• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.177-198
• /
• 2018

Recently, as economic property it has become necessary to acquire and utilize the framework for water resource measurement and performance management as the property of water resources changes to hold "public property". To date, the evaluation of water technology has been carried out by feasibility study analysis or technology assessment based on net present value (NPV) or benefit-to-cost (B/C) effect, however it is not yet systemized in terms of valuation models to objectively assess an economic value of technology-based business to receive diffusion and feedback of research outcomes. Therefore, K-water (known as a government-supported public company in Korea) company feels the necessity to establish a technology valuation framework suitable for technical characteristics of water resources fields in charge and verify an exemplified case applied to the technology. The K-water evaluation technology applied to this study, as a public interest goods, can be used as a tool to measure the value and achievement contributed to society and to manage them. Therefore, by calculating the value in which the subject technology contributed to the entire society as a public resource, we make use of it as a basis information for the advertising medium of performance on the influence effect of the benefits or the necessity of cost input, and then secure the legitimacy for large-scale R&D cost input in terms of the characteristics of public technology. Hence, K-water company, one of the public corporation in Korea which deals with public goods of 'water resources', will be able to establish a commercialization strategy for business operation and prepare for a basis for the performance calculation of input R&D cost. In this study, K-water has developed a web-based technology valuation model for public interest type water resources based on the technology evaluation system that is suitable for the characteristics of a technology in water resources fields. In particular, by utilizing the evaluation methodology of the Institute of Advanced Industrial Science and Technology (AIST) in Japan to match the expense items to the expense accounts based on the related benefit items, we proposed the so-called 'K-water's proprietary model' which involves the 'cost-benefit' approach and the FCF (Free Cash Flow), and ultimately led to build a pipeline on the K-water research performance management system and then verify the practical case of a technology related to "desalination". We analyze the embedded design logic and evaluation process of web-based valuation system that reflects characteristics of water resources technology, reference information and database(D/B)-associated logic for each model to calculate public interest-based and profit-based technology values in technology integrated management system. We review the hybrid evaluation module that reflects the quantitative index of the qualitative evaluation indices reflecting the unique characteristics of water resources and the visualized user-interface (UI) of the actual web-based evaluation, which both are appended for calculating the business value based on financial data to the existing web-based technology valuation systems in other fields. K-water's technology valuation model is evaluated by distinguishing between public-interest type and profitable-type water technology. First, evaluation modules in profit-type technology valuation model are designed based on 'profitability of technology'. For example, the technology inventory K-water holds has a number of profit-oriented technologies such as water treatment membranes. On the other hand, the public interest-type technology valuation is designed to evaluate the public-interest oriented technology such as the dam, which reflects the characteristics of public benefits and costs. In order to examine the appropriateness of the cost-benefit based public utility valuation model (i.e. K-water specific technology valuation model) presented in this study, we applied to practical cases from calculation of benefit-to-cost analysis on water resource technology with 20 years of lifetime. In future we will additionally conduct verifying the K-water public utility-based valuation model by each business model which reflects various business environmental characteristics.

• Journal of Global Scholars of Marketing Science
• /
• v.20 no.1
• /
• pp.89-97
• /
• 2010

