• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.25-41
• /
• 2014

Recently, the number of social media users has increased rapidly because of the prevalence of smart devices. As a result, the amount of real-time data has been increasing exponentially, which, in turn, is generating more interest in using such data to create added value. For instance, several attempts are being made to analyze the relevant search keywords that are frequently used on new portal sites and the words that are regularly mentioned on various social media in order to identify social issues. The technique of "topic analysis" is employed in order to identify topics and themes from a large amount of text documents. As one of the most prevalent applications of topic analysis, the technique of issue tracking investigates changes in the social issues that are identified through topic analysis. Currently, traditional issue tracking is conducted by identifying the main topics of documents that cover an entire period at the same time and analyzing the occurrence of each topic by the period of occurrence. However, this traditional issue tracking approach has two limitations. First, when a new period is included, topic analysis must be repeated for all the documents of the entire period, rather than being conducted only on the new documents of the added period. This creates practical limitations in the form of significant time and cost burdens. Therefore, this traditional approach is difficult to apply in most applications that need to perform an analysis on the additional period. Second, the issue is not only generated and terminated constantly, but also one issue can sometimes be distributed into several issues or multiple issues can be integrated into one single issue. In other words, each issue is characterized by a life cycle that consists of the stages of creation, transition (merging and segmentation), and termination. The existing issue tracking methods do not address the connection and effect relationship between these issues. The purpose of this study is to overcome the two limitations of the existing issue tracking method, one being the limitation regarding the analysis method and the other being the limitation involving the lack of consideration of the changeability of the issues. Let us assume that we perform multiple topic analysis for each multiple period. Then it is essential to map issues of different periods in order to trace trend of issues. However, it is not easy to discover connection between issues of different periods because the issues derived for each period mutually contain heterogeneity. In this study, to overcome these limitations without having to analyze the entire period's documents simultaneously, the analysis can be performed independently for each period. In addition, we performed issue mapping to link the identified issues of each period. An integrated approach on each details period was presented, and the issue flow of the entire integrated period was depicted in this study. Thus, as the entire process of the issue life cycle, including the stages of creation, transition (merging and segmentation), and extinction, is identified and examined systematically, the changeability of the issues was analyzed in this study. The proposed methodology is highly efficient in terms of time and cost, as it sufficiently considered the changeability of the issues. Further, the results of this study can be used to adapt the methodology to a practical situation. By applying the proposed methodology to actual Internet news, the potential practical applications of the proposed methodology are analyzed. Consequently, the proposed methodology was able to extend the period of the analysis and it could follow the course of progress of each issue's life cycle. Further, this methodology can facilitate a clearer understanding of complex social phenomena using topic analysis.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.48 no.2
• /
• pp.20-33
• /
• 2020

This study aims to examine the trends in the preservation of urban public parks with a focus on the international movement to acknowledge and preserve the heritage value of urban parks. First, the background in which the concept of "historic urban park" first appeared internationally, as well as the current situation were investigated. Then, the cases of the United Kingdom (UK), the United States (US), and Japan, all of which are already preserving and managing urban public parks, were analyzed. In the ICOMOS-IFLA Document on Historic Urban Public Parks, the International Council on Monuments and Sites (ICOMOS), which is a group of specialists dedicated to the conservation and management of cultural heritage, mentions that it is necessary to maintain the social, intangible, aesthetic, ecological, and civic values of historic urban public parks. In addition, according to ICOMOS, it is necessary to preserve elements of parks, such as space composition, topography, light, and environment. The UK, the USA, and Japan have their own unique characteristics for the background of preserving urban parks, the preservation system, the selection of parks to be preserved, and the elements to be preserved within the park. The UK has categorized parks into certain types from each period and has tried to preserve the common elements in each type. The US has selected the parks to preserve by determining the meaning of the parks itself considering multiple aspects, embracing not only the physical form of the parks, but also the culture, monumentality, and social values. Recently, Japan began the preservation of historic urban parks as a matter of policy and started to implement a preservation policy by investigating modern parks that are believed to be worth preserving. Specialists in cultural heritage preservation have argued that the method of preservation of historic urban parks must differ from that of other parks or gardens. Nonetheless, observing cases in these three countries showed that, regardless of their administrative and legal systems regarding cultural heritage and urban public parks, their policies were still limited to preserving only the physical elements of parks. The direction and methodology for the preservation of historic urban parks must be developed further and elaborated upon in terms of the evolving concept and definition of heritage. Urban parks are where various historic values are accumulated, connoting historical meanings dealing with the memories of the parks and the urban dwellers. This study found that, worldwide, park management has been carried out in a way that the historic values of parks are respected and preserved. This global trend in preserving the historic values of urban public parks has significant implications for the management of urban public parks in Korea that are being formed and renewed repeatedly.

