• Journal of the Korean Society of Costume
• /
• v.37
• /
• pp.253-273
• /
• 1998

The culture reflects the ideology of a particular period in time and such values change according to the needs and requests of that time which eventually becomes an important factorin forming the exterior. The clothing is part of a way that composes and expresses the inherent substance of society and culture. Also, the clothing itself manifests the artistic values and behavior of mankind as an external structure maintaining its place as a big part in culture. The purpose of this study are to elucidat the concept of naturalism, which is discussed in many facets in the modern era; I studied the concept as well as the history of naturalism in order to manifest the meaning of clothing in the context of culture and I explained the concept in terms of the modern era. On such ground, I explained the naturalism expressed through clothing and characterized the exter-nal form of clothing. Also, in order to know the stream of naturalism in the modern context, I referred to the Vogue magazine of the 90s, using Delong's ABC method. Naturalism, in the context of modern fashion is a way to express the nostalgia of nature's vi-ability and purity of ecology apart from the artificial and structural appearance that resulted form scientific enhancement and hence, the ecological crisis. Naturalism pursues the soft- ness and comfort of the natural silhouette, color and material of the human body and it can be said that naturalism emphasizes the mix-ture of three substances : human, nature and clothing. The naturalism can be characterized by the factors expressed in clothing as follows. First, the naturalism shown in the form it-self draws the beauty of the bodyline without any reduction nor exaggeration. Without any distorttion of the human bodyline it shown the curve as one moves along, using the soft material. Second, the naturalism shown in color most-ly uses the natural tone with added white color and other color low in intensity and value like the receded colors of the earth that could be compared to the beauty of ecru. Third, the naturalism shown in the material is thin, light and soft in texture. In order to bring out the most natural curve of the human body, the natural fiber becomes the main material, sometimes, using crude materials. Due to the lindustrial improvement, softness and elasticity is added to the natural fibers giving them an important role as materials. Fourth, the naturalism shown in textile depicts the real natural objects in life. According to my study, the personality of naturalism in modern clothing was shown to be most strong in material and then in the order of form, texture and textile. The material com-posed of the natural silhouette and natural fibers were used to make soft color. In form, Paul Poiret made appearance expressing the natural beauty of the human body without the corset ; it continued with the inner lining making the clothing hard but in the 90s, lining-less, extremely exposed clothes and knit wear is used to emphasize the natural beauty of the body. In color and textile, the tendency spok-en above is not as strong but in color, instead of high intensity or value, the usage of neutral colors with added white color or ecru color, ear-th tone is increasing. In textile, the usage of flowers as natural material is seen frequently. As a whole, naturalistic trend in the 90s is increasing and the modern fashion is breaking out from the artificial and architectural form and conforming to a form that can realize the natural beauty of the human body. And the natural color and textile that conforms to such ideas are being used to pursue the human oriented trend that has appeared due to the increase in usage of soft natural fiber. Nowadays, the idea of returning to nature, defying the artificiality, desiring the leisure and psychological abundance that can be explained as naturalistic way of thinking is necessitated in this modern era as long as humans coexist with nature, this tendency will continue in clothing.

• Journal of Korean society of Dental Hygiene
• /
• v.11 no.2
• /
• pp.197-211
• /
• 2011