This study researches the effects of common features on a no-choice option with respect to regulatory focus theory. The primary interest is in three factors and their interrelationship: common features, no-choice option, and regulatory focus. Prior studies have compiled vast body of research in these areas. First, the "common features effect" has been observed bymany noted marketing researchers. Tversky (1972) proposed the seminal theory, the EBA model: elimination by aspect. According to this theory, consumers are prone to focus only on unique features during comparison processing, thereby dismissing any common features as redundant information. Recently, however, more provocative ideas have attacked the EBA model by asserting that common features really do affect consumer judgment. Chernev (1997) first reported that adding common features mitigates the choice gap because of the increasing perception of similarity among alternatives. Later, however, Chernev (2001) published a critically developed study against his prior perspective with the proposition that common features may be a cognitive load to consumers, and thus consumers are possible that they are prone to prefer the heuristic processing to the systematic processing. This tends to bring one question to the forefront: Do "common features" affect consumer choice? If so, what are the concrete effects? This study tries to answer the question with respect to the "no-choice" option and regulatory focus. Second, some researchers hold that the no-choice option is another best alternative of consumers, who are likely to avoid having to choose in the context of knotty trade-off settings or mental conflicts. Hope for the future also may increase the no-choice option in the context of optimism or the expectancy of a more satisfactory alternative appearing later. Other issues reported in this domain are time pressure, consumer confidence, and alternative numbers (Dhar and Nowlis 1999; Lin and Wu 2005; Zakay and Tsal 1993). This study casts the no-choice option in yet another perspective: the interactive effects between common features and regulatory focus. Third, "regulatory focus theory" is a very popular theme in recent marketing research. It suggests that consumers have two focal goals facing each other: promotion vs. prevention. A promotion focus deals with the concepts of hope, inspiration, achievement, or gain, whereas prevention focus involves duty, responsibility, safety, or loss-aversion. Thus, while consumers with a promotion focus tend to take risks for gain, the same does not hold true for a prevention focus. Regulatory focus theory predicts consumers' emotions, creativity, attitudes, memory, performance, and judgment, as documented in a vast field of marketing and psychology articles. The perspective of the current study in exploring consumer choice and common features is a somewhat creative viewpoint in the area of regulatory focus. These reviews inspire this study of the interaction possibility between regulatory focus and common features with a no-choice option. Specifically, adding common features rather than omitting them may increase the no-choice option ratio in the choice setting only to prevention-focused consumers, but vice versa to promotion-focused consumers. The reasoning is that when prevention-focused consumers come in contact with common features, they may perceive higher similarity among the alternatives. This conflict among similar options would increase the no-choice ratio. Promotion-focused consumers, however, are possible that they perceive common features as a cue of confirmation bias. And thus their confirmation processing would make their prior preference more robust, then the no-choice ratio may shrink. This logic is verified in two experiments. The first is a $2{\times}2$ between-subject design (whether common features or not X regulatory focus) using a digital cameras as the relevant stimulus-a product very familiar to young subjects. Specifically, the regulatory focus variable is median split through a measure of eleven items. Common features included zoom, weight, memory, and battery, whereas the other two attributes (pixel and price) were unique features. Results supported our hypothesis that adding common features enhanced the no-choice ratio only to prevention-focus consumers, not to those with a promotion focus. These results confirm our hypothesis - the interactive effects between a regulatory focus and the common features. Prior research had suggested that including common features had a effect on consumer choice, but this study shows that common features affect choice by consumer segmentation. The second experiment was used to replicate the results of the first experiment. This experimental study is equal to the prior except only two - priming manipulation and another stimulus. For the promotion focus condition, subjects had to write an essay using words such as profit, inspiration, pleasure, achievement, development, hedonic, change, pursuit, etc. For prevention, however, they had to use the words persistence, safety, protection, aversion, loss, responsibility, stability etc. The room for rent had common features (sunshine, facility, ventilation) and unique features (distance time and building state). These attributes implied various levels and valence for replication of the prior experiment. Our hypothesis was supported repeatedly in the results, and the interaction effects were significant between regulatory focus and common features. Thus, these studies showed the dual effects of common features on consumer choice for a no-choice option. Adding common features may enhance or mitigate no-choice, contradictory as it may sound. Under a prevention focus, adding common features is likely to enhance the no-choice ratio because of increasing mental conflict; under the promotion focus, it is prone to shrink the ratio perhaps because of a "confirmation bias." The research has practical and theoretical implications for marketers, who may need to consider common features carefully in a practical display context according to consumer segmentation (i.e., promotion vs. prevention focus.) Theoretically, the results suggest some meaningful moderator variable between common features and no-choice in that the effect on no-choice option is partly dependent on a regulatory focus. This variable corresponds not only to a chronic perspective but also a situational perspective in our hypothesis domain. Finally, in light of some shortcomings in the research, such as overlooked attribute importance, low ratio of no-choice, or the external validity issue, we hope it influences future studies to explore the little-known world of the "no-choice option."

• Korean Journal of Agricultural Science
• /
• v.2 no.2
• /
• pp.341-356
• /
• 1975

