• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.1-19
• /
• 2018

Since stock movements forecasting is an important issue both academically and practically, studies related to stock price prediction have been actively conducted. The stock price forecasting research is classified into structured data and unstructured data, and it is divided into technical analysis, fundamental analysis and media effect analysis in detail. In the big data era, research on stock price prediction combining big data is actively underway. Based on a large number of data, stock prediction research mainly focuses on machine learning techniques. Especially, research methods that combine the effects of media are attracting attention recently, among which researches that analyze online news and utilize online news to forecast stock prices are becoming main. Previous studies predicting stock prices through online news are mostly sentiment analysis of news, making different corpus for each company, and making a dictionary that predicts stock prices by recording responses according to the past stock price. Therefore, existing studies have examined the impact of online news on individual companies. For example, stock movements of Samsung Electronics are predicted with only online news of Samsung Electronics. In addition, a method of considering influences among highly relevant companies has also been studied recently. For example, stock movements of Samsung Electronics are predicted with news of Samsung Electronics and a highly related company like LG Electronics.These previous studies examine the effects of news of industrial sector with homogeneity on the individual company. In the previous studies, homogeneous industries are classified according to the Global Industrial Classification Standard. In other words, the existing studies were analyzed under the assumption that industries divided into Global Industrial Classification Standard have homogeneity. However, existing studies have limitations in that they do not take into account influential companies with high relevance or reflect the existence of heterogeneity within the same Global Industrial Classification Standard sectors. As a result of our examining the various sectors, it can be seen that there are sectors that show the industrial sectors are not a homogeneous group. To overcome these limitations of existing studies that do not reflect heterogeneity, our study suggests a methodology that reflects the heterogeneous effects of the industrial sector that affect the stock price by applying k-means clustering. Multiple Kernel Learning is mainly used to integrate data with various characteristics. Multiple Kernel Learning has several kernels, each of which receives and predicts different data. To incorporate effects of target firm and its relevant firms simultaneously, we used Multiple Kernel Learning. Each kernel was assigned to predict stock prices with variables of financial news of the industrial group divided by the target firm, K-means cluster analysis. In order to prove that the suggested methodology is appropriate, experiments were conducted through three years of online news and stock prices. The results of this study are as follows. (1) We confirmed that the information of the industrial sectors related to target company also contains meaningful information to predict stock movements of target company and confirmed that machine learning algorithm has better predictive power when considering the news of the relevant companies and target company's news together. (2) It is important to predict stock movements with varying number of clusters according to the level of homogeneity in the industrial sector. In other words, when stock prices are homogeneous in industrial sectors, it is important to use relational effect at the level of industry group without analyzing clusters or to use it in small number of clusters. When the stock price is heterogeneous in industry group, it is important to cluster them into groups. This study has a contribution that we testified firms classified as Global Industrial Classification Standard have heterogeneity and suggested it is necessary to define the relevance through machine learning and statistical analysis methodology rather than simply defining it in the Global Industrial Classification Standard. It has also contribution that we proved the efficiency of the prediction model reflecting heterogeneity.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.608-611
• /
• 2003