Objectives : OHIP-14 and EQ-5D were used, targeting the residents of farming communities to identify the elements that influence oral cavity's health and quality of life due to health and to identify the importance of oral cavity's health in order to increase health of adults' oral cavity and quality of life via improved health. Methods : This research was conducted from July 17th, 2010 to August 16th, 2010 targeting 600 residents in Goryeong-gun, Gyeongsangbuk-do, aging over 40. The data has been analyzed using Mann-Whitney U test, Kruskal-Wallis test and hierarchical multiple regression through SPSS Win Program 18.0 version. Results : 1. OHIP-14 and EQ-5D based on general characteristics showed lower oral health-related quality of life and health-related quality of life on the following cases: women (p=0.004, p<0.001), older (p<0.001, p<0.001), lower scholastic ability (p<0.001, p<0.001), lower average of average spending money (p<0.001, p<0.001), higher number of chronic disease (p<0.001, p<0.001), less drinking (p=0.012, p=0.008), lower perceived oral health and health status (p<0.001, p<0.001) and non smoking showed only EQ-5D (p<0.001). 2. OHIP-14 and EQ-5D based on oral health behavior showed lower oral health-related quality of life and health-related quality of life on the following cases: no periodic oral check-up (p<0.001, p<0.001), less experience of oral health education (p<0.001, p<0.001), horizontal tooth-brushing method(p<0.001, p<0.001) and lower frequency of tooth-brushing showed only OHIP-14 (p=0.042). OHIP-14 and EQ-5D based on oral health status and subjective oral symptom showed lower oral health-related quality of life and health-related quality of life on following cases: number of existing tooth less than 20 (p<0.001, p<0.001), the number of missing teeth more than 9 (p<0.001, p=0.044), DMFT (Decay, Missing, Filling Teeth) index more than 18 (p<0.001, p<0.001), wears denture (p<0.001, p<0.001), edentulous (p<0.001, p=0.002), have xerostomia (p<0.001, p<0.001) and have chewing discomfort (p<0.001, p<0.001). 3. Factors affecting OHIP-14 were gender, age, perceived oral health status, perceived health status, number of existing teeth, dental status, xerostomia and chewing discomfort, and the of reliability (how well it explains) the final model was 48.7%. EQ-5D showed relevance on gender, age, presence of chronic disease, perceived health status, xerostomia, chewing discomfort and oral health-related quality of life, and the reliability of the final model was 42.9%. Conclusions : In order to improve the quality of life of ruralists, oral health needs to be improved or remained by increasing the rate of possession of the existing teeth and preventing the loss of teeth. In order to do so, improvement of accessibility of dental clinic, change of direction from treatment-centered to prevention-centered health care system, development of oral health education program and various oral health care policies which would vitalize continuous oral health care system are considered to be necessary.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.33-49
• /
• 2018

The impact of TV Drama success on TV Rating and the channel promotion effectiveness is very high. The cultural and business impact has been also demonstrated through the Korean Wave. Therefore, the early prediction of the blockbuster success of TV Drama is very important from the strategic perspective of the media industry. Previous studies have tried to predict the audience ratings and success of drama based on various methods. However, most of the studies have made simple predictions using intuitive methods such as the main actor and time zone. These studies have limitations in predicting. In this study, we propose a model for predicting the popularity of drama by analyzing the customer's viewing pattern based on various theories. This is not only a theoretical contribution but also has a contribution from the practical point of view that can be used in actual broadcasting companies. In this study, we collected data of 280 TV mini-series dramas, broadcasted over the terrestrial channels for 10 years from 2003 to 2012. From the data, we selected the most highly ranked and the least highly ranked 45 TV drama and analyzed the viewing patterns of them by 11-step. The various assumptions and conditions for modeling are based on existing studies, or by the opinions of actual broadcasters and by data mining techniques. Then, we developed a prediction model by measuring the viewing-time distance (difference) using Euclidean and Correlation method, which is termed in our study similarity (the sum of distance). Through the similarity measure, we predicted the success of dramas from the viewer's initial viewing-time pattern distribution using 1~5 episodes. In order to confirm that the model is shaken according to the measurement method, various distance measurement methods were applied and the model was checked for its dryness. And when the model was established, we could make a more predictive model using a grid search. Furthermore, we classified the viewers who had watched TV drama more than 70% of the total airtime as the "passionate viewer" when a new drama is broadcasted. Then we compared the drama's passionate viewer percentage the most highly ranked and the least highly ranked dramas. So that we can determine the possibility of blockbuster TV mini-series. We find that the initial viewing-time pattern is the key factor for the prediction of blockbuster dramas. From our model, block-buster dramas were correctly classified with the 75.47% accuracy with the initial viewing-time pattern analysis. This paper shows high prediction rate while suggesting audience rating method different from existing ones. Currently, broadcasters rely heavily on some famous actors called so-called star systems, so they are in more severe competition than ever due to rising production costs of broadcasting programs, long-term recession, aggressive investment in comprehensive programming channels and large corporations. Everyone is in a financially difficult situation. The basic revenue model of these broadcasters is advertising, and the execution of advertising is based on audience rating as a basic index. In the drama, there is uncertainty in the drama market that it is difficult to forecast the demand due to the nature of the commodity, while the drama market has a high financial contribution in the success of various contents of the broadcasting company. Therefore, to minimize the risk of failure. Thus, by analyzing the distribution of the first-time viewing time, it can be a practical help to establish a response strategy (organization/ marketing/story change, etc.) of the related company. Also, in this paper, we found that the behavior of the audience is crucial to the success of the program. In this paper, we define TV viewing as a measure of how enthusiastically watching TV is watched. We can predict the success of the program successfully by calculating the loyalty of the customer with the hot blood. This way of calculating loyalty can also be used to calculate loyalty to various platforms. It can also be used for marketing programs such as highlights, script previews, making movies, characters, games, and other marketing projects.