• Journal of Korean Ophthalmic Optics Society
• /
• v.9 no.2
• /
• pp.333-343
• /
• 2004

Impression cytology refers to application of cellulose acetate filter material to the ocular surface to remove the superficial layers of the conjunctival epithelium. The technique is non-invasive, is easy to perform, causes minimal discomfort to the patient, and can be used to follow changes in the conjunctival ocular surface over time. With this method, the morphology of the conjunctival ocular surface can be studied and the degree of squmaous metaplasia assessed. This study was performed to evaluate the conjunctival surface by impression cytology in dry eye patients. A total of 70 students with no contact lens wearing history were recruited. Subjects were required to fill in a McMonnies dry eye symptom questionnaire. The non-invasive tear thinning time(TIT) test of each subject was measured, followed by Schirmer tear test(STI), tear film break-up time(TBUT) tests and Rose-bengal staining were performed as a baseline. Conjunctival epithelial cells from the inferior bulbar conjunctiva were harvested by the impression cytology technique. The specimens collected were labelled and stained with PAS(Periodic Acid Schift)-haematoxylin. The goblet cells and conjunctival epithelial cells were observed under a light microscope of 400x magnification. The specimens were classified according to the Nelson Grading scale which was based on the degree of squamous metaplasia such as changes of goblet cells density, size/form, N:C(nucleus : cytoplasm) ratio. Dry eye patients were observed morphological changes of the epithelial cells, different nuclear alterations, decrease of the goblet cells density. The degree of cytological changes was related to severity of dry eye conditions. When the epithelial cell morphology was graded according to the system described by Nelson, specimens from the control group revealed 91.43% of the eyes to be grade 0 and 8.57% to be grade 1, whereas of the dry eye patients, 20% were grade 0, 42.86% grade 1, 34.29% grade 2 and 2,86% grade 3. Impression cytology represents a non- or minimally invasive biopsy of the ocular surface epithelium with no side effects or contraindications. It has demonstrated to be a useful diagnostic aid for a wide variety of processes involving the ocular surface. This technique is a safe, simple method and may help increase understanding of various ocular surface alterations in dry eye patients.

• Journal of the Korean Society of Costume
• /
• v.18
• /
• pp.111-131
• /
• 1992

