
• 1984

Two Fe-hydrous oxide A,B and one Al-hydroxide minerals were synthesized precipitating Fe $Cl_3$ and $AlCl_3$ with alkali solution(NaOH) at pH 6.0, 12.0 and 4.5 respectively, for precise understanding of physico-chemical and surface charge characteristics of soils in which these minerals are dominant. Identification of these final products, effect of free and amorphous materials on X-ray diffraction analysis, particle size distribution and surface change characterics of these minerals were performed. Fe-hydroxide A and B were identified as great deal of X-ray amorphous material and as goethite with large amount of X-ray amorphous material, respectively. Dehydration by oven at $105^{\circ}C$ of these minerals exhibited akaganeite peaks with low X-ray amorphous hump and pure goethite peaks for Fe-hydroxide A and B, respectively. Both minerals, however, turned into hematite upon firing at $550^{\circ}C$. On the other hand, Al-hydroxide identified as mixture of gibbsite and bayerite of around 7:3 ratio. Application of sodium dithionite and ammonium oxalate solutions for removal of free or amorphous Fe and Al from these minerals revealed that only peak intensities of Al-hydroxide system were enhanced upon Al-extraction by oxalate solution even though dithionite solution was much powerful to extract Fe from Fe-hydrous oxide systems. Original(wet) Fe-hydrous oxide A has the highest specific surface and surface charge development(negative and positive), and the greatest amount of less than $2{\mu}m$ sized particles. Specific surface and clay sized particles(less than $2{\mu}m$) of Fe-hydrous oxide A, however, were drastically reduced upon dehydration($P_2O_5$ and oven drying) compare to the rest minerals. The Z.P.C. of these synthetic minerals were 8.0-8.5, 7.5-8.0 and 5.5-6.0 for Fe-hydrous oxide A, B and Al-hydroxide, respectively.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.5 no.1
• /
• pp.1-10
• /
• 2002

Purpose; Dysregulation of gastric epithelial cell proliferation and apoptosis are important in development of ulcer, atrophy and neoplasia in Helicobacter pylori (H. pylori) infection. The aim of this study was to investigate the effect of infection of H. pylori on gastric epithelial cell proliferation and apoptosis in children. Methods: Histological grading by updated Sydney system, PCNA immunostaining and TUNEL method were performed in H. pylori positive (N=58) and negative (N=40) gastric biopsy specimens. Results: In H. pylori positive children, there were significantly higher grade of polymorphonuclear neutrophil activity (P=0.000), chronic inflammation (P=0.000), epithelial damage (P=0.000) and lymphoid follicles (P=0.000) than in H. pylori negative children. Intestinal metaplasia was not seen in H. pylori positive children. PCNA index was significantly different between H. pylori positive children ($67.8{\pm}18.13$) and H. pylori negative children ($54.8{\pm}14.46$, P=0.000). There was positive correlation between PCNA index and H. pylori density (r=0.277, P=0.007), polymorphonuclear neutrophil activity (r=0.280, P=0.007) and chronic inflammation (r=0.284, P=0.006). Apoptosis index of H. pylori positive children ($0.44{\pm}0.447$) was significantly higher than of H. pylori negative children ($0.14{\pm}0.196$, P=0.000). There was positive correlation between apoptosis index and H. pylori density (r=0.472, P=0.000), polymorphonuclear neutrophil activity (r=0.370, P=0.001) and chronic inflammation (r=0.483, P=0.000). There was positive correlation between PCNA index and apoptosis index (r=0.353, P=0.003). Conclusion: The PCNA and apoptosis index in H. pylori positive children were significantly higher than in H. pylori negative children. This study suggested that gastric epithelial cell proliferation and apoptosis are important to pathogenesis of H. pylori infection in children.

• Journal of Animal Environmental Science
• /
• v.7 no.1
• /
• pp.1-12
• /
• 2001

This study was conducted to develope an automatic liquid feeder for early weaning piglets and to test the efficacy of the system. The liquid feeder consists of water heating and discharge unit, dry diet storing and discharge unit, mixing and discharge unit, mixed liquid feed-delivering unit, and the central control part which control each unit, feeding frequency and the amount of feeding. For investigating the possibility of practical use, a feeding trial was carried out using eighteen three way crossbred piglets weaned on 19 days of age for the experimental period of six weeks. Experimental diet was provided in liquid form using the automatic liquid feeder for the first three weeks and in dry form for the later three weeks. The water heating and discharge unit exactly supplied warm water by 27 $m\ell$/s, into the mixing unit. The dry diet storing and discharge unit supplied dry feed by 3.7g/s, into the mixing unit. Being compared with the standard growth rate suggested by NRC, average daily gain of the piglets during the first three weeks of liquid feeding was lower by 10%, while it was higher during three weeks of dry feeding and over the whole experimental period by 24 and 17%, respectively. Feed/gain was 1.09, 2.14 and 1.89 for the first 3 weeks, later 3 weeks, and whole period, respectively. Diarrhea was observed for three days from day 3 to day 7 after feeding liquid diet, but no pig died of it. In conclusion, a preliminary test for the newly developed an automatic liquid feeder using 19 days of age weaning piglets showed that the unit was successfully operated without any major problems. Piglets raised on a liquid diet through the unit developed grew less during the first three weeks, but their growth and feed intake were greatly improved thereafter, indicating the developed automatic liquid feeder may be practically used in swine industry.

• Journal of Food Hygiene and Safety
• /
• v.27 no.4
• /
• pp.366-374
• /
• 2012

Recently pathogenic E. coli is one of the main foodborne pathogens resulting in many patients in Korea. To understand the characteristics of pathogenic E. coli outbreaks in Korea, the epidemiological investigation reports of pathogenic E. coli outbreak in 2009 (41 reports) and in 2010 (27 reports) were collected in the web site of the Korea Centers for Disease Control and Prevention, reviewed and analysed in this study. The main places of the pathogenic E. coli outbreaks were food catering service area (64.8%) and restaurants (25.0%). The main type of the pathogens were EPEC (44.7%) and ETEC (34.2%). EAEC and EHEC was responsible for 10.5 and 9.2%, respectively. Eight of 68 outbreak cases were caused by more than 2 types of pathogenic E. coli which implicates the complicated contamination pathways of pathogenic E. coli. The incidence rate of pathogenic E. coli was $33.6{\pm}30.5%$ and the main symptoms were diarrhea, stomach ache, nausea, vomiting, and fever etc. The two identified food sources were identified as frozen hamburger pattie and squid-vegetable mixture. To improve the food source identification by epidemiological investigation, food poisoning notification to the agency should not be delayed, whole food items attributed the outbreak should be collected and detection method of the various pathogenic E. coli in food has to be improved. In conclusion, the characteristics between the EHEC outbreaks in the western countries and the EPEC or ETEC outbreaks in Korea needs to be distinguished to prepare food safety management plan. In addition, the development of the trace back system to find the contamination pathway with the improved detection method in food and systemic and cooperative support by the related agencies are necessary.