• Journal of Science of Art and Design
• /
• v.10
• /
• pp.5-50
• /
• 2006

The terminology "human body" simply means a physical body but also more often, as an object in art works, carries symbolic concepts incorporating the whole history of human lives. Human body has been employed as an artistic object capturing physical body, delivering artist's idea expressing life indicators from different standpoints of times and places. This point of view about human body in art works has in fact rather short history since 1960's when modern thinking paradigm focusing upon rationality and reasoning has begun declining and on the contrary when the body used to be the servant of the mind and soul for a long time has begun attracting artist's attention as a real entity from the viewpoint of dichotomy. During the 1960's, frequent performances in Pop art and of Fluxus showed that the human body has been an important media for artistic communication after importance of body performances had been raised in Action painting in 1940's. The human body became a more determined media in body art works that had got into stride after Yves Kline's conceptual works applying body and its traces. These kinds of art works have continued and consolidated into the Feminism came into blossom in 1980's and into fragmentated and disembodied body art trend in 1990's. Through development of trends in body works, human body now might well be regarded as a clue provide from individual identity with implication over the world. This thesis is to analyse in semiotic way main works of Kiki Smith who is a representative artist devoting to Feminism and proposing extended significance of human body. In the analysis process of works done by two great artists with histrorical background of art trend in order to find and open an significance horizon of human body, semiotics and bodism are therefore perceived as pertinent and applied as basic tools. The first stage of analysis is to get the significances emerged in between expression part and contextual parts, which are separated structually from the most basic level. The study deals with body works furthermore in the way of structual cohesion of the expression and the context from the view of A J. Greimas' Structural Semantics and tried to build up a basic frame for the extended significances of human body. This thesis is, on the other hand, to attempt to contribute for extension of disembodied and fragmentated body discussed in the structural semantic frame earlier by Julia Kriesteva who delivers abjection concepts and phenomenology of Maurice Merleau-Ponty who enables to overview relationship between the body and the world from the viewpoint of Bodism, further into interpretation level. The other works are Kiki smith's that showed epics about death in mid-1980's, detailed humbleness of vulnerable human body exposed to dichotomy and fragmentation in 1990's and religion and mythology incorporating wouln healing in 2000's and henceforth. Through the analysis of Kiki Smith's representative work 'Pee body', it is verified and confirmed that fragmentated body showed beyond boundary gap of the human body and ultimately tends to imply human healing owing to divine maternity. Bodily symbols in Kiki Smith's are extended to the universal world to imply human life and death on the one hand and religion and mythology of human wound and divine healing one the other hand. This thesis through these process and results of analysis is in a broad context, to emphasize that human body as objectified text has a key indicator role to understand world as well as semiotic extension in art works in late 20th century so that we might confirm bodily symbol as a cultural context constitutes a section of contemporary visual arts.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• Information Systems Review
• /
• v.16 no.3
• /
• pp.161-177
• /
• 2014

