• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.177-192
• /
• 2016

Machine learning is a field of artificial intelligence. It refers to an area of computer science related to providing machines the ability to perform their own data analysis, decision making and forecasting. For example, one of the representative machine learning models is artificial neural network, which is a statistical learning algorithm inspired by the neural network structure of biology. In addition, there are other machine learning models such as decision tree model, naive bayes model and SVM(support vector machine) model. Among the machine learning models, we use SVM model in this study because it is mainly used for classification and regression analysis that fits well to our study. The core principle of SVM is to find a reasonable hyperplane that distinguishes different group in the data space. Given information about the data in any two groups, the SVM model judges to which group the new data belongs based on the hyperplane obtained from the given data set. Thus, the more the amount of meaningful data, the better the machine learning ability. In recent years, many financial experts have focused on machine learning, seeing the possibility of combining with machine learning and the financial field where vast amounts of financial data exist. Machine learning techniques have been proved to be powerful in describing the non-stationary and chaotic stock price dynamics. A lot of researches have been successfully conducted on forecasting of stock prices using machine learning algorithms. Recently, financial companies have begun to provide Robo-Advisor service, a compound word of Robot and Advisor, which can perform various financial tasks through advanced algorithms using rapidly changing huge amount of data. Robo-Adviser's main task is to advise the investors about the investor's personal investment propensity and to provide the service to manage the portfolio automatically. In this study, we propose a method of forecasting the Korean volatility index, VKOSPI, using the SVM model, which is one of the machine learning methods, and applying it to real option trading to increase the trading performance. VKOSPI is a measure of the future volatility of the KOSPI 200 index based on KOSPI 200 index option prices. VKOSPI is similar to the VIX index, which is based on S&P 500 option price in the United States. The Korea Exchange(KRX) calculates and announce the real-time VKOSPI index. VKOSPI is the same as the usual volatility and affects the option prices. The direction of VKOSPI and option prices show positive relation regardless of the option type (call and put options with various striking prices). If the volatility increases, all of the call and put option premium increases because the probability of the option's exercise possibility increases. The investor can know the rising value of the option price with respect to the volatility rising value in real time through Vega, a Black-Scholes's measurement index of an option's sensitivity to changes in the volatility. Therefore, accurate forecasting of VKOSPI movements is one of the important factors that can generate profit in option trading. In this study, we verified through real option data that the accurate forecast of VKOSPI is able to make a big profit in real option trading. To the best of our knowledge, there have been no studies on the idea of predicting the direction of VKOSPI based on machine learning and introducing the idea of applying it to actual option trading. In this study predicted daily VKOSPI changes through SVM model and then made intraday option strangle position, which gives profit as option prices reduce, only when VKOSPI is expected to decline during daytime. We analyzed the results and tested whether it is applicable to real option trading based on SVM's prediction. The results showed the prediction accuracy of VKOSPI was 57.83% on average, and the number of position entry times was 43.2 times, which is less than half of the benchmark (100 times). A small number of trading is an indicator of trading efficiency. In addition, the experiment proved that the trading performance was significantly higher than the benchmark.

• Journal of the HCI Society of Korea
• /
• v.9 no.2
• /
• pp.23-31
• /
• 2014

A variety of writing support systems focus on the information management or the feature analysis of the commercially successful narrative texts. In these approaches, the reader's role in the narrative creating process is overlooked. During a writing work, an author anticipates the reader's response or expectation to the narrative and he/she organizes the narrative either along or against the prediction about readers. Assessing and controlling the reader's comprehension in the development of events influences the aesthetic quality of the narrative. In this paper, we suggest a writing support system to visualize and adjust the characteristics of a narrative text related to the reader's comprehension, which is theoretically based on the narrative structure model and the event-indexing situation model. Under the development of the support system, we designed an interactive framework to create events as the basic units of story and arrange them onto both story- and discourse-time axes. Using this framework, we analyzed the organization of events about an actual film narrative. We also proposed both the continuity of the situational dimensions and the cognitive complexity as the characteristics to affect the reader's comprehension, hence we devised a method to visualize and evaluate them. This method was applied to the actual film narrative and the result was discussed in the aspect of the features of the narrative and wiring support strategies.

