• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.147-168
• /
• 2017

There have been many studies on accurate stock market forecasting in academia for a long time, and now there are also various forecasting models using various techniques. Recently, many attempts have been made to predict the stock index using various machine learning methods including Deep Learning. Although the fundamental analysis and the technical analysis method are used for the analysis of the traditional stock investment transaction, the technical analysis method is more useful for the application of the short-term transaction prediction or statistical and mathematical techniques. Most of the studies that have been conducted using these technical indicators have studied the model of predicting stock prices by binary classification - rising or falling - of stock market fluctuations in the future market (usually next trading day). However, it is also true that this binary classification has many unfavorable aspects in predicting trends, identifying trading signals, or signaling portfolio rebalancing. In this study, we try to predict the stock index by expanding the stock index trend (upward trend, boxed, downward trend) to the multiple classification system in the existing binary index method. In order to solve this multi-classification problem, a technique such as Multinomial Logistic Regression Analysis (MLOGIT), Multiple Discriminant Analysis (MDA) or Artificial Neural Networks (ANN) we propose an optimization model using Genetic Algorithm as a wrapper for improving the performance of this model using Multi-classification Support Vector Machines (MSVM), which has proved to be superior in prediction performance. In particular, the proposed model named GA-MSVM is designed to maximize model performance by optimizing not only the kernel function parameters of MSVM, but also the optimal selection of input variables (feature selection) as well as instance selection. In order to verify the performance of the proposed model, we applied the proposed method to the real data. The results show that the proposed method is more effective than the conventional multivariate SVM, which has been known to show the best prediction performance up to now, as well as existing artificial intelligence / data mining techniques such as MDA, MLOGIT, CBR, and it is confirmed that the prediction performance is better than this. Especially, it has been confirmed that the 'instance selection' plays a very important role in predicting the stock index trend, and it is confirmed that the improvement effect of the model is more important than other factors. To verify the usefulness of GA-MSVM, we applied it to Korea's real KOSPI200 stock index trend forecast. Our research is primarily aimed at predicting trend segments to capture signal acquisition or short-term trend transition points. The experimental data set includes technical indicators such as the price and volatility index (2004 ~ 2017) and macroeconomic data (interest rate, exchange rate, S&P 500, etc.) of KOSPI200 stock index in Korea. Using a variety of statistical methods including one-way ANOVA and stepwise MDA, 15 indicators were selected as candidate independent variables. The dependent variable, trend classification, was classified into three states: 1 (upward trend), 0 (boxed), and -1 (downward trend). 70% of the total data for each class was used for training and the remaining 30% was used for verifying. To verify the performance of the proposed model, several comparative model experiments such as MDA, MLOGIT, CBR, ANN and MSVM were conducted. MSVM has adopted the One-Against-One (OAO) approach, which is known as the most accurate approach among the various MSVM approaches. Although there are some limitations, the final experimental results demonstrate that the proposed model, GA-MSVM, performs at a significantly higher level than all comparative models.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.123-139
• /
• 2019