Corporate credit rating assessment consists of complicated processes in which various factors describing a company are taken into consideration. Such assessment is known to be very expensive since domain experts should be employed to assess the ratings. As a result, the data-driven corporate credit rating prediction using statistical and artificial intelligence (AI) techniques has received considerable attention from researchers and practitioners. In particular, statistical methods such as multiple discriminant analysis (MDA) and multinomial logistic regression analysis (MLOGIT), and AI methods including case-based reasoning (CBR), artificial neural network (ANN), and multiclass support vector machine (MSVM) have been applied to corporate credit rating.2) Among them, MSVM has recently become popular because of its robustness and high prediction accuracy. In this study, we propose a novel optimized MSVM model, and appy it to corporate credit rating prediction in order to enhance the accuracy. Our model, named 'GAMSVM (Genetic Algorithm-optimized Multiclass Support Vector Machine),' is designed to simultaneously optimize the kernel parameters and the feature subset selection. Prior studies like Lorena and de Carvalho (2008), and Chatterjee (2013) show that proper kernel parameters may improve the performance of MSVMs. Also, the results from the studies such as Shieh and Yang (2008) and Chatterjee (2013) imply that appropriate feature selection may lead to higher prediction accuracy. Based on these prior studies, we propose to apply GAMSVM to corporate credit rating prediction. As a tool for optimizing the kernel parameters and the feature subset selection, we suggest genetic algorithm (GA). GA is known as an efficient and effective search method that attempts to simulate the biological evolution phenomenon. By applying genetic operations such as selection, crossover, and mutation, it is designed to gradually improve the search results. Especially, mutation operator prevents GA from falling into the local optima, thus we can find the globally optimal or near-optimal solution using it. GA has popularly been applied to search optimal parameters or feature subset selections of AI techniques including MSVM. With these reasons, we also adopt GA as an optimization tool. To empirically validate the usefulness of GAMSVM, we applied it to a real-world case of credit rating in Korea. Our application is in bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. The experimental dataset was collected from a large credit rating company in South Korea. It contained 39 financial ratios of 1,295 companies in the manufacturing industry, and their credit ratings. Using various statistical methods including the one-way ANOVA and the stepwise MDA, we selected 14 financial ratios as the candidate independent variables. The dependent variable, i.e. credit rating, was labeled as four classes: 1(A1); 2(A2); 3(A3); 4(B and C). 80 percent of total data for each class was used for training, and remaining 20 percent was used for validation. And, to overcome small sample size, we applied five-fold cross validation to our dataset. In order to examine the competitiveness of the proposed model, we also experimented several comparative models including MDA, MLOGIT, CBR, ANN and MSVM. In case of MSVM, we adopted One-Against-One (OAO) and DAGSVM (Directed Acyclic Graph SVM) approaches because they are known to be the most accurate approaches among various MSVM approaches. GAMSVM was implemented using LIBSVM-an open-source software, and Evolver 5.5-a commercial software enables GA. Other comparative models were experimented using various statistical and AI packages such as SPSS for Windows, Neuroshell, and Microsoft Excel VBA (Visual Basic for Applications). Experimental results showed that the proposed model-GAMSVM-outperformed all the competitive models. In addition, the model was found to use less independent variables, but to show higher accuracy. In our experiments, five variables such as X7 (total debt), X9 (sales per employee), X13 (years after founded), X15 (accumulated earning to total asset), and X39 (the index related to the cash flows from operating activity) were found to be the most important factors in predicting the corporate credit ratings. However, the values of the finally selected kernel parameters were found to be almost same among the data subsets. To examine whether the predictive performance of GAMSVM was significantly greater than those of other models, we used the McNemar test. As a result, we found that GAMSVM was better than MDA, MLOGIT, CBR, and ANN at the 1% significance level, and better than OAO and DAGSVM at the 5% significance level.

• Sleep Medicine and Psychophysiology
• /
• v.20 no.1
• /
• pp.15-21
• /
• 2013

Objectives: Cognitive impairment in restless legs syndrome (RLS) patients can be affected by sleep deprivation, anxiety and depression, which are common in RLS. The objective of this study is to investigate relationship between cognitive impairment and RLS in the non-medicated Korean elderly with controlling for psychiatric conditions. Method: The study sample for this study comprised 25 non-medicated Korean elderly RLS patients and 50 age-, sex-, and education- matched controls. All subjects were evaluated with comprehensive cognitive function assessment tools- including the Korean version of Consortium to Establish a Registry for Alzheimer's Disease Assessment Packet (CERAD-K), severe cognitive impairment rating scale (SCIRS), frontal assessment battery (FAB), and clock drawing test (CLOX). Sleep quality and depression were also assessed with Pittsburgh sleep quality index (PSQI) and geriatric depression scale (GDS). Results: PSQI and GDS score showed no difference between RLS and control group. There was no significant difference between two groups in nearly all the cognitive function except in constructional recognition test, in which subjects with RLS showed lower performance than control group (t=-2.384, p=0.02). Subjects with depression ($GDS{\geq}10$) showed significant cognitive impairment compared to control in verbal fluency, Korean version of Mini Mental Status Examination in the CERAD-K (MMSE-KC), word list memory, trail making test, and frontal assessment battery (FAB). In contrast, no difference was observed between subjects who have low sleep quality (PSQI>5) and control group. Conclusions: At the exclusion of the impact of insomnia and depression, cognitive function was found to be relatively preserved in RLS patients compared to control. Impairment of visual recognition in RLS patients can be explained in terms of dopaminergic dysfunction in RLS.

• The Korean Journal of Health Service Management
• /
• v.2 no.1
• /
• pp.137-154
• /
• 2008