선진국입을 목전에 둔 한국경제의 발전을 위해서 지식과 기술을 기반으로 한 벤처기업의 생성과 발전은 매우 중요한 요소라 할 수 있다. 민과 관의 적절한 벤처 투자는 미래의 기업가들에게 신지식 창조의 동기를 부여하고 성장, 발전단계에 있는 기업들에게 자본을 공급함으로써 미래의 산업을 창조하는 매우 중요한 활동이다. 국내외적으로 벤처 투자자본에 대한 연구가 활발히 진행되어 왔으나 재무론을 바탕으로 한 벤처투자에 관한 연구와 다양한 벤처투자자본들의 유형과 투자행태 등을 설문지를 통해 밝혀내는 탐색적 연구들에 국한되어 연구, 발표되고 있는 실정이다. 본 연구에서는 벤처자본시장의 대표적 투자자본인 사적 창업투자회사와 정부 벤처정책투자 간의 전략적 상호작용을 가격모델을 통해 고찰하였다. Bertrand paradox의 가정에서 기술한 바와 같이 정부 벤처정책투자간 민간 창업투자회사들과 같은 투자전략을 구사하면 민간 창업투자회사들은 시장에서 살아남기 어렵고 결과적으로 정부는 벤처기업의 생성 및 발전지원이라는 목적에 부합되지 않은 투자를 한 것이 된다. Hotelling(1929)의 위치차별모델이 역설하는 바와 같이 정부 벤처정책투자는 사적 창업투자회사가 지향하는 투자와는 다른 투자정책을 구사할 때만 벤처기업 육성이라는 목표를 효율적으로 수행할 수가 있을 것이다. 이 연구 논문에서는 다양한 투자변수에 대한 Nash Equibrium이 존재함을 증명함으로써 사적 창업투자회사와 정부의 벤처정책투자가 벤처기업의 육성이라는 목적에 맞는 효율적 투자를 하기 위해 취해야 할 투자 전략들을 밝혀내었다.가 있는 것 같다. 따라서 본 연구에서는 웹기반 쇼핑시스템의 확산에 관련된 균형된 분석을 수행하기 위하여 경영(management)과 기술 (technology)을 조화롭게 고려한 관점에서 연구를 수행하고자 한다. 즉, 본 논문에서는 기술적 측면(technical aspect)과 경영적 측면(management aspect)을 동시에 고려하여 웹기반 쇼핑시스템의 주요만 특성을 살펴보고, 향후 정보통신 기술(ICT)의 확산에 관한 연구에서 두 가지 관점의 통합적 중요성에 대하여 강조하고자 한다. 그에 덧붙여 웹기반 쇼핑시스템과 다른 정보시스템을 비교하여 전자상거래 환경에서 웹기반 쇼핑시스템의 주요만 특성들이 두가지 연구관점에서 어떻게 개념화 될 수 있는지를 고찰하고자 한다. 이러만 분석에 기반하여 본 연구에서는 기술적 측면과 경영적인 측면을 동시에 고려한 웹기반 쇼핑시스템의 특성을 제시하고자 한다. 결론적으로 본 연구의 목적은 본 논문에서 적용한 기술(technical)과 경영(management)의 조화로운 연구관점이 향후 정보통신 기술이나 시스템, 그리고 전자상거래에 관련된 일련의 연구에 적응되어 보다 균형잡힌 논의와 분석이 이루어 질 수 있는 시발점이 되길 기대한다.생된 $CH_{4}$를 회수하여 이용하면 대체에너지원으로 활용 가치가 높은 것으로 판단된다./207), $99.2\%$(238/240), $98.5\%$(133/135) 및 $100\%$ (313)였다. 각각 두 개의 요골동맥과 우내흉동맥에서 부

• Journal of Korean Philosophical Society
• /
• v.116
• /
• pp.281-312
• /
• 2010

Der vorliegende Beitrag problematisiert die Zeichen einer Zeit, in der nach der 'Wende des Sprachparadigmas' alle Prozesse einer Posttranszendenz, die in der heutigen philosophischen Problemsituation versucht werden, $bel{\ddot{a}}chelt$ werden, der Relativismus, Partikularismus und Skeptizismus $verst{\ddot{a}}rkt$ wird, und als Resultat die Kritik, Ablehnung und das Desinteresse an der Ideologie der Vernunft und Wahrheit sich verbreitet. Ich werde daher umgekehrt gerade an diesem Punkt ansetzen und ${\ddot{u}}ber$ die Notwendigkeit und Dringlichkeit der Rehabilitierung der "$Realit{\ddot{a}}t$ einer moralischen Vernunft" nachdenken. Zweck dieses Beitrags ist es, in Zusammenhang mit der Rehabilitierung der $Realit{\ddot{a}}t$ einer moralischen Vernunft, aufzuzeigen, welche theoretische Erkenntnis bzw.moralische Erkenntnis wahr ist, d.h., dass ein 'bewiesenes', da 'objektiv gerechtfertigtes' Argument existiert. $Daf{\ddot{u}}r$ werde ich als erstes auf das Problem der Relativistischen und Skeptizistischen Anhaltspunkte philosophisch eingehen(2), zur ${\ddot{U}}berwindung$ dieser Anhaltspunkte eine Rechtfertigung der rationelen und moralischen $Begr{\ddot{u}}ndung$ versuchen(3). In Folge soll betrachtet werden, dass die Rechtfertigung der rational moralischen $Begr{\ddot{u}}ndung$ mit dem Problem der $Letztbegr{\ddot{u}}ndung$ in enger Verbindung steht(4), und nachdem darauf hingewiesen wird, dass dies durch eine Konfrontation mit der Fallibilismus These zu erkenntnistheoretisch objektiver $G{\ddot{u}}ltigkeit$ gelangt(5), werde ich den Beitrag $abschlie{\ss}en$(6).