The Korean NPL market was formed by the government and foreign capital shortly after the 1997 IMF crisis. However, this market is short-lived, as the bad debt has started to increase after the global financial crisis in 2009 due to the real economic recession. NPL has become a major investment in the market in recent years when the domestic capital market's investment capital began to enter the NPL market in earnest. Although the domestic NPL market has received considerable attention due to the overheating of the NPL market in recent years, research on the NPL market has been abrupt since the history of capital market investment in the domestic NPL market is short. In addition, decision-making through more scientific and systematic analysis is required due to the decline in profitability and the price fluctuation due to the fluctuation of the real estate business. In this study, we propose a prediction model that can determine the achievement of the benchmark yield by using the NPL market related data in accordance with the market demand. In order to build the model, we used Korean NPL data from December 2013 to December 2017 for about 4 years. The total number of things data was 2291. As independent variables, only the variables related to the dependent variable were selected for the 11 variables that indicate the characteristics of the real estate. In order to select the variables, one to one t-test and logistic regression stepwise and decision tree were performed. Seven independent variables (purchase year, SPC (Special Purpose Company), municipality, appraisal value, purchase cost, OPB (Outstanding Principle Balance), HP (Holding Period)). The dependent variable is a bivariate variable that indicates whether the benchmark rate is reached. This is because the accuracy of the model predicting the binomial variables is higher than the model predicting the continuous variables, and the accuracy of these models is directly related to the effectiveness of the model. In addition, in the case of a special purpose company, whether or not to purchase the property is the main concern. Therefore, whether or not to achieve a certain level of return is enough to make a decision. For the dependent variable, we constructed and compared the predictive model by calculating the dependent variable by adjusting the numerical value to ascertain whether 12%, which is the standard rate of return used in the industry, is a meaningful reference value. As a result, it was found that the hit ratio average of the predictive model constructed using the dependent variable calculated by the 12% standard rate of return was the best at 64.60%. In order to propose an optimal prediction model based on the determined dependent variables and 7 independent variables, we construct a prediction model by applying the five methodologies of discriminant analysis, logistic regression analysis, decision tree, artificial neural network, and genetic algorithm linear model we tried to compare them. To do this, 10 sets of training data and testing data were extracted using 10 fold validation method. After building the model using this data, the hit ratio of each set was averaged and the performance was compared. As a result, the hit ratio average of prediction models constructed by using discriminant analysis, logistic regression model, decision tree, artificial neural network, and genetic algorithm linear model were 64.40%, 65.12%, 63.54%, 67.40%, and 60.51%, respectively. It was confirmed that the model using the artificial neural network is the best. Through this study, it is proved that it is effective to utilize 7 independent variables and artificial neural network prediction model in the future NPL market. The proposed model predicts that the 12% return of new things will be achieved beforehand, which will help the special purpose companies make investment decisions. Furthermore, we anticipate that the NPL market will be liquidated as the transaction proceeds at an appropriate price.

• Journal of Animal Science and Technology
• /
• v.45 no.6
• /
• pp.939-948
• /
• 2003

The objective of this study was to identify the quantitative traits loci(QTL) for economically important traits such as growth, carcass and meat quality on pig chromosome 6. A three generation resource population was constructed from cross between Korean native boars and Landrace sows. A total of 240 F$_2$ animals were produced using intercross between 10 boars and 31 sows of F$_1$ animals. Phenotypic data including body weight at 3 weeks, backfat thickness, muscle pH, shear force and crude protein level were collected from F$_2$ animals. Animals including grandparents(F$_0$), parents(F$_1$) and offspring(F$_2$) were genotyped for 29 microsatellite markers and PCR-RFLP marker on chromosome 6. The linkage analysis was performed using CRI-MAP software version 2.4(Green et al., 1990) with FIXED option to obtain the map distances. The total length of SSC6 linkage map estimated in this study was 169.3cM. The average distance between adjacent markers was 6.05cM. For mapping of QTL, we used F$_2$ QTL Analysis Servlet of QTL express, a web-based QTL mapping tool(http://qtl.cap.ed.ac.uk). Five QTLs were detected at 5% chromosome-wide level for body weight of 3 weeks of age, shear force, meat pH at 24 hours after slaughtering, backfat thickness and crude protein level on SSC6.

• Korean Journal of Psychosomatic Medicine
• /
• v.7 no.2
• /
• pp.213-225
• /
• 1999