• Sleep Medicine and Psychophysiology
• /
• v.3 no.1
• /
• pp.85-95
• /
• 1996

Obstructive sleep apnea syndrome(OSAS) in childhood is unique and different n-om that in adulthood in several aspects, including pathophysiology, clinical features, diagnostic criteria, complications, management, and prognosis. Characteristic features of childhood OSAS in comparison with the adult form are the variety of severe complications such as developmental delay, more prominent behavioral and cognitive impairments, vivid cardiovascular symptoms, and increased death risk, warranting a special attention to the possible diagnosis of OSAS in children who snore. However, the childhood OSAS is often neglected and unrecognized. We, therefore, report a case of very severe OSAS in a 5-year-old boy who was sucessfully treated with continuous positive airway pressure(CPAP) treatment. Interestingly, the patient was comor-bid with the attention deficit hyperactivity disorder. Prior to the initial visit to us, adenotonsillectomy had been done at the age of 4 with no significant improvement of apneic symptoms and heavy snoring. On the initial diagnostic procedures, marked degree of snoring was audible even in the daytime wake state and the patient was observed to be very hyperactive. Increased pulmonary vascularity with borderline cardiomegaly was noted on chest X-ray. The baseline polysomnography revealed that the patient was very sleep-apneic and snored very heavily, with the respiratory disturbance index(RDI) of 46.9 per hour of sleep, the mean SaO2 of 78.8%, and the lowest SaO2 of 40.0%(the lowest detectable oxygen level by the applied oxymeter). The second night polysomnography was done for CPAP titration and the optimal pressure turned out to be $8.0\;cmH_2O$. The applied CPAP treatment was well tolerated by the patient and was found to be very effective in alleviating heavy snoring and severe repetitive sleep apneas. After 18 months of the CPAP treatment, the patient was followed up with nocturnal polysomnography(baseline and CPAP nights) and clinical examination. Sleep apneas were still present without CPAP on the baseline night. However, the severity of OSAS was significantly decreased(RDI of 15.7, mean SaO2 of 96.2%, and the lowest SaO2 of 83.0%), compared to the initial polysomnographic findings before initiation of long-term CPAP treatment. Wechsler intelligence tests done before and after the CPAP treatment were compared with each other and surprising improvement of intelligence(total 9 points, performance 16 points) was noted. Clinically he was found to be markedly improved in his attention deficit hyperactive behavior after CPAP treatment, but with minimal change of TOVA(test of variables of attention) scores except conversion of reaction time score into normal range. On the chest X-ray taken after 18 months of CPAP application, the initial cardiopulmonary abnormalities were not found at all. We found that the CPAP treatment in a young child is very effective, safe, and well-tolerated and also improves the co-morbid attention deficit hyperactive symptoms. Overall, the growth and development of the child has been facilitated with the long-term use of CPAP. Cardiovascular complications induced by OSAS have been also normalized with CPAP treatment. We suggest that early diagnosis and active treatment intervention of OSAS in children are crucial in preventing and ameliorating possible serious complications caused by repetitive sleep apneas and consequent hypoxic damage during sleep.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.25 no.4
• /
• pp.33-47
• /
• 2022