This study was carried out to evaluate three winter active synthetic varieties in a succeeding generations of improvement and polycross progenies of seven genotypes selected at the cool and wet climate of the Western Oregon, in their performance of the polycross progeny test comparing with a control variety, high yielding 'Fawn', at Daejon, Korea. Various plant and leaf characteristics, especially related to photosynthesis, and forage production during the first summer after the establishment were examined. The important conclusions of this study are summarized as follows: 1. The differences of leaf fresh weight among groups and control exhibit genetic differences. The a verage of leaf fresh weight of polycross progeny group was the heaviest and those of winter active synthetic varieties in the succeeding generations of improvement was heavier than variety 'fawn'. Within polycross progeny group the genotypes exhibit genetic differences for leaf dry weight. 2. The leaf area exhibited genetic differences among groups and control. The average of winter active synthetic varieties in a succeeding generation was larger than variety 'Fawn'. Those oi the polycross progeny group was the largest among groups and control. 3. Differences of specific leaf weight(S. L. W.) among and within varieties, genotypes and control were not significant. Further investigation in this respect is necessary through the study of the diurnal change in S. L. W. 4. Differences of leaf width among groups and control exhibited genetic differences. The average leaf width of winter active varieties was larger than those of 'Fawn' variety. And those of polycross progenies of genotypes was the largest. 5. Plant height of 'fawn' variety in the first measurement was higher than those of winter active tall fescue varieties and genotypes. The deviation in plant height among polyeross progenies of seven genotypes gave a great deviation. The regrowth ability of plant height was not different suggesting that this characteristics was about the same among and within groups and control. 6. Plant width, spreading ability, improved through the succeeding generations of the improvement of the winter active synthetic varieties for the first measurement. Differences of plant width at the second measurement among genotypes within polycross progeny group were big enough to show the genetic difference. 7. Tiller number of the winter active synthetic varieties and the average of genotypes in polycross progeny was more than those of the control 'Fawn' in the first measurement. On the second measurement, the differences of tiller number appeared among three synthetic varieties indicating improvement, and there were genetic differences among seven genotypes in polycross progeny test. 8. Forage yield on the first cutting showed a considerble improvement of forage yield in the more advanced generation of synthetic varieties and genetic differences among seven genotypes in the polycross progeny test. The average of polycross progeny group was higher than those of the control or three winter active varieties. It was suggested that we could make a further improvement for the forage yield. 9. The regrowth ability of these winter active varieties and genotypes was about the same capacity at least on the measurement of the regrowth in forage yield and plant height during summer. 10. On the whole, the averages of the polycross progeny group was in the highest value and those of synthetic varieties were higher than the control variety, 'Fawn', for the most characteristics except S. L. W. and the plant height on the first measurement even though the differences were not always significant. And there were genetic differences among seven gentypes in their performance of the polycross progeny. 11. Although it was not always sgnificant, the most advanced winter active variety, '1002', had in the highest value for all plant characteristics and forage yield measurements than the other two varieties, '1001'. 12. The results of the association study among various characteristics were quite agreeable and would be useful in the selection of desirable genotypes for the development of a better variety.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.171-193
• /
• 2018