Objectives : The purpose of this study was to investigate how the play habits, temperament, and environmental factors might affect childhood obesity. Methods : Two hundred sixty children, aged 4 through 6 years living in Seoul & Cheonan were surveyed by a questionnaire about the children's play habit and the parent's related factors such as weight, height, education, income. In addition the Korean version of the Parent Temperament Questionnaire for Children and the Korean version of the Family Environment Scale were also administered to parents of those children. The height and weight of those children were measured and the percentage of body fat was measured by Bioelectrical Impedance Fatness Analyzer. Result : 1) Among 260 children, 25 children were considered to be obese on the basis of both obesity index and percentage of body fat. 2) Parents of obese children showed a significantly higher educational level(p<0.05) and mothers of obese children had significantly more jobs(p<0.05) and showed higher body mass index(p<0.05) than those of nonobese children. 3) By observing play habits of children, obese children spent significantly longer time in watching TV and video(p<0.05), while nonobese children showed a trend to play outside(p<0.1). 4) On the Korean version of the Parent Temperament Questionnaire for Children, obese children showed significantly less activity than nonobese ones(p <0.05). 5) Family of obese children had significantly higher point on subscale of Achievement orientation, Intellectual-cultural orientation and Moral-religious emphasis of the Korean version of the Family Environment Scale(p<0.05). 6) Percentage of body fat of obese children was correlated with children's watching TV time, activity level, scores of Achievement orientation, Intellectual-cultural orientation of the Korean version of the Family Environment Scale and the both parent's education levels(p<0.05). Conclusion : Obese children showed hypoactivity and more watching TV time. And obese children's both parent had higher educational level and their mother had higher Body Mass Index and more jobs. Family of obese children had higher point on items of Achievement orientation, Intellectual-cultural orientation and Moral-religious emphasis. Family environmental factors influence on children's obesity through interaction of genetic and behavioral-psychological factors concomittently.

• Journal of Radiation Protection and Research
• /
• v.38 no.2
• /
• pp.106-118
• /
• 2013

In this paper, we analyzed the Cognition of irradiated food and its relation with self-efficacy. The most important variables described behaviors based on health choices compared with the choice to choose irradiated food items. According to the survey, 33.1% of respondents said that the reason why irradiated food is considered to be a health risk is because "radiation is dangerous". 27.9% of respondents answered that "eating irradiated food is like eating a radioactive substance", 21.1% said radiated food is comparable to a "genetic variation in food" while 10.1% said "food goes bad during the irradiation process". On this basis, it is reasonable to conclude that respondents have a misunderstanding of irradiated food without reference to the general theory of irradiated knowledge. In this respect, it would be helpful to provide education showing that irradiated food is not related to eating harmful or genetically modified food to help high school students create informed opinions of irradiated food. In terms of relevance with health-specific self-efficacy, experience of acquiring information about irradiated food was marked at r=0.148 (p<0.01), experience of purchasing irradiated food was marked at r=0.077 (p<0.05), experience of eating irradiated food was marked at r=0.113 (p<0.01) while knowledge of irradiated food, attitude towards irradiated food and behavior was marked at r=0.103 (p<0.01), r=0.076 (p<0.05) and r=0.105 (p<0.01) respectively. This shows that self-efficacy is high when one has experience of acquiring information about irradiated food, purchasing or eating irradiated food resulting in a high level of knowledge, attitude and behavior. Education which serves to improve the level of self-efficacy needs to be provided along with an educational program which will increase the public's understanding of irradiated food. It is expected that if this education which increases the level of self-efficacy is provided together with correct information of irradiated food, behavior to choose and eat irradiated food will also improve.

