• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.1-17
• /
• 2019

Because stock price forecasting is an important issue both academically and practically, research in stock price prediction has been actively conducted. The stock price forecasting research is classified into using structured data and using unstructured data. With structured data such as historical stock price and financial statements, past studies usually used technical analysis approach and fundamental analysis. In the big data era, the amount of information has rapidly increased, and the artificial intelligence methodology that can find meaning by quantifying string information, which is an unstructured data that takes up a large amount of information, has developed rapidly. With these developments, many attempts with unstructured data are being made to predict stock prices through online news by applying text mining to stock price forecasts. The stock price prediction methodology adopted in many papers is to forecast stock prices with the news of the target companies to be forecasted. However, according to previous research, not only news of a target company affects its stock price, but news of companies that are related to the company can also affect the stock price. However, finding a highly relevant company is not easy because of the market-wide impact and random signs. Thus, existing studies have found highly relevant companies based primarily on pre-determined international industry classification standards. However, according to recent research, global industry classification standard has different homogeneity within the sectors, and it leads to a limitation that forecasting stock prices by taking them all together without considering only relevant companies can adversely affect predictive performance. To overcome the limitation, we first used random matrix theory with text mining for stock prediction. Wherever the dimension of data is large, the classical limit theorems are no longer suitable, because the statistical efficiency will be reduced. Therefore, a simple correlation analysis in the financial market does not mean the true correlation. To solve the issue, we adopt random matrix theory, which is mainly used in econophysics, to remove market-wide effects and random signals and find a true correlation between companies. With the true correlation, we perform cluster analysis to find relevant companies. Also, based on the clustering analysis, we used multiple kernel learning algorithm, which is an ensemble of support vector machine to incorporate the effects of the target firm and its relevant firms simultaneously. Each kernel was assigned to predict stock prices with features of financial news of the target firm and its relevant firms. The results of this study are as follows. The results of this paper are as follows. (1) Following the existing research flow, we confirmed that it is an effective way to forecast stock prices using news from relevant companies. (2) When looking for a relevant company, looking for it in the wrong way can lower AI prediction performance. (3) The proposed approach with random matrix theory shows better performance than previous studies if cluster analysis is performed based on the true correlation by removing market-wide effects and random signals. The contribution of this study is as follows. First, this study shows that random matrix theory, which is used mainly in economic physics, can be combined with artificial intelligence to produce good methodologies. This suggests that it is important not only to develop AI algorithms but also to adopt physics theory. This extends the existing research that presented the methodology by integrating artificial intelligence with complex system theory through transfer entropy. Second, this study stressed that finding the right companies in the stock market is an important issue. This suggests that it is not only important to study artificial intelligence algorithms, but how to theoretically adjust the input values. Third, we confirmed that firms classified as Global Industrial Classification Standard (GICS) might have low relevance and suggested it is necessary to theoretically define the relevance rather than simply finding it in the GICS.

• Korean Journal of Environmental Agriculture
• /
• v.38 no.3
• /
• pp.166-172
• /
• 2019

BACKGROUND: Increase in the ratio of small berries in blueberry production decreases the farmers' profits due to weakening market competitiveness and lowering harvest efficiency. One of the reasons for increased small berries is over fruit-load. For improving productivity and competitiveness of blueberry in Korea, hand-thinning can be applied to increase fruit quality before the developing adequate chemical thinning methods. This study was conducted to investigate the proper timing and methods for floral buds thinning in rabbiteye blueberry. METHODS AND RESULTS: Eight years old bushes of rabbiteye bluberries 'Brightwell' as a primary cultivar and 'Powderblue' as a pollinizer were used for this study. Fruit size distribution by leaf-to-fruit ratio was investigated by counting the number of leaves and fruits in canes of 127 'Brightwell' plants whose fruit set varied. Fifty percent of flowers/floral buds were removed in four different floral buds stages such as bud swell, late pink bud, full bloom, and petal fall, and the consumed time for thinning and fruit characteristics were recorded to investigate the effect and proper timing of floral buds thinning. Fruit weight and soluble solids content tended to increase in proportion to leaf-to-fruit ratio and the production of the number of fruits less than 13 mm in diameter decreased when leaf-to-fruit ratio was more than 2.5. Manual floral buds thinning by hands was fastest in full bloom stage and slowest in bud swelling stage. In all cultivars, fruit size was significantly smaller in non-thinning treatment than thinning, and there was, however, no significant difference in total fruit yield. The number of fruits less than 13 mm in diameter increased in both cultivars as floral buds thinning was delayed. Consumed time for picking 90% berries out of total berries per bush was shortest in full bloom stage thinning in 'Brightwell' and bud swelling, full bloom thinning in 'Powderblue'. These were 25 and 20 days faster than no thinning, respectively. CONCLUSION: Although the effect of floral buds thinning varied depending on the cultivars, our results confirmed that floral buds thinning was effective for the early intensive harvesting and the increase of the large fruit ratio and the harvesting productivity. Also, in order to increase thinning efficiency, it is recommended to remove the flower buds before the full bloom stage.