This thesis was designed to study Symbolics of Chinese Liturgical Vestments. Chinese who regarded the life of human beings as the combination of heaven and earth considered garments as the traditional product of the movement of nature. Accordingly, they thought human beings are the center of the universe composed by heaven and earth and the chief of all things; therefore man only can utilize clothes to distinguish from all of the colours. This views of clothes led to the development of liturgical vestments esteemed courtesy than anything else, especially the thought of courtesy associated with Conficius who regarded courtesy as the highest things and since then the theory of Five Elements and courtesy were inherited by all the adherents of Conficius. Yin and Yang Five Elements in the liturgical vestments was given absolute symbolics in both formative side and in colourful side. results of research studied in this was can be summed up as follows : 1. The crown of rites was made imitating after the system of head, horn, beard, bread of birds and beasts and that form of crown is front-circ-ular and back-rectangular meant to be towards light and dark. That the upper part of faceplace is black represented the way of heaven and lower part of red symbolized the way of earth. 2. Upper vestment of liturgical rites symbolizes heaven and outskirt represented earth. So front of outskirt is YANG and back is Yin. It is why then are going to harmonize positive and negative making front part three width and back part four width. Therefore, emperor who symbolizes heaven made the subjects recognize high and low and wore Dae-gu(大 ), Kon-bok(袞服), Bel-bok, Chui-bok, and Hyonbok according to the object and position of rites so that he may rule the country based on courtesy. 3. As an accessory of liturgical vestments, Bul, Pae-ok, Su, Dae-dai, Hyok-Dai, Kyu, and Hol were used. Before Bul was used man dressed skirt as the first waist-dress in order to conceal intimate part of the body. Pae-ok, as decoration blended with jade was worn by men of virtue, so men of virtue symbolized morality and virtue by Pae-ok. Su began from Yeok, connected with Pae-su , in Chou-dynasty is said to be originated by practical needs and they are divided into large Su and small su, and maintained as decoration to signify the class positions. Dae-dai did the work as not to loose the liturgical vestments and leather belt hang Bul and Su to begin as the function of practical use are in later years it became decoration to symboliz e the class position. Kyu was a jade used when empeor nominated feudal lords and observe ceremony to God and Hol, was held in hands to record everything not to forget. These Kyu and Hol became to offer courtesy during the time of rites and in later years it became used according to class position rather than practical use. 4. As far as colours are concerned, colours based by five colours according to YIN-YANG Five Elements theory and they were divided into a primary colour and a secondary colours. Primary colours corresponded with the theory of Five Elements each other, Blue, Red, Tellow, White, and Black symbolized ive Elements, five hour space, five directions, and five emperors. Secondary colours contradict with Blue, Red, Yellow, White and Black and another as a primary colour and they are Green, Scaret, Indigo, Violet, Hun colour, Chu colour, and Chi colour. This primary colour was used in liturgical vestments, that is, upper-vestments used black colour. This primary colour was used in liturgical vestments, that is, upper-vestments used black colour as primary colour and outskirt was used Hun colour as secondary colours. Thus symbolism in chinese liturgical vestments mainly began with heaven and earth and corresponded with YIN-YANG Five Elements Scool. They were developed as the scholary theory and Conficius and his followers in the later days and continued up to Min-dynasty.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2004.11a
• /
• pp.122-125
• /
• 2004

In radiotherapy of tumors in liver, enough planning target volume (PTV) margins are necessary to compensate breathing-related movement of tumor volumes. To overcome the problems, this study aims to obtain patients' body movements by using a moving phantom and an ultrasonic sensor, and to develop respiration gating techniques that can adjust patients' beds by using reversed values of the data obtained. The phantom made to measure patients' body movements is composed of a microprocessor (BS II, 20 MHz, 8K Byte), a sensor (Ultra-Sonic, range 3 cm ${\sim}$3 m), host computer (RS232C) and stepping motor (torque 2.3Kg) etc., and the program to control and operate it was developed. The program allows the phantom to move within the maximum range of 2 cm, its movements and corrections to take place in order, and x, y and z to move successively. After the moving phantom was adjusted by entering random movement data(three dimensional data form with distance of 2cm), and the phantom movements were acquired using the ultra sonic sensor, the two data were compared and analyzed. And then, after the movements by respiration were acquired by using guinea pigs, the real-time respiration gating techniques were drawn by operating the phantom with the reversed values of the data. The result of analyzing the acquisition-correction delay time for the three types of data values and about each value separately shows that the data values coincided with one another within 1% and that the acquisition-correction delay time was obtained real-time (2.34 ${\times}$ 10$^{-4}$sec). This study successfully confirms the clinic application possibility of respiration gating techniques by using a moving phantom and an ultra sonic sensor. With ongoing development of additional analysis system, which can be used in real-time set-up reproducibility analysis, it may be beneficially used in radiotherapy of moving tumors.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.16 no.3
• /
• pp.202-210
• /
• 2013