Wild boars(Sus scrofa) are expanding their range of behavior as their habitats change. Appearing in urban centers and private houses, it caused various social problems, including damage to crops. In order to prevent damage and effectively manage wild boars, there is a need for ecological research considering the characteristics and movement characteristics of wild boars. The purpose of this study is to analyze home range and identify land cover types in key areas through tracking wild boars, and to predict the movement connectivity of wild boars in consideration of previous studies and their preferred land use characteristics. In this study, from January to June 2021, four wild boars were captured and tracked in Jinju city, Gyeongsangnam-do, and the preferred land cover type of wild boars was identified based on the MCP 100%, KDE 95%, and KDE 50% results. As a result of the analysis of the home range for each individual, it was found that 100% of MCP was about 0.68km², 2.77km², 2.42km², and 0.16km², and the three individuals overlapped the home range, refraining from habitat movement and staying in the preferred area. The core areas were analyzed as about 0.55km², 2.05km², 0.82km², and 0.14km² with KDE 95%., and about 0.011km², 0.033km², 0.004km², and 0.003km² with KDE 50%. When the preferred land cover type of wild boar was confirmed based on the results of analysis of the total home range area and core area that combined all individuals, forests were 55.49% (MCP 100%), 54.00% (KDE 95%), 77.69% (KDE 50%), respectively, with the highest ratio, and the urbanization area, grassland, and agricultural area were relatively high. A connectivity scenario was constructed in which the ratio of the land cover type preferred by the analyzed wild boar was reflected as a weight for the resistance value of the connectivity analysis, and this was compared with the connectivity evaluation results analyzed based on previous studies and wild boar characteristics. When the current density values for the wild boar movement data were compared, the average value of the existing scenario was 2.76, the minimum 1.12, and the maximum 4.36, and the weighted scenario had an average value of 2.84, the minimum 0.96, and the maximum 4.65. It was confirmed that, on average, the probability of movement predictability was about 2.90% better even though the weighted scenario had movement restrictions due to large resistance values. It is expected that the identification of the movement route through the movement connectivity analysis of wild boars can be suggested as an alternative to prevent damage by predicting the point of appearance. In the future, when analyzing the connectivity of species including wild boar, it is judged that it will be effective to use movement data on actual species.

• The Korean Journal of Air & Space Law and Policy
• /
• v.25 no.1
• /
• pp.3-26
• /
• 2010

The European Union(EU) has recently introduced its Directive 2008/101/EC to include aviation in the EU ETS(emissions trading system). As an amendment to Directive 2003/87/EC that regulates reduction of the green house gas(GHG) emissions in Europe in preparation for the Kyoto Protocol, 1997, it obliges both EU and non-EU airline operators to reduce the emission of the carbon dioxide(CO2) significantly in the year 2012 and thereafter from the level they made in 2004 to 2006. Emission allowances allowed free of charge for each airline operator is 97% in the first year 2012 and 95% from 2013 and thereafter from the average annual emissions during historical years 2004 to 2006. Taking into account the rapid growth of air traffic, i.e. 5% in recent years, airlines operating to EU have to reduce their emissions by about 30% in order to meet the requirements of the EU Directive, if not buy the emissions right in the emissions trading market. However, buying quantity is limited to 15% in the year 2012 subject to possible increase from the year 2013. Apart from the hard burden of the airline operators, in particular of those from non-European countries, which is not concern of this paper, the EU Directive has certain legal problems. First, while the Kyoto Protocol of universal application is binding on the Annex I countries of the Climate Change Convention, i.e. developed countries including all Member States of the European Union to reduce GHG at least by 5% in the implementation period from 2008 to 2012 over the 1990 level, non-Annex I countries which are not bound by the Kyoto Protocol see their airlines subjected to aircraft emissions reductions scheme of EU when operating to EU. This is against the provisions of the Kyoto Protocol dealing with the emissions of GHG including CO2, target of the EU Directive. While the Kyoto Protocol mandates ICAO to set up a worldwide scheme for aircraft emissions to contribute to stabilizing GHG concentrations in the atmosphere at a level that would prevent dangerous anthropogenic interference with the climate system, the EU ETS was drawn up outside the framework of the international Civil Aviation Organization(ICAO). Second, EU Directive 2008/101 defines 'aviation activities' as covering 'flights which depart from or arrive in the territory of a Member State to which the [EU] Treaty applies'. While the EU airlines are certainly subject to the EU regulations, obliging non-EU airlines to reduce their emissions even if the emissions are produced during the flight over the high seas and the airspace of the third countries is problematic. The point is whether the EU Directive can be legally applied to extra-territorial behavior of non-EU entities. Third, the EU Directive prescribes 2012 as the first year for implementation. However, the year 2012 is the last year of implementation of the Kyoto Protocol for Annex I countries including members of EU to reduce GHG including the emissions of CO2 coming out from domestic airlines operation. Consequently, EU airlines were already on the reduction scheme of CO2 emissions as long as their domestic operations are concerned from 2008 until the year 2012. But with the implementation of Directive 2008/101 from 2012 for all the airlines, regardless of the status of the country Annex I or not where they are registered, the EU airlines are no longer at the disadvantage compared with the airlines of non-Annex I countries. This unexpected premium for the EU airlines may result in a derogation of the Kyoto Protocol at least for the year 2012. Lastly, as a conclusion, the author shed light briefly on how the Korean aviation authorities are dealing with the EU restrictive measures.