The increase of the supply of medical service and the increase of hospitals have intensified the competition of hospitals, and the advancement towards internationalization in the opening of medical industry has triggered the infinite competition of medical profession. In addition, the high expectation of customers and quality improvement in the medical care in accordance with the improvement of overall income, and the change of active role of medical consumers according to the popularization and the improvement of rights awareness reflect the customer needs and choice in the medical service. Customers wanted to receive the kind and pleasant service under the up-to-date medical service. Therefore, as a solution, hospital coordinators were emerged for the purpose of smooth treatment and customer satisfaction by generalizing all service of hospital. Accordingly, this thesis attempted to investigate the effect of hospital coordinator education curriculum on the education satisfaction and the quality of medical service. In order to solve the purpose of this study, I, author reviewed the existing literatures, established hypothesis, and verified hypothesis by using the variety of statistics techniques such as reliability, validity, frequency analysis, and regression analysis. The verification of hypothesis is as followings: First, among education training factors of hospital coordinators, the quality of instructor significantly affects the satisfaction of hospital coordinator education training. Second, among training factors of hospital coordinator, the attitude of trainee significantly affects the training satisfaction of hospital coordinator. Third, among education training factors of hospital coordinator, education course significantly affects the training satisfaction of hospital coordinator education. As the qualities of instructor are better equipped, the satisfaction of education becomes higher. It indicates that the education method of instructors is important as an index to represent the qualities of instructor such as the appropriateness of education method, preparation, passion, visual materials, the adequacy of education procession, and specialized knowledge, and it has important effect on the satisfaction of education. In order to enhance the satisfaction of hospital coordinator education, the creation of education environment, making trainee concentrate on the education, is required by appropriately allocating programs, arousing interest in education, based on the attitude of trainee, discussion, and preliminary programs, preparation, ahead of enforcement of education. Fourth, the satisfaction of hospital coordinator education training significantly affects the reliability among the qualities of medical service. Fifth, satisfaction of hospital coordinator education training significantly affects hospitality I kindness among the qualities of medical service. If the education satisfaction of trainee is high, it is effective in the practical application such as dealing with complaints, the duty performance for the patients, and so on in offering the medical service, related to reliability and furthermore, we can find the positive change in the attitude change of medical professions related to the reliability of hospital coordinator. In addition, in the process of offering medical services such as the kind explanation on the duty, rapid response to the customers inquiry, and tidy uniform, practical effect was verified. Sixth, the education training factor of hospital coordinator significantly affects the reliability among the quality of medical service. Seventh, the education training factors of hospital coordinator significantly affect hospitality/kindness. In the education of hospital coordinator, the methods to attract the interest of trainee by emphasizing reliability should be sought and for gaining the practical effect of hospital coordinator education, the sufficient preparation and investigation on the education curriculum should be prerequisite and under this condition, intensified discussion on the instructor and education course is needed. In the design of education course, more education hours and subjects should be allocated in the part of hospitality in order to improve the practical application of hospitality. Therefore, it is meaningful in a sense that this study newly approached the components of hospital coordinator education and the need to modify the quality components of medical service in accordance with the study subjects was raised. This study also finds its meaning in that it provides basic materials for the study of future hospital coordinator education by suggesting the system development model of hospital coordinator education through preliminary study of education training. In addition, this study is meaningful in the aspect that it suggested the direction of education training by showing how the hospital coordinator education training would applied to the hospital coordinator course of the Continuing Education Center at Pusan and Kyungnam National University to some extent. Since all investigation of this study was approached from the side of hospital coordinator, the thoughts of patients who are beneficiaries of medical service, and care givers cannot be identified. Therefore, the satisfaction of patients and care givers through the experience of medical service, which is the essential prerequisite of medical service, should be importantly considered and investigated. Accordingly, The study of comparing and analyzing the views of both patients and care givers should be carried out in the future.

• Horticultural Science & Technology
• /
• v.29 no.5
• /
• pp.420-432
• /
• 2011

Population dynamics of greenhouse whitefly, Trialeurodes vaporariorum (Westwood), were modeled and simulated to compare the temperature effects of air and tomato leaf inside greenhouse using DYMEX model simulator (pre-programed module based simulation program developed by CSIRO, Australia). The DYMEX model simulator consisted of temperature dependent development and oviposition modules. The normalized cumulative frequency distributions of the developmental period for immature and oviposition frequency rate and survival rate for adult of greenhouse whitefly were fitted to two-parameter Weibull function. Leaf temperature on reversed side of cherry tomato leafs (Lycopersicon esculentum cv. Koko) was monitored according to three tomato plant positions (top, > 1.6 m above the ground level; middle, 0.9 - 1.2 m; bottom, 0.3 - 0.5 m) using an infrared temperature gun. Air temperature was monitored at same three positions using a Hobo self-contained temperature logger. The leaf temperatures from three plant positions were described as a function of the air temperatures with 3-parameter exponential and sigmoidal models. Data sets of observed air temperature and predicted leaf temperatures were prepared, and incorporated into the DYMEX simulator to compare the effects of air and leaf temperature on population dynamics of greenhouse whitefly. The number of greenhouse whitefly immatures was counted by visual inspection in three tomato plant positions to verify the performance of DYMEX simulation in cherry tomato greenhouse where air and leaf temperatures were monitored. The egg stage of greenhouse whitefly was not counted due to its small size. A significant positive correlation between the observed and the predicted numbers of immature and adults were found when the leaf temperatures were incorporated into DYMEX simulation, but no significant correlation was observed with the air temperatures. This study demonstrated that the population dynamics of greenhouse whitefly was affected greatly by the leaf temperatures, rather than air temperatures, and thus the leaf surface temperature should be considered for management of greenhouse whitefly in cherry tomato grown in greenhouses.