As incomes increase, interest in ocean leisure picks up. As a result, a lot of research and developments on hull form design and production of planing boats, mostly used for ocean leisure, are needed. Analysis in researches on resistance of planing boats shows that resistance characteristic of planing boats is different from resistance characteristic of general boats because the former is fast, and its wetted surface is very small. Using Savitsky formula widely used in the calculation of effective horse power in shipbuildingyards, and propulsion system and engine manufacturers, this study calculated total resistance of a research planing boat. Then it analyzed the flow characteristics of the planing boat through theoretical analysis and wind tunnel experiment, and computed air resistance and lift force by changes of speed and trim angle. It also compared and analyzed result of theoretical analysis and experiment of the ratio of air resistance to total resistance under variations of velocity and trim angle. When the study is used to estimate more accurate effective horse power, it is expected to remedy abuses of unnecessarily installing high-powered engine. As nature disasters due to abnormal changes of weather increase, interest in greenhouse gas grows. International Maritime Organization (IMO) legislated Energy Efficiency Design Index (EEDI) and Energy Efficiency Operational Indicator (EEOI) to reduce ship greenhouse gas emissions. But this index will be applied to over 400 tons ships, small ships, emitting more greenhouse gases than larege ships per unit power, will dodge the regulations. Thus, this study indicated a problem by calculating greenhouse gas emissions of an ocean leisure planning boat (a small ship), and suggested the need for EEDI of small ships.

• Korean Journal of Food Science and Technology
• /
• v.41 no.5
• /
• pp.552-559
• /
• 2009

In this study, the anticancer activity of the water extract at $100^{\circ}C$ was compared to that of the callus extracts via a ultrasonification extraction process. All the extracts were utilized to evaluate cytotoxicity, antioxidant and immune activities. The callus extracted via ultrasonification extraction showed relatively low cytotoxicity on normal human cell lines, HEK293 and HEL299, showing 13.17% and 21.78%, respectively. The callus extract has 59.82% which was similar to 61.70% for water extracts. It was also found that callus extract yielded higher nitric oxide secretion form macrophage than other extracts. The growths of both human stomach adenocarcinoma (AGS) cell and human lung carcinoma (A549) were inhibited up to 70% by adding 1.0 mg/mL of the callus extracts with ultrasonification extraction. This inhibition ratio (70%) was almost close to that of water extract. Human hepatoma carcinoma (HEP3B) cell growth was most significantly inhibited up to 75% by adding 1.0 mg/mL of callus extracts, and its selectivity was highest compared to other extracts. It indicates that the callus extracts could selectively inhibit growth of digestive system-related cancer cells. It can be also concluded from the results of this study that the callus extracts associated with ultrasonification extraction process have the potential for anticancer activity.

• Clinical and Experimental Pediatrics
• /
• v.50 no.9
• /
• pp.912-918
• /
• 2007