• Phonetics and Speech Sciences
• /
• v.11 no.1
• /
• pp.29-40
• /
• 2019

The paper investigates the minimal pair of Korean phonemes quantitatively. To achieve this goal, I calculated the number of consonant minimal pairs in the syllable-initial position as both raw counts and relative counts, and analyzed the part of speech relations of the two words in the minimal pair. "Urimalsaem" was chosen as the object of this study because it was judged that the minimal pair analysis should be done through a dictionary and it is the largest among Korean dictionaries. The results of the study are summarized as follows. First, there were 153 types of minimal pairs out of 337,135 examples. The ranking of phoneme pairs from highest to lowest was 'ㅅ-ㅈ, ㄱ-ㅅ, ㄱ-ㅈ, ㄱ-ㅂ, ㄱ-ㅎ, ${\ldots}$, ㅆ-ㅋ, ㄸ-ㅋ, ㅉ-ㅋ, ㄹ-ㅃ, ㅃ-ㅋ'. The phonemes that played a major role in the formation of the minimal pair were /ㄱ, ㅅ, ㅈ, ㅂ, ㅊ/, in that order, which showed a high proportion of palatals. The correlation between the raw count of minimal pairs and the relative count of minimal pairs was found to be quite high r=0.937. Second, 87.91% of the minimal pairs shared the part of speech (same syntactic category). The most frequently observed type has been 'noun-noun' pair (70.25%), and 'vowel-vowel' pair (14.77%) was the next ranking. It can be indicated that the minimal pair could be grouped into similar categories in terms of semantics. The results of this study can be useful for various research in Korean linguistics, speech-language pathology, language education, language acquisition, speech synthesis, and artificial intelligence-machine learning as basic data related to Korean phonemes.

• Korean Journal of Breeding Science
• /
• v.50 no.4
• /
• pp.406-414
• /
• 2018

This study was conducted to develop environmental risk assessments and biosafety guides for insect-resistant genetically modified rice in an LMO (Living Modified Organism) isolation field. In the LMO quarantine area of Kyungpook National University, the species diversities and population densities of non-target insects found on insect-resistant genetically modified rice (Bt-T), rice resistant to Cnaphalocrocis medinalis, and non-GM rice (Dongjin-byeo and Ilmi-byeo) were investigated. The Bt-T plants were, therefore, evaluated under field conditions to detect possible impacts on above ground insects and spiders. In 2016 and 2017, the study compared transgenic rice and two non-GM reference rice, namely Dongjin-byeo and Ilmi-byeo, at Gunwi. A total of 9,552 individuals from 51 families and 11 orders were collected from the LMO isolation field. From the three types of rice fields, a total of 3,042; 3,212; and 3,297 individuals from the Bt-T, Dongjin-byeo, and Ilmi-byeo were collected, respectively. There was no difference between the population densities of the non-target insect pests, natural enemies, and other insects on the Bt-T compared to non-GM rice. The data on insect species population densities were subjected to principal component analysis (PCA) without distinguishing between the three varieties, namely GM, non-GM, and reference cultivar, in all cultivation years. However, the PCA clearly separated the samples based on the cultivation years. These results suggest that insect species diversities and population densities during plant cultivation are determined by environmental factors (growing condition and seasons) rather than by genetic factors.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.10
• /
• pp.261-268
• /
• 2021