LOD(Linked Open Data) cloud is a practical implementation of semantic web. We suggested a new method that provides identity links conveniently in LOD cloud. It also allows changes in LOD to be reflected to searching results without any omissions. LOD provides detail descriptions of entities to public in RDF triple form. RDF triple is composed of subject, predicates, and objects and presents detail description for an entity. Links in LOD cloud, named identity links, are realized by asserting entities of different RDF triples to be identical. Currently, the identity link is provided with creating a link triple explicitly in which associates its subject and object with source and target entities. Link triples are appended to LOD. With identity links, a knowledge achieves from an LOD can be expanded with different knowledge from different LODs. The goal of LOD cloud is providing opportunity of knowledge expansion to users. Appending link triples to LOD, however, has serious difficulties in discovering identity links between entities one by one notwithstanding the enormous scale of LOD. Newly added entities cannot be reflected to searching results until identity links heading for them are serialized and published to LOD cloud. Instead of creating enormous identity links, we propose LOD to prepare its own link policy. The link policy specifies a set of target LODs to link and constraints necessary to discover identity links to entities on target LODs. On searching, it becomes possible to access newly added entities and reflect them to searching results without any omissions by referencing the link policies. Link policy specifies a set of predicate pairs for discovering identity between associated entities in source and target LODs. For the link policy specification, we have suggested a set of vocabularies that conform to RDFS and OWL. Identity between entities is evaluated in accordance with a similarity of the source and the target entities' objects which have been associated with the predicates' pair in the link policy. We implemented a system "Change Acceptable In-Depth Searching System(CAIDS)". With CAIDS, user's searching request starts from depth_0 LOD, i.e. surface searching. Referencing the link policies of LODs, CAIDS proceeds in-depth searching, next LODs of next depths. To supplement identity links derived from the link policies, CAIDS uses explicit link triples as well. Following the identity links, CAIDS's in-depth searching progresses. Content of an entity obtained from depth_0 LOD expands with the contents of entities of other LODs which have been discovered to be identical to depth_0 LOD entity. Expanding content of depth_0 LOD entity without user's cognition of such other LODs is the implementation of knowledge expansion. It is the goal of LOD cloud. The more identity links in LOD cloud, the wider content expansions in LOD cloud. We have suggested a new way to create identity links abundantly and supply them to LOD cloud. Experiments on CAIDS performed against DBpedia LODs of Korea, France, Italy, Spain, and Portugal. They present that CAIDS provides appropriate expansion ratio and inclusion ratio as long as degree of similarity between source and target objects is 0.8 ~ 0.9. Expansion ratio, for each depth, depicts the ratio of the entities discovered at the depth to the entities of depth_0 LOD. For each depth, inclusion ratio illustrates the ratio of the entities discovered only with explicit links to the entities discovered only with link policies. In cases of similarity degrees with under 0.8, expansion becomes excessive and thus contents become distorted. Similarity degree of 0.8 ~ 0.9 provides appropriate amount of RDF triples searched as well. Experiments have evaluated confidence degree of contents which have been expanded in accordance with in-depth searching. Confidence degree of content is directly coupled with identity ratio of an entity, which means the degree of identity to the entity of depth_0 LOD. Identity ratio of an entity is obtained by multiplying source LOD's confidence and source entity's identity ratio. By tracing the identity links in advance, LOD's confidence is evaluated in accordance with the amount of identity links incoming to the entities in the LOD. While evaluating the identity ratio, concept of identity agreement, which means that multiple identity links head to a common entity, has been considered. With the identity agreement concept, experimental results present that identity ratio decreases as depth deepens, but rebounds as the depth deepens more. For each entity, as the number of identity links increases, identity ratio rebounds early and reaches at 1 finally. We found out that more than 8 identity links for each entity would lead users to give their confidence to the contents expanded. Link policy based in-depth searching method, we proposed, is expected to contribute to abundant identity links provisions to LOD cloud.

• Tuberculosis and Respiratory Diseases
• /
• v.41 no.5
• /
• pp.521-530
• /
• 1994

Background : The past studies on prediction formulas of pulmonary function parameters in healthy nonsmoking Korean adults have been performed in relatively small number of subjects and the reported results were restricted on a few parameters. Also there was no systematic investigation into the effect of smoking on pulmonary function parameters in smokers who have no respiratory symptoms. Therefore we attempted to establish prediction formulas of pulmonary function parameters and examined the effect of smoking on pulmonary function parameters. Methods We analyzed the result of parameters derived from the forced expiratory spirogram in 1,067 nonsmoking subjects from June in 1990 to December in 1991. They consisted of 306 males and 761 females and had neither respitatory symptoms nor history of respiratory disease. We derived prediction formulas by multiple linear regression method from their age, heights, and weights in each sex. To examine the effect of smoking on pulmonary function parameters, we classified 383 smoking men into three groups according to the past amount of smoking as follows : i.e. group of smokers who have smoked below 10 pack-years, 10-20 pack-years and above 20 pack-years. Regarding each group of past smoking as an independent dummy variable, we analyzed pulmonary function parameters including nonsmoking men as a baseline by multiple linear regression. We evaluated the smoking effect on pulmonary function parameters according to estimated p-value. Result : 1) Prediction formulas for pulmonary function parameters in each sex were derived. 2) The past smoking less than 10 pack-years does not give any effect on pulmonary function parameters. The past smoking of 10~20 pack-years showed significant negative correlation with $FEV_1$/FVC and FEF 25~75%, and the smoking above 20 pack years showed negative correlation with $FEV_1$ and $FEV_1$/FVC. Conclusion : We have got prediction formulas of pulmonary function parameters which is driven from forced expiratory spirogram in nonsmoking Korean adults by multiple linear regression from age, heights and weights of subjects. The past smoking more than 10 pack-years showed negative correlation with some pulmonary function parameters of airflow obstruction.