• Journal of Korean Medicine Rehabilitation
• /
• v.19 no.2
• /
• pp.125-156
• /
• 2009

Objectives : To research the trend of studies related to rheumatoid arthritis and to indicate the hereafter direction for its study in oriental medicine and its treatment. Methods : I reviewed 75 domestic oriental medical journals, and 50 medical journals about rheumatoid arthritis published after 2004, and comparative analysis was made. And these theses were classified by college, year, field of study, subject. Results : The following are the results of this study. 1. Classified by oriental medical college, Dae-jeon college published the most theses, followed by Dong-guk, Kyung-hee, Se-myung and Dong-shin college. Han-yang college published the most theses among college of medicine. 2. Classified by type of thesis, experimental theses(70 pieces, 94%) showed higher rate than that of clinical theses(4 pieces, 5%) in oriental medical studies. However, in medical studies, clinical theses(34 pieces, 68%) showed higher rate than that of experimental theses(15 pieces, 30%). 3. Analyzed by subject, the most dealt subject in oriental medicine was herb medication, followed by herbal acupuncture, single herb, electroacupuncture, sasang & gene, acupuncture & moxibustion, complex accordingly. The most dealt subject in medical clinical journals was standards of diagnosis & prognosis, followed by medication, gene analysis, pathogenesis, clinical pattern, operative treatment and complication accordingly. 4. In theses related to herb medication, most of the subject was to evaluate anti-inflammatory and immunoregulatory effects of herb medication with geopungseup, jibitong, hwalhyeolgeoer function. The tendency of experimental methods was focusing on understanding anti-inflammatory and immunoregulatory mechanisms through molecular biologic methods by analyzing cytokine and gene. 5. Most of theses related to herbal acupuncture were experimental studies verifying ant-inflammatory and immnoregulatory effects through methods observing change of cytokine and immunoregulatory factors. Regarding remedies for herbal acupuncture, Ulmus davidiana Planch was most preferred, followed by bee venom. 6. In theses related to single herb, Boik-yak was most prefered, followed by Geopungseup-yak and Hwalhyeolgeoer-yak. Regarding methods of research, there were tendency of shifting from methods verifying travail, anti-inflammatory and anti-pyretic effects through a test of behavior, morphometry, serology and temperature measurement of the rectum and the skin into verifying anti-inflammatory and immunoregulatory effects through observing inflammatory cytokine in the joint and cells of spleen. 7. In theses related to electroacupuncture, ST36 and adjuvant were most preferred as acupoints and induced factor. The tendency of experimental methods was turning from verifying mechanism of travail effect to analyzing inflammation and pain inducing factors. 8. Diverse medical clinical studies were published. Subjects such as diagnosis and prognosis, medication, gene analysis, clinical pattern, operational treatment, complication and pathogenesis were published. Especially, studies about standards of early diagnosis, and research on possible parallel medications with methotrexate were actively inquired. 9. Most of theses related to medical experimental studies was about mediators and receptors related to inflammatory induction and osteoclasia mechanism. Also, it was presented blockage of them can be effective on rheumatoid arthritis. Conclusions : The oriental medicine studies have merit in its diversity of treatment, but it clinical studies is lacking compared to experimental studies. Also, more diversity of subjects is necessary. Therefore, complementary measures are needed. Hereafter, oriental medicine research about rheumatoid arthritis needs more clinical research verifying the effectiveness and safety in clinical field. Also, we require oriental medical standard of diagnosis and researches on pathological generation which would make early checkup and prognosis possible.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.21 no.12
• /
• pp.715-732
• /
• 2009