Cloud computing is a computing paradigm in which users can utilize computing resources in a pay-as-you-go manner. In a cloud system, resources can be dynamically scaled up and down to the user's on-demand so that the total cost of ownership can be reduced. The Modeling and Simulation (M&S) technology is a renowned simulation-based method to obtain engineering analysis and results through CAE software without actual experimental action. In general, M&S technology is utilized in Finite Element Analysis (FEA), Computational Fluid Dynamics (CFD), Multibody dynamics (MBD), and optimization fields. The work procedure through M&S is divided into pre-processing, analysis, and post-processing steps. The pre/post-processing are GPU-intensive job that consists of 3D modeling jobs via CAE software, whereas analysis is CPU or GPU intensive. Because a general-purpose desktop needs plenty of time to analyze complicated 3D models, CAE software requires a high-end CPU and GPU-based workstation that can work fluently. In other words, for executing M&S, it is absolutely required to utilize high-performance computing resources. To mitigate the cost issue from equipping such tremendous computing resources, we propose HEMOS-Cloud service, an integrated cloud and cluster computing environment. The HEMOS-Cloud service provides CAE software and computing resources to users who want to experience M&S in business sectors or academics. In this paper, the economic ripple effect of HEMOS-Cloud service was analyzed by using industry-related analysis. The estimated results of using the experts-guided coefficients are the production inducement effect of KRW 7.4 billion, the value-added effect of KRW 4.1 billion, and the employment-inducing effect of 50 persons per KRW 1 billion.

• Journal of Food Hygiene and Safety
• /
• v.36 no.4
• /
• pp.298-309
• /
• 2021

In this study we sought to develop a simultaneous analysis method for cis-bixin and cis-norbixin, the main components, to detect annatto pigment in food. To establish the optimal test method, the HPLC analysis methods of the European Food Safety Authority (EFSA), Japan's Ministry of Health, Labor and Welfare (MHLW), and National Institute of Food and Drug Safety Evaluation (NIFDS) were compared and reviewed. In addition, a new pretreatment method applicable to various foods was developed after selecting conditions for simultaneous high-performance liquid chromatography (HPLC) analysis in consideration of linearity, limit of detection (LOD), limit of quantification (LOQ), and analysis time. The HPLC analysis method of NIFDS showed the best linearity (R² ≥ 0.999), exhibiting low detection and quantification limits for cis-norbixin and cis-bixin as 0.03, 0.05 ㎍/mL, and 0.097, 0.16 ㎍/mL, respectively. All previously reported pretreatment methods had limitations in various food applications. However, the new pretreatment method showed a high recovery rate for all three main food groups of fish meat and meat products, processed cheese and beverages. This method showed an excellent simultaneous recovery rate of 98% or more for cis-bixin and cis-norbixin. The HPLC analysis method with a new pretreatment method showed high linearity with a coefficient of determination (R²) of 1 for both substances, and the accuracy (recovery rate) and precision (%RSD) were 98% and between 0.4-7.9, respectively. From this result, the optimized analytical method was considered to be very suitable for the simultaneous analysis of cis-bixin and cis-norbixin, two main components of annatto pigment in food.

• Journal of Bio-Environment Control
• /
• v.28 no.4
• /
• pp.366-375
• /
• 2019

This experiment aims to determine the proper irrigation scheduling based on a whole-substrate capacitance using a newly developed device (SCMD) by comparing with the integrated solar radiation automated irrigation system (ISR) and sap flow sensor automated irrigation system (SF) for the cultivation of tomato (Solanum lycopersicum L. 'Hoyong' 'Super Doterang') during spring to winter season. For the SCMD system, irrigation was conducted every 10 minutes after the first irrigation was started until the first run-off was occurred, of which the substrate capacitance was considered to be 100%. When the capacitance threshold (CT) was reached to the target point, irrigation was re-conducted. After that, when the target drain volume (TDV) was occurred, the irrigation stopped. The irrigation volume per event for the SCMD was set to 50, 75, or 100 mL at CT 0.9 and TDV 100 mL during the spring to summer cultivation, and the CT was set to 0.65, 0.75, 0.80, or 0.90 in the winter cultivation. When the irrigation volume per event was set to 50, 75, or 100 mL, the irrigation frequency in a day was 39, 29, and 19, respectively, and the drain rate was 3.04, 9.25, and 20.18%, respectively. When the CT was set to 0.65, 0.75, or 0.90 in winter, the irrigation frequency was about 6, 7, 15 times, respectively and the drain rate was 9.9, 10.8, 35.3% respectively. The signal of stem sap flow at the beginning of irrigation starting time did not correspond to that of solar irradiance when the irrigation volume per event was set to 50 or 75 mL, compared to that of 100 mL. In winter cultivation, the stem sap flow rate and substrate volumetric water content at the CT 0.65 treatment were very low, while they were very high at CT 0.90 was high. All the integrated data suggest that the proper range of irrigation volume per event is from 75 to 100 mL under at CT 0.9 and TDV 100 mL during the spring to summer cultivation, and the proper CT seems to be higher than 0.75 and lower than 0.90 under at 75 mL of the irrigation volume per event and TDV 70 mL during the winter cultivation. It is going to be necessary to investigate the relationship between capacitance value and substrate volumetric water content by determining the correction coefficient.