• Journal of the Korean Applied Science and Technology
• /
• v.37 no.4
• /
• pp.893-905
• /
• 2020

This study is a study on solubilization and emulsifying power of tocopheryl acetate using vegetable surfactants. High purity polyglyceryl-10 isostearate and polyglyceryl-10 oleate were mixed to synthesize a vegetable surfactant with excellent solubilizing power and emulsifying power. The mixed raw material was named Solubil EWG-1100. The appearance of this raw material was a pale yellowish paste with a specific smell, specific gravity of 1.12, and acid value of 0.085. The HLB value of this surfactant was calculated by the Griffin's equation with an average value of 15.17. The behavior of this surfactant to solubilize tocopheryl acetate was mechanically verified. The performance of solubilization was evaluated by a method of visual evaluation and was measured by a transmittance rate at 650 nm using a UV spectrophotometer. As a result, in the formulation using 3% ethanol as a co-solvent, the concentration of surfactant was required to solubilize tocopheryl acetate was required about 5 times of natural surfactant. In the formulation without ethanol as a co-solvent, the concentration of surfactant was required to solubilize tocopheryl acetate required about 7 times of natural surfactant. In addition, the concentration of surfactant required to make an emulsifivation 10 % of tocopheryl acetate was 1 wt% of Solubil EWG-1100, and the emulsified particle size was 3.5 mm in cream formula. In order to obtain stable and fine emulsified particles, it was found that as the concentration of tocopheryl acetate increased, the concentration of Solubil EWG-1100 also was to increase. As a result of testing the solubilizing power of the surfactant according to the pH various change, it showed stable solubilizing power in the acidic region of pH=3.2, the neutral region of pH=7.0, and the alkaline region of pH=11.8. As application, based on these results, it is expected that it can be widely applied to the cosmetics field that develops skin care prescriptions, sensitive skin products, and heavy dry skin products.

• Journal of Biomedical Engineering Research
• /
• v.19 no.5
• /
• pp.455-468
• /
• 1998

For the objective interpretation of cerebral metabolic patterns in epilepsy patients, we developed computer-aided classifier using artificial neural network. We studied interictal brain FDG PET scans of 257 epilepsy patients who were diagnosed as normal(n=64), L TLE (n=112), or R TLE (n=81) by visual interpretation. Automatically segmented volume of interest (VOI) was used to reliably extract the features representing patterns of cerebral metabolism. All images were spatially normalized to MNI standard PET template and smoothed with 16mm FWHM Gaussian kernel using SPM96. Mean count in cerebral region was normalized. The VOls for 34 cerebral regions were previously defined on the standard template and 17 different counts of mirrored regions to hemispheric midline were extracted from spatially normalized images. A three-layer feed-forward error back-propagation neural network classifier with 7 input nodes and 3 output nodes was used. The network was trained to interpret metabolic patterns and produce identical diagnoses with those of expert viewers. The performance of the neural network was optimized by testing with 5~40 nodes in hidden layer. Randomly selected 40 images from each group were used to train the network and the remainders were used to test the learned network. The optimized neural network gave a maximum agreement rate of 80.3% with expert viewers. It used 20 hidden nodes and was trained for 1508 epochs. Also, neural network gave agreement rates of 75~80% with 10 or 30 nodes in hidden layer. We conclude that artificial neural network performed as well as human experts and could be potentially useful as clinical decision support tool for the localization of epileptogenic zones.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.6 no.3
• /
• pp.171-178
• /
• 2008

Metal filter elements were newly introduced to the high temperature filter(HTF) system in the low- and intermediate-level radioactive waste vitrification plant. In order to evaluate the performance of various metal materials as filter media, elements made of AISI 316L, AISI 904L, and Inconel 600 were included to the test set of filter elements. At the visual inspection to the elements performed after completion of each test, a few dark spots were observed on the surface of some elements. Especially they were found much more at the AISI 316L elements than others. To check the dark spots are the corrosion phenomena or not, two kinds of analyses were performed to the tested filter elements. Firstly, the surfaces or the cross sections of filter specimens cut out from both normal area and dark spot area of elements were analyzed by SEM/EDS. The results showed that the dark spots were not evidences of corrosion but the deposition of sodium, sulfur and silica compounds volatilized from waste or molten glass. Secondly, the ring tensile strength were analyzed for the ring-shape filter specimens cut out from each kind of element. The result obtained from the strength tested showed no evidence of corrosion as well. Conclusionally, depending on the two kinds of analysis, no evidences of corrosion were found at the tested metal filter elements. But the dark spots formed on the surface could reduce the effective filtering area and increase the overall pressure drop of HTF system. Thus, continuous heating inside filter housing up to dew point will be required normally. And a few long-period test should be followed for the exact evaluation of corrosion of the metal filter elements.