• Women's Health Nursing
• /
• v.4 no.2
• /
• pp.217-230
• /
• 1998

The purpose of this descriptive correlational study was to define the relationship between the experience of Sanhuujori, Korean traditional non-professional postpartal care after delivery and abortion and present health status of chronic arthritis female patient who visited to outpatient clinic of rheumatic internal medicine at a hospital located in Seoul, Korea. A convenience sample of 64 women who orally agreed to be a participant and data were collected form October 1996 to May, 1997 for sis months by way of interview with semistructured questionnaire. The data were analyzed by the SPSS pc program using t-test, ANOVA and Scheffe test as a post hoc and Pearson Correlation Coefficient. The results of the study were as follows ; Mean age of participants was 53.2 years and mean number of children was 3.1. Mean frequency of abortion was 2.1 times per woman. Seventy four percentage of respondents did not have Sanhujori after abortion. The mean period of Sanhujori after delivery was 17.7, 15.2, 13.8 days from the first child to third child and shorter than that of general woman such as 20.0, 19.0, 17.3 days in the previous study. On the subjective evaluation of whether the women did Sanhujori well or not, the rate of 'did Sanhujori wrongly' was the highest rank in each child where as general woman 'did Sanhujori well' at the first child, 'moderate' at the second and third child and 'did Sanhujori wrongly' at the 4th and fifth child. The health status implies both subjective health status women perceived and the rate of complaints of physical symptom distress women are experiencing presently. The respondents of 82.5% perceived them as unhealthy or sick and 68.9% of women complained more than two symptoms. Mean number of physical symptom distress women complained was 2.33. The main sites of physical symptom distress were upper & lower extremities 69.1% including knee and hand, whole body 19.1%, neck 3.7%, waist & shoulders 2.7% respectively. The characteristics of the symptoms were mostly pain 60%, swelling 19.8%, rigidity & deformity 7.9% respectively, sensation of heat 6.8% and weakness 1.7%. Women perceived the etiology of the chronic arthritis as stress 25.8%, 'did Sanhujori wrongly' & overwork 23.4% respectively, genetic 12.9%, malnutrition, 4.8%, and aging process 3.2%. There were significant positive correlation between subjective health status and the period of Sanhujori after delivery of the second child(r=-0.22) and negative correlation with the number of child at the level of 5% of significance statistically(r=0.27). There were significant negative correlation between the rate of complaints of physical symptom distress and the subjective evaluation whether she did Sanhujori well or not at the level of 5% of significance statistically(r=-0.23). And the rate of complaints of physical symptom distress in the group of women who experienced abortion was significantly higher than that of women who did not experience it at the level of 5% significance statistically(t=2.00) In conclusion, this finding reconfirmed the possible relationship between health status of chronic arthritis female patient and the experience of Sanhujori after delivery & abortion. It provides a challenge to the professional care givers to research further on the effects of Sanhujori on the health status, health recovery after abortion or delivery from the various aspects through the crosssectional and longitudinal research for the refinement of the reality of not only as cultural phenomenon but as conceptual model for the appropriateness of intervention and quality of care for desirable health outcomes.

• The Journal of the Petrological Society of Korea
• /
• v.6 no.3
• /
• pp.210-225
• /
• 1997

From their general natures of peraluminous, S-type and ilmenite-series granites, two-mica granites in the Cheongsan, Inje-Hongcheon, Yeongju and Namwon areas were originated from crust-derived granitic magma and solidified under reducing condition. Each two-mica granite in Inje-Hongcheon and Namwon districts was differentiated from the the residual magma of porphyric biotite granite and high Ti/Mg biotite granite, respectively. The genetic relationships between two-mica granite and porphyritic biotite granite in Chenongsan district and between two-mica granite and biotite granodiorite in Yeongju district are ambiguous. In Namwon district granitic magmas were water-saturated and possible water solubilities in magmas were more than 5.8wt.%. In Yeongju district two-mica granitic magma was nearly water-saturated and showed possible water solubilities between 2.4~5.8wt.%. Two-mica granitic magmas in Cheongsan and Inje-Hongcheon districts were water-undersaturated. Pressure-dependent minimum melt compositions (0.5~2kb) and petrographic textures of two-mica granites in Inje-Hongcheon and Yeongju districts represent that the granites intruded and solidified at shallow level, whereas those in Cheongsan and Namwon districts exhibit relatively deeper level of granitic intrusion (2-3kb). The intersection of granite-solidus/muscovite stability indicates that magmatic primary muscovite can be crystallized from the water-saturated magma above 1.6kb (ca. 6km), but below the pressure muscovite can be formed by the subsolidus reaction. On the other hand, more pressure would be necessary for the crystallization of primary muscovite from the water-undersaturated magma. This pressure condition can explain the occurrence of primary and secondary muscovites from the two-mica granites in the areas considered. The experimental muscovite stability must be cautious of the application to examine the origin of muscovite. The muscovite stability can move toward high temperature field with adding of Ti, Fe and Mg components to the octahedral site of pure muscovite end member.