• Clinical and Experimental Pediatrics
• /
• v.45 no.7
• /
• pp.862-874
• /
• 2002

Purpose : We tried to evaluate whether the detection rate of Helicobacter pylori in gastric biopsy specimens could be improved by using pre-embedding immunoelectron microscopy. Methods : A total of 119 children who complained of upper gastrointestinal symptoms were endoscoped at the Gyeongsang National University Hospital from July, 1996 to July, 1999. Five biopsy specimens(three for urease test, one for hematoxylin-eosin(H & E) staining, and one for preembedding immunoelectron microscopy) were obtained from each antrum and body. Immunoblotting analysis were also performed. Results : Among the 119 patients, H. pylori were found in 116 patients(97.5%) by the immunoelectron microscopy. Among three patients who were found H. pylori negative in immunoelectron microscopy, two patients showed H. pylori in H & E stained slides and one patient was urease test positive(color change within six hours). Urease tests were positive in 107 patients(89.9 %). The positive rate of immunoblotting tests was 81.5%. However, only 13 patients(10.9%) showed H. pylori on the H & E stained antrum or body tissue. Conclusion : In this study, we found H. pylori histopathologically in most of the pediatric patients who complained of upper gastrointestinal symptoms. This study showed that pre-embedding immunoelectron microscopic examinations can be used as a gold standard in the diagnosis of childhood H. pylori infection. However, this method also has limited capacity to detect widely scattered H. pylori compared to the other histopathologic diagnostic methods.

• Tuberculosis and Respiratory Diseases
• /
• v.50 no.2
• /
• pp.222-228
• /
• 2001

Backgrounds : Recent technological developments have introduced a new method to identifying M. tuberculosis complex DNA in clinical samples directly. The direct amplification test (DAT) is approved for identifying M. tuberculosis complex in respiratory specimens that are smear-positive for acid-fast bacilli (AFB). When there is a discrepancy between the AFB smear and DAT, no information on their clinical utility is currently available. In this study, the diagnostic reliability of DAT was investigated in suspected pulmonary tuberculosis patients whose sputum AFB smear was negative. Methods : From June 1, 1998 through May 30, 1999, 909 patients with presumed active pulmonary tuberculosis were enrolled. A sputum AFB stain, culture, DAT and/or biopsy were performed. Using the criteria of clinical tuberculosis or confirmed tuberculosis, the positive predictive value of DAT in diagnosing pulmonary tuberculosis was investigated. Results : The positive predictive value of DAT was 82.1% by the clinically active tuberculosis criteria. However, it decreased to 61.5% when diagnosis was restricted to only to culture positive or biopsy proven cases. The false positive rate of DAT was 18.0%. Conclusion : The DAT is a valuable diagnostic method in suspected patients whose sputum AFB is was negative.