• Journal of the Korean Society of Radiology
• /
• v.14 no.3
• /
• pp.203-209
• /
• 2020

The purpose of this study is to assess the mechanical stability and alignment of the patient positioning system (PPS) of Leksell Gamma Knife Perfexion(LGK PFX). The alignment of the PPS of the LGK PFX was evaluated through measurements of the deviation of the coincidence of the Radiological Focus Point(RFP) and the PPS Calibration Center Point(CCP) applying different weights on the couch(0, 50, 60, 70, 80, and 90 kg). In measurements, a service diode test tool with three diode detectors being used biannually at the time of the routine preventive maintenance was used. The test conducted with varying weights on the PPS using the service diode test tool measured the radial deviations for all three collimators 4, 8, and 16 mm and also for three different positions of the PPS. In order to evaluate the alignment of the PPS, the radial deviations of the correspondence of the radiation focus and the LGK calibration center point of multiple beams were averaged using the calibrated service diode test tool at three university hospitals in Busan and Gyeongnam. Looking at the center diode for all collimators 4, 8, and 16 mm without weight on the PPS, and examining the short and long diodes for the 4 mm collimator, the means of the validation difference, i.e., the radial deviation for the setting of 4, 8, and 16 mm collimators for the center diode were respectively measured to 0.058 ± 0.023, 0.079 ± 0.023, and 0.097 ± 0.049 mm, and when the 4 mm collimator was applied to the center diode, the short diode, and the long diode, the average of the radial deviation was respectively 0.058 ± 0.023, 0.078 ± 0.01 and 0.070 ± 0.023 mm. The average of the radial deviations when irradiating 8 and 16 mm collimators on short and long diodes without weight are measured to 0.07 ± 0.003(8 mm sd), 0.153 ± 0.002 mm(16 mm sd) and 0.031 ± 0.014(8 mm ld), 0.175 ± 0.01 mm(16 mm ld) respectively. When various weights of 50 to 90 kg are placed on the PPS, the average of radial deviation when irradiated to the center diode for 4, 8, and 16 mm is 0.061 ± 0.041 to 0.075 ± 0.015, 0.023 ± 0.004 to 0.034 ± 0.003, and 0.158 ± 0.08 to 0.17 ± 0.043 mm, respectively. In addition, in the same situation, when the short diode for 4, 8, and 16 mm was irradiated, the averages of radial deviations were 0.063 ± 0.024 to 0.07 ± 0.017, 0.037 ± 0.006 to 0.059 ± 0.001, and 0.154 ± 0.03 to 0.165 ± 0.07 mm, respectively. In addition, when irradiated on long diode for 4, 8, and 16 mm, the averages of radial deviations were measured to be 0.102 ± 0.029 to 0.124 ± 0.036, 0.035 ± 0.004 to 0.054 ± 0.02, and 0.183 ± 0.092 to 0.202 ± 0.012 mm, respectively. It was confirmed that all the verification results performed were in accordance with the manufacturer's allowable deviation criteria. It was found that weight dependence was negligible as a result of measuring the alignment according to various weights placed on the PPS that mimics the actual treatment environment. In particular, no further adjustment or recalibration of the PPS was required during the verification. It has been confirmed that the verification test of the PPS according to various weights is suitable for normal Quality Assurance of LGK PFX.

• The Korean Journal of Food And Nutrition
• /
• v.24 no.3
• /
• pp.340-349
• /
• 2011

This study examined the roles of autolytic enzymes and microorganisms in the ripening process of salted Alaska pollack tripe made with various concentrations of salt i.e, 7.5% and 20% by weight. Salted Alaska pollack tripe treated with antibiotic agents for the inhibition of microbial growth and a control were prepared experimentally, and changes in chemical composition and viable cell counts were investigated, individually, during the ripening process. Just after the preparation of the low salt Alaska pollack tripe made with 7.5% salt, viable bacterial cells occurred at a level of $10^5$ CFU/g. In the control, bacterial counts increased rapidly to $10^7$ CFU/g by the 14th day of ripening. However, in the sample treated with antibiotic agents, counts were decreased to a level of $10^4$ CFU/g by the 3rd day of ripening and increased gradually to $10^6$ CFU/g by the 5th day of ripening, and then the same value was maintained there-after. Just after the preparation of the high salt Alaska pollack tripe made with 20% salt, viable bacterial cells occurred at a level of $10^3$ CFU/g. In both the samples treated with antibiotic agents and the control, bacterial counts decreased rapidly to $10^0$ CFU/g by the 45th day of ripening and increased gradually there-after. The content of amino type nitrogen was 76.3 mg% just after the preparation of the low salt Alaska pollack tripe made with 7.5% salt. Amino type nitrogen content was increased to 283.5 mg% by the 5th day of proper ripening in the control, but it was increased to 208.0 mg% in the sample treated with antibiotic agents. The difference in amino type nitrogen content was 75.5 mg/100 g. The content of amino type nitrogen was 57.2 mg% just after the preparation of the high salt Alaska pollack tripe made with 20% salt. Amino type nitrogen content was increased to 198.3 mg by the 60th day of proper ripening in the control, but it was increased to 162.0 mg% in the sample treated with the antibiotic agents. The difference in amino type nitrogen content was 36.3 mg/100 g. The contents of VBN and TMA-N were 102.1 mg% and 20.5 mg%, respectively, at the 7th day of ripening in the low salt Alaska pollack tripe made with 7.5% salt. The content of VBN was 60.0 mg% and TMA-N was not detected at the 21st day of ripening in the sample treated with antibiotic agents. The control sample was spoiled by the 7th day of ripening but the sample treated with antibiotic agents was not spoiled by the 21st day of ripening. On the other hand, VBN content was 37.2 mg% and TMA-N was not detected at the 90th day of ripening in the high salt Alaska pollack tripe made with 20% salt, and the control sample was not spoiled.