This article reviews the papers published in the Korean Journal of Air-Conditioning and Refrigeration Engineering during 2008. It is intended to understand the status of current research in the areas of heating, cooling, ventilation, sanitation, and indoor environments of buildings and plant facilities. Conclusions are as follows. (1) Research trends in thermal and fluid engineering have been surveyed in the categories of general fluid flow, fluid machinery and piping, new and renewable energy, and fire. Well-developed CFD technologies were widely applied in developing facilities and their systems. New research topics include fire, fuel cell, and solar energy. Research was mainly focused on flow distribution and optimization in the fields of fluid machinery and piping. Topics related to the development of fans and compressors had been popular, but were no longer investigated widely. Research papers on micro heat exchangers using nanofluids and micro pumps were also not presented during this period. There were some studies on thermal reliability and performance in the fields of new and renewable energy. Numerical simulations of smoke ventilation and the spread of fire were the main topics in the field of fire. (2) Research works on heat transfer presented in 2008 have been reviewed in the categories of heat transfer characteristics, industrial heat exchangers, and ground heat exchangers. Research on heat transfer characteristics included thermal transport in cryogenic vessels, dish solar collectors, radiative thermal reflectors, variable conductance heat pipes, and flow condensation and evaporation of refrigerants. In the area of industrial heat exchangers, examined are research on micro-channel plate heat exchangers, liquid cooled cold plates, fin-tube heat exchangers, and frost behavior of heat exchanger fins. Measurements on ground thermal conductivity and on the thermal diffusion characteristics of ground heat exchangers were reported. (3) In the field of refrigeration, many studies were presented on simultaneous heating and cooling heat pump systems. Switching between various operation modes and optimizing the refrigerant charge were considered in this research. Studies of heat pump systems using unutilized energy sources such as sewage water and river water were reported. Evaporative cooling was studied both theoretically and experimentally as a potential alternative to the conventional methods. (4) Research papers on building facilities have been reviewed and divided into studies on heat and cold sources, air conditioning and air cleaning, ventilation, automatic control of heat sources with piping systems, and sound reduction in hydraulic turbine dynamo rooms. In particular, considered were efficient and effective uses of energy resulting in reduced environmental pollution and operating costs. (5) In the field of building environments, many studies focused on health and comfort. Ventilation. system performance was considered to be important in improving indoor air conditions. Due to high oil prices, various tests were planned to examine building energy consumption and to cut life cycle costs.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.99-112
• /
• 2010

Ensemble learning is a method for improving the performance of classification and prediction algorithms. It is a method for finding a highly accurateclassifier on the training set by constructing and combining an ensemble of weak classifiers, each of which needs only to be moderately accurate on the training set. Ensemble learning has received considerable attention from machine learning and artificial intelligence fields because of its remarkable performance improvement and flexible integration with the traditional learning algorithms such as decision tree (DT), neural networks (NN), and SVM, etc. In those researches, all of DT ensemble studies have demonstrated impressive improvements in the generalization behavior of DT, while NN and SVM ensemble studies have not shown remarkable performance as shown in DT ensembles. Recently, several works have reported that the performance of ensemble can be degraded where multiple classifiers of an ensemble are highly correlated with, and thereby result in multicollinearity problem, which leads to performance degradation of the ensemble. They have also proposed the differentiated learning strategies to cope with performance degradation problem. Hansen and Salamon (1990) insisted that it is necessary and sufficient for the performance enhancement of an ensemble that the ensemble should contain diverse classifiers. Breiman (1996) explored that ensemble learning can increase the performance of unstable learning algorithms, but does not show remarkable performance improvement on stable learning algorithms. Unstable learning algorithms such as decision tree learners are sensitive to the change of the training data, and thus small changes in the training data can yield large changes in the generated classifiers. Therefore, ensemble with unstable learning algorithms can guarantee some diversity among the classifiers. To the contrary, stable learning algorithms such as NN and SVM generate similar classifiers in spite of small changes of the training data, and thus the correlation among the resulting classifiers is very high. This high correlation results in multicollinearity problem, which leads to performance degradation of the ensemble. Kim,s work (2009) showedthe performance comparison in bankruptcy prediction on Korea firms using tradition prediction algorithms such as NN, DT, and SVM. It reports that stable learning algorithms such as NN and SVM have higher predictability than the unstable DT. Meanwhile, with respect to their ensemble learning, DT ensemble shows the more improved performance than NN and SVM ensemble. Further analysis with variance inflation factor (VIF) analysis empirically proves that performance degradation of ensemble is due to multicollinearity problem. It also proposes that optimization of ensemble is needed to cope with such a problem. This paper proposes a hybrid system for coverage optimization of NN ensemble (CO-NN) in order to improve the performance of NN ensemble. Coverage optimization is a technique of choosing a sub-ensemble from an original ensemble to guarantee the diversity of classifiers in coverage optimization process. CO-NN uses GA which has been widely used for various optimization problems to deal with the coverage optimization problem. The GA chromosomes for the coverage optimization are encoded into binary strings, each bit of which indicates individual classifier. The fitness function is defined as maximization of error reduction and a constraint of variance inflation factor (VIF), which is one of the generally used methods to measure multicollinearity, is added to insure the diversity of classifiers by removing high correlation among the classifiers. We use Microsoft Excel and the GAs software package called Evolver. Experiments on company failure prediction have shown that CO-NN is effectively applied in the stable performance enhancement of NNensembles through the choice of classifiers by considering the correlations of the ensemble. The classifiers which have the potential multicollinearity problem are removed by the coverage optimization process of CO-NN and thereby CO-NN has shown higher performance than a single NN classifier and NN ensemble at 1% significance level, and DT ensemble at 5% significance level. However, there remain further research issues. First, decision optimization process to find optimal combination function should be considered in further research. Secondly, various learning strategies to deal with data noise should be introduced in more advanced further researches in the future.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.45-67
• /
• 2016