• Tuberculosis and Respiratory Diseases
• /
• v.46 no.3
• /
• pp.338-349
• /
• 1999

Polymorphonuclear leukocytes(PMN) are the predominant inflammatory cells recruited in acute lung injury such as adult respiratory distress syndrome, pneumonia and also chronic lung disease such as idiopathic pulmonary fibrosis and pulmonary emphysema. Interleukin-8(IL-8) is an 8,000 D protein produced by many cells and has potent neutrophil chemoattractant and activating properties. The GRO, also called melanoma growth-stimulatory activity(MGSA), referring to a peptide of 73 amino acids, was reported to be mitogenic for cultured human melanoma cells. Mature GRO/MGSA has marked sequence similarity to IL-8. In view of the structural similarities to IL-8, it was of particular interest to test GRO for neutrophil activating and chemotactic properties. We found a significant release of IL-8 and GRO/MGSA from the cultured human umbilical vein endothelial cell(HUVEC) which was stimulated either with TNF$\alpha$ or IL-1$\beta$ and also found the expression of IL-8 and GRO/MGSA mRNA. Neutrophil chemotactic activity was enhanced in accordance with the increased IL-8 and GRO/MGSA. Our study also suggest that the IL-8 is more important in the increased neutrophil chemotactic activity than GRO/MGSA when endothelial cell is stimulated with TNF$\alpha$ or IL-1$\beta$ in vitro.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.4
• /
• pp.760-765
• /
• 1998

Background: Glucose uptake has been found to be increased in cancer cells, and FDG-PET imaging is used for diagnosis of cancer using this phenomenon. However, the exact mechanism of increased glucose uptake in cancer cells has not been clarified. Recent studies demonstrated the presence of glucose transporter(GLUT) mRNA expression in gastrointestinal cancer and head and neck cancer, and suggested that GLUT may be associated with glucose uptake in cancer cells. In lung cancer cells, glucose metabolism is also known to be increased. We evaluated GLUT mRNA expression in human lung cancer cell lines in order to find out the mechanism of increased glucose uptake in lung cancer. Method: Total RNA was isolated from 15 human lung cancer cell lines and immortalized bronchial epithelial cell line(BEAS-2B). After electrophoresis of $20{\mu}g$ total RNA, Northern blot analysis was done using GLUT1 cDNA and GLUT3 cDNA as probes. Results: Thirteen of 14 human lung cancer cell lines expressed GLUT1 mRNA and 10 of 14 human lung cancer cell lines expressed GLUT3 mRNA. Eight human lung cancer cell lines expressed both GLUT mRNAs. BEAS-2B expressed GLUT1 mRNA and did not express detectable GLUT3 mRNA. Conclusion: The increase of glucose metabolism in lung cancer may be associated with GLUT1 and GLUT3 expression.

• Journal of Wetlands Research
• /
• v.24 no.2
• /
• pp.83-92
• /
• 2022

The amount of the plastic waste has been increasing according to global demand for plastic. Microplastics are the most hazardous among all plastic pollutants due to their toxicity and unknown physicochemical properties. This study investigates the optimal methodology that can be applied to sewage samples for detecting microplastics before discussing reducing microplastics in MWTPs. In this study, the effect of different pretreatment methods while detecting microplastic analysis of MWTP influent samples was investigated; the samples were collected from the J sewage treatment plant. There are many pretreatment methods but two of them are widely used: Fenton digestion and hydrogen peroxide oxidation. Although there are many pretreatment methods that can be applied to investigate microplastics, the most widely used methods for sewage treatment plant samples are Fenton digestion and H₂O₂ oxidation. For each pretreatment method, there were factors that could cause an error in the measurement. To overcome this, in the case of the Fenton digestion pretreatment, it is recommended to proceed with the analysis by filtration instead of the density separation method. In the case of the H₂O₂ oxidation method, the process of washing with distilled water after the reaction is recommended. As a result of the analysis, the concentration of microplastics was measured to be 2.75ea/L for the sample using the H₂O₂ oxidation method and 3.2ea/L for the sample using the Fenton oxidation method, and most of them were present in the form of fibers. In addition, it is difficult to guarantee the reliability of measurement results from quantitative analysis performed via microscope with eyes. A calibration curve was created for prove the reliability. A total of three calibration curves were drawn, and as a result of analysis of the calibration curves, all R² values were more than 0.9. This ensures high reliability for quantitative analysis. The qualitative analysis could determine the series of microplastics flowing into the MWTP, but could not confirm the chemical composition of each microplastic. This study can be used to confirm the chemical composition of microplastics introduced into MWTP in the future research.