• Journal of Nutrition and Health
• /
• v.53 no.6
• /
• pp.629-647
• /
• 2020

Purpose: This study was undertaken to develop a nutrition quotient for elementary school children (NQ-C) for evaluating the overall dietary quality and eating behaviors. Methods: The NQ-C was developed by implementing 3 stages: item generation, item reduction, and validation. Candidate food behavior checklist (FBC) items of the NQ-C were derived from systematic literature reviews, expert in-depth interviews, statistical analyses of the fifth Korean National Health and Nutrition Examination Survey data, and national nutrition policies and recommendations. For the pilot survey, 260 elementary school students (128 second graders and 132 fifth graders) completed self-administered questionnaires as well as 24-hour dietary intakes, with the help of their parents and survey team staff, if required. Based on the pilot survey results, expert reviews, and priorities of national nutrition policy and recommendations, checklist items were reduced from 41 to 24. A total of 20 items for NQ-C were finally selected from results generated from 1,144 nationwide samples surveyed. Construct validity of the NQ-C was assessed using the confirmatory factor analysis, LInear Structural RELations. Results: Analyses of the exploratory factors of NQ-C identified that 5 dimensions of diet (balance, diversity, moderation, practice and environment) accounted for 46.2% of the total variance. Standardized path coefficients were used as weights of the items. The NQ-C and 5-factor scores of the subjects were calculated using the obtained weights of the FBC items. Conclusion: Our data indicates that NQ-C is a useful and suitable instrument for assessing nutrition adequacy, dietary quality, and eating behaviors of Korean elementary school children.

• (The) Korean Journal of Educational Psychology
• /
• v.32 no.1
• /
• pp.99-130
• /
• 2018

The purpose of this study was to examine the longitudinal relationship between resilience and social support of school violence exposure types including school bullying, victimization, and dual experience. The study used data obtained from the third year (2012) of the Seoul Education Longitudinal Study of 1,137 elementary school students in grade 6 who reported experiencing school violence. The results of the autoregressive cross-lagged model are as follows. First, as a result of measuring the self-regression coefficients of resilience and social support of the youth exposed to school violence at 3 time points (2012, 2014, and 2016), it was found for all types of violence that resilience and social support at the previous time point showed a signigicant positive effect on the same variable at the next time point. Second, in the case of the cross-lagged effects of resilience and social support, the effect of previous social support on resilience at the next time point was statistically significant for the victimization group, but not for the bullying or dual experience groups. Third, considering the opposite path from resilience to social support, resilience at the previous time point had a significant influence on the social support at the next time point for both the bullying and victimization groups. This result is new and can be complementary to the cross-sectional studies so far using a longitudinal view. The results of this study suggest that the bullying and victimized students who are relatively more resilient are less likely to perceive social support than those who are not resilient. Finally, we discuss the longitudinal relationship between resilience and social support, the limitations of this study, and implications for future research.

• Korean Journal of Food Science and Technology
• /
• v.52 no.6
• /
• pp.565-572
• /
• 2020

The 3-monochloropropane-1,2-diol (3-MCPD) is a contaminant that occurs in foodstuffs in its free form as well as in its bound form. The objective of this study was to evaluate the effects of emulsifier, frying temperature, and the amounts of salt and oil on the formation of bound 3-MCPD in a fried snack model. Emulsifier affected the formation of bound 3-MCPD; furthermore, it was observed that the largest amount of bound 3-MCPD was detected in the fried snack model when glycerin esters of fatty acids were used as emulsifiers. Frying temperature also affected the formation of bound 3-MCPD, which increased significantly as the frying temperature increased from 145 to 190℃. In addition, salt affected the formation of bound 3-MCPD. As the amount of salt increased, the amount of bound 3-MCPD also increased significantly. Moreover, it was observed that the amount of oil did not affect the formation of bound 3-MCPD. These results will aid in the reduction of bound 3-MCPD in fried snacks.