Purpose : Breast milk contains several components that provide specific immunity and affect the maturation of the infant's immune system. Allergic disease (AD), including atopic eczema, asthma, allergic rhinitis, and food allergy is characterized by an imbalance between cytokines produced by distinct T-helper cell subtypes. The aim of the study was to investigate the concentrations of cytokines and chemokines that were involved in allergic reactions in breast milk from allergic and nonallergic mothers and then analyse the effect of breastfeeding duration on the prevalence of allergic disease in the age of two. Methods : The breast milk samples were collected from mothers with AD (n=88) and without AD (n=47). Breast milk was collected at the second day (colostrum) and four weeks later (mature milk).The level of Interlukine (IL)-4, IL-5, IL-6, IL-8, IL-10, IL-13, $TGF-{\beta}1$, $TGF-{\beta}2$, RANTES in breast milk were determined by commercially available enzyme-linked immunosorbent assay (ELISA) kits according to the manufacturer's instructions. Results : Mothers with AD had a higher concentration of IL-8 in colostrum compared with those without AD (P=0.021). But, $TGF-{\beta}1$ and $TGF-{\beta}2$ were higher concentrated in colostrum of mother without AD (P=0.013, P=0.001). Whereas concentrations of other cytokines were not significantly different between the two groups. There was no association between levels of cytokines and chemokines in the breast milk and allergic development during the first 2 years of life in the infants. Conclusion : The higher concentration of $TGF-{\beta}1$ and $TGF-{\beta}2$ in colostrum from non-allergic mothers may explain the protective effect. But, the higher concentrations of IL-8 in colostrum from allergic mothers may in part explain the controversial results on the protective effect of breastfeeding against allergic diseases. We conclude that there is no convincing evidence form a relation between cytokines in breast milk and allergic diseases in infants. Longer follow-up are necessary to evaluate the effects of breast milk components on AD.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.227-240
• /
• 2011

New concepts and ideas often result from extensive recombination of existing concepts or ideas. Both researchers and developers build on existing concepts and ideas in published papers or registered patents to develop new theories and technologies that in turn serve as a basis for further development. As the importance of patent increases, so does that of patent analysis. Patent analysis is largely divided into network-based and keyword-based analyses. The former lacks its ability to analyze information technology in details while the letter is unable to identify the relationship between such technologies. In order to overcome the limitations of network-based and keyword-based analyses, this study, which blends those two methods, suggests the keyword network based analysis methodology. In this study, we collected significant technology information in each patent that is related to Light Emitting Diode (LED) through text mining, built a keyword network, and then executed a community network analysis on the collected data. The results of analysis are as the following. First, the patent keyword network indicated very low density and exceptionally high clustering coefficient. Technically, density is obtained by dividing the number of ties in a network by the number of all possible ties. The value ranges between 0 and 1, with higher values indicating denser networks and lower values indicating sparser networks. In real-world networks, the density varies depending on the size of a network; increasing the size of a network generally leads to a decrease in the density. The clustering coefficient is a network-level measure that illustrates the tendency of nodes to cluster in densely interconnected modules. This measure is to show the small-world property in which a network can be highly clustered even though it has a small average distance between nodes in spite of the large number of nodes. Therefore, high density in patent keyword network means that nodes in the patent keyword network are connected sporadically, and high clustering coefficient shows that nodes in the network are closely connected one another. Second, the cumulative degree distribution of the patent keyword network, as any other knowledge network like citation network or collaboration network, followed a clear power-law distribution. A well-known mechanism of this pattern is the preferential attachment mechanism, whereby a node with more links is likely to attain further new links in the evolution of the corresponding network. Unlike general normal distributions, the power-law distribution does not have a representative scale. This means that one cannot pick a representative or an average because there is always a considerable probability of finding much larger values. Networks with power-law distributions are therefore often referred to as scale-free networks. The presence of heavy-tailed scale-free distribution represents the fundamental signature of an emergent collective behavior of the actors who contribute to forming the network. In our context, the more frequently a patent keyword is used, the more often it is selected by researchers and is associated with other keywords or concepts to constitute and convey new patents or technologies. The evidence of power-law distribution implies that the preferential attachment mechanism suggests the origin of heavy-tailed distributions in a wide range of growing patent keyword network. Third, we found that among keywords that flew into a particular field, the vast majority of keywords with new links join existing keywords in the associated community in forming the concept of a new patent. This finding resulted in the same outcomes for both the short-term period (4-year) and long-term period (10-year) analyses. Furthermore, using the keyword combination information that was derived from the methodology suggested by our study enables one to forecast which concepts combine to form a new patent dimension and refer to those concepts when developing a new patent.