Given the recent development of smart devices, users are producing, sharing, and acquiring a variety of information via the Internet and social network services (SNSs). Because users tend to use multiple media simultaneously according to their goals and preferences, domestic SNS users use around 2.09 media concurrently on average. Since the information provided by such media is usually textually represented, recent studies have been actively conducting textual analysis in order to understand users more deeply. Earlier studies using textual analysis focused on analyzing a document's contents without substantive consideration of the diverse characteristics of the source medium. However, current studies argue that analytical and interpretive approaches should be applied differently according to the characteristics of a document's source. Documents can be classified into the following types: informative documents for delivering information, expressive documents for expressing emotions and aesthetics, operational documents for inducing the recipient's behavior, and audiovisual media documents for supplementing the above three functions through images and music. Further, documents can be classified according to their contents, which comprise facts, concepts, procedures, principles, rules, stories, opinions, and descriptions. Documents have unique characteristics according to the source media by which they are distributed. In terms of newspapers, only highly trained people tend to write articles for public dissemination. In contrast, with SNSs, various types of users can freely write any message and such messages are distributed in an unpredictable way. Again, in the case of newspapers, each article exists independently and does not tend to have any relation to other articles. However, messages (original tweets) on Twitter, for example, are highly organized and regularly duplicated and repeated through replies and retweets. There have been many studies focusing on the different characteristics between newspapers and SNSs. However, it is difficult to find a study that focuses on the difference between the two media from the perspective of supply and demand. We can regard the articles of newspapers as a kind of information supply, whereas messages on various SNSs represent a demand for information. By investigating traditional newspapers and SNSs from the perspective of supply and demand of information, we can explore and explain the information dilemma more clearly. For example, there may be superfluous issues that are heavily reported in newspaper articles despite the fact that users seldom have much interest in these issues. Such overproduced information is not only a waste of media resources but also makes it difficult to find valuable, in-demand information. Further, some issues that are covered by only a few newspapers may be of high interest to SNS users. To alleviate the deleterious effects of information asymmetries, it is necessary to analyze the supply and demand of each information source and, accordingly, provide information flexibly. Such an approach would allow the value of information to be explored and approximated on the basis of the supply-demand balance. Conceptually, this is very similar to the price of goods or services being determined by the supply-demand relationship. Adopting this concept, media companies could focus on the production of highly in-demand issues that are in short supply. In this study, we selected Internet news sites and Twitter as representative media for investigating information supply and demand, respectively. We present the notion of News Value Index (NVI), which evaluates the value of news information in terms of the magnitude of Twitter messages associated with it. In addition, we visualize the change of information value over time using the NVI. We conducted an analysis using 387,014 news articles and 31,674,795 Twitter messages. The analysis results revealed interesting patterns: most issues show lower NVI than average of the whole issue, whereas a few issues show steadily higher NVI than the average.