• 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.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.31 no.2
• /
• pp.43-57
• /
• 2013

The purpose of this study is to identify potential semantic landscape makeup of "the Forty Eight Poems of Soswaewon" according to Yin-Yang and Five Elements Principle(陰陽五行論). that speculation system between human's nature and cosmical universal order. Existing academic discussions made so far concerning this topic can be summed up as follows: 1. Among Yin-Yang-based landscape makeups of the Forty Eight Poems of Soswaewon, poetic writings for embodiment of interactions between nature and human behaviors focused on depicting dynamic aspects of a poetic narrator when he appreciates or explores hills and streams as of to live free from worldly cares. Primarily, many of those writings were created on the east and south primarily through assignment of yang. On the other hand, poetic writings for embodiment of nature and seasonal scenery - as static landscape makeup of yin - were often created on or near the north and west for many times. Those writings focusing on embodiment of nature and artificial scenery as a work are divided into two categories: One category refers to author Kim In-hu's expression of semantic landscape from seasonal scenery in nature. The other refers to his depiction of realistic garden images as they are. In the Forty Eight Poems of Soswaewon, the poetic writings show that author Kim focused on embodying seasonal scenery rather than expressing human behaviors. In addition, both Poem No. 1 and Poem No. 48(last poem; titled 'Jangwon Jeyeong') were created in a same place, which author Kim sought to understand the place as a space of beginning and end where yin and yang - i.e. the principle of natural cycle - are inherent. 2. According to construction about landscape in the Forty Eight Poems of Soswaewon on the basis of Ohaeng-ron (five natural element principle), it was found that tree(木) and fire(火) are typical examples of a world combined by emanation. First, many of poetic writings depicting the sentiments of tree focused on embodying seasonal scenery and were located in the place of Ogogmun(五曲門) area in the east, from overall perspective of Soswaewon. The content of these poems shows generation and curve / straightness in flexibility and simplicity. Many of poems depicting the sentiments of fire(火) focused on embodying human behaviors, and they were created in Aeyangdan area on the south of Soswaewon over which sun rises at noon. These poems are all on a status of side movement that is characterized by emanation and ascension which belong to attributes of yang. 3. With regard to Ohaeng-ron's interpretation about landscape in the Forty Eight Poems of Soswaewon, it was found that metal(金) and water(水) are typical examples of world combined by convergence. First, it was found that all of poems depicting sentiments of metal focused on embodying seasonal scenery, and were created in a bamboo grove area on the west from overall perspective of Soswaewon. They represent scenery of autumn among 4 seasons to symbolize faithfulness vested in a man of virtue(seonbi) with integrity and righteousness. Poems depicting sentiments of water were created in vicinity of Jewoldang on the north, possibly topmost of Soswaewon. They were divided into two categories: One category refers to poems embodying actions of welcoming the first full moon deep in the night after sunset, and the other refers to poems embodying natural scenery of snowscape. All of those poems focused on expressing any atmosphere of turning into yin via convergence. 4. With regard to Ohaeng-ron's interpretation of landscape in the Forty Eight Poems of Soswaewon, it was found that poems depicting sentiments of earth(土), a complex body of convergence and emanation, were created in vicinity of mountain stream around Gwangpunggak which is located in the center of Soswaewon. These poems focused on carrying actions of author Kim by way of natural phenomena and artificial scenery.