• Journal of Aquaculture
• /
• v.19 no.2
• /
• pp.77-83
• /
• 2006

This study was conducted to investigate changes of hemolymph count, antioxidant enzyme activities (catalase: CAT and superoxide dismutase: SOD) and Heat Shock Protein 70 (HSP70) mRNA in hemolymph, hepatopancreas and gill of abalone (Haliotis sieboldii) exposed to various water temperatures. Abalones were exposed to 10, 15, 20, 25 or $30^{\circ}C$ for 0, 6, 12, 24 or 48 hours. Survival rate of abalone was 100% at 10, 15, 20 and $25^{\circ}C$, but 0% at $30^{\circ}C$. Hemolymph counts increased at lower water temperatures (10 and $15^{\circ}C$) and decreased at $30^{\circ}C$. SOD activity decreased immediately after exposure to lower or higher water temperatures compared to the control ($20^{\circ}C$) with an exception at $30^{\circ}C$ where the activity increased. At lower temperatures, SOD activity rose high after 24 hours, but decreased again at 48 hours. At $25^{\circ}C$, it decreased compared to the control. CAT activity decreased immediately after exposure to 10 or $25^{\circ}C$ compared to the control, and then was recovered to the initial level after increment. At $15^{\circ}C$, CAT activity was high after 6 hours, and then was recovered to the initial level after increment. At $30^{\circ}C$, the activity decreased throughout the experiment. The HSP70 mRNA expression in gill increased at lower temperatures compared to the control ($20^{\circ}C$) and $25^{\circ}C$. In this study, rapid change of wale, temperature caused stress response in abalone which had been raised at $20^{\circ}C$. At molecular level, HSP70 was expressed rapidly, but antioxidant enzymes like SOD and CAT were expressed later than HSP70. At 15 and $25^{\circ}C$ of water temperatures, the HSP70, SOD and CAT expression were stable with time. However, at $30^{\circ}C$, all abalone died possibly because they could not develop resistance to high temperature.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.5 no.1
• /
• pp.31-37
• /
• 1976

1. In order to increase our physical power through raising the amount of Hb to normal level and thus enrich our national power, it is earnestly required to improve the general eating habits in the direction of taking enough animal protein (nutrition food) that is required to form Hb and adequate administrative procedures of the nursery school are to be taken at the same time. 2. The genetic amentia's development of skeleton is generally under the normal level. And so their physical condition should be inferior to the standard growth rate of the same age. But the fact is that their physical growth is almost the same as the same age with only few exceptions. Besides, considering the fact that their amount of Hb is less than that of the normal level, I think we can conclude that the majority of the amentia in the nursery school were malnutrition during their prenatal period or during their infancy. We need continuous statistical study concerning many amentia that is scattered all part of our country, to make our amentia's hereditary transmission and the expression clear. And so the Intelligence Quotient of the amentia are from 26 to 80, we consider to need nourishing meal in ordinary times to make more efficient development of intellectual faculties. 3. As to the relation between blood type and disease, there are much debates going on in many countries. To get more apodictic results, however, continuous study is desired to be made in the future.

• Journal of Korean Society of Forest Science
• /
• v.97 no.3
• /
• pp.204-214
• /
• 2008

This study was conducted to analyze the influence of simulated acid rain on growth of Liliodendron tulipifera seedlings. The seedlings were treated with four levels of simulated acid rain, 5.6, 4.9, 3.9, or 2.9, and dry weight, growth of stem and root were investigated. There were statistically significant differences at 1% and 5% in the total dry weight of the above-part among the simulated acid rain treated groups with different levels of pH and different types of soil. The dry weight of the above part tended to decrease as the acidity of the simulated acid rain increases. The total dry weight of the below-part was significantly different according to the levels of acidity of the acid rain in all three soils and was shown a significant difference according to the soil types at only pH 2.9 plot. The dry weight of the below part in soils A and C decreased as the pH level decreases. The rate of stem growth was significantly different among the treatment groups of acidity of the acid rain at significance level of 0.01 and among the treatment groups of soil types at 0.01 and 0.05 levels from June to August. In all three soil types, the greatest stem growth occurred during the period of June. Moreover, stem growth was promoted at pH 3.9 plot and pH 4.9 plot whereas it was suppressed at pH 2.9 plot. Though the amount of fine roots and very fine roots in soil depth of 0-7 cm and 7-14 cm were significantly different among the treatment groups of pH level, fine root was not shown a significant difference among the pH groups in soil depth of 14-21cm. The types of soil significantly affected only on the amount of the very fine root.