• BMB Reports
• /
• v.40 no.5
• /
• pp.625-635
• /
• 2007

The enzyme squalene synthase (EC 2.5.1.21) catalyzes a reductive dimerization of two farnesyl diphosphate (FPP) molecules into squalene, a key precursor for the sterol and triterpene biosynthesis. A full-length cDNA encoding squalene synthase (designated as TcSqS) was isolated from Taxus cuspidata, a kind of important medicinal plants producing potent anti-cancer drug, taxol. The full-length cDNA of TcSqS was 1765 bp and contained a 1230 bp open reading frame (ORF) encoding a polypeptide of 409 amino acids. Bioinformatic analysis revealed that the deduced TcSqS protein had high similarity with other plant squalene synthases and a predicted crystal structure similar to other class I isoprenoid biosynthetic enzymes. Southern blot analysis revealed that there was one copy of TcSqS gene in the genome of T. cuspidata. Semi-quantitative RT-PCR analysis and northern blotting analysis showed that TcSqS expressed constitutively in all tested tissues, with the highest expression in roots. The promoter region of TcSqS was also isolated by genomic walking and analysis showed that several cis-acting elements were present in the promoter region. The results of treatment experiments by different signaling components including methyl-jasmonate, salicylic acid and gibberellin revealed that the TcSqS expression level of treated cells had a prominent diversity to that of control, which was consistent with the prediction results of TcSqS promoter region in the PlantCARE database.

• Korean Journal of Environment and Ecology
• /
• v.14 no.2
• /
• pp.111-118
• /
• 2000

본연구는 울릉도의 성인봉과 태하령 지역의 산림 식생을 대상으로 199년 7-8월에 식생조사와 토양조사에 의한 너도밤나무 군락의 임분구조 및 DCCA ordination을 이용하여 분석한 결과는 다음과 같다. 1. 울릉도 산림의 중요치를 각 군락별로 살펴보면 너도밤나무-섬조릿대 군락에서 중요치가 높은 종은 너도밤나무, 우산고로쇠, 마가목, 섬단풍, 섬벚나무 등의 순으로 너도 밤나무-일색고사리 군락은 우산고로쇠 너도밤나무, 마가목 층층나무, 등수국 등의 순으로 나타났다 그리고 너도밤나무-큰두루미꽃 군락에서 중요치가 높은 종은 너도밤나무 우산고로쇠 등수국 마가목 음나무등의 순으로 솔송나무-섬잣나무 군락은 섬잣나무, 너도밤나무, 솔송나무, 회솔나무, 섬피나무 등의 순으로 나타났다. 2. DCCA ordination에 의하면 산림군락과 환경요인과의 상관관계는 다음과 같다 너도밤나무-섬조릿대 군락은 해발고가 높고 네 군락 중 토양수분이나 전절소 유기물 등이 많은 지역에 분포하고 있었다. 너도밤나무-일색고사리 군락은 해발고가 다른 군집보다 높고 토양수분이나 전질소, 유기물 등이 많아 너도밤나무-섬조릿대 군락과 매우 유사한 입지환경을 가진 지역이나 토성 중 clay 가 많이 함유된 지역에 분포하고 있었다. 너도밤나무-큰두루미꽃 군락은 해발고가 네 군락 중 중간지역에 분포하고 있으며 토양수분이나 유기물, 전질소 등도 중간인 지역에 분포하고 있었다. 솔송나무-섬잣나무 군락은 해발고가 낮고 토양수분이나 전질소, 유기물이 적고 sand가 많이 함유된 토양에 분포하고 있었다. 3. 울릉도 산림군락으 Shannon의 종다양도 지수는 0.5455~0.8801으로 비교적 낮은 수치를 나타내고 있다. 또한 너도밤나무 군락에서 분포하고 있는 주요 종의 조서열 중요치 곡선을 보면 전체의 기울기가 완만하여 너도밤나무 군락은 안정적이라 할 수 있다.단 생산성 향상을 위한 세포의 고농도 배양에는 조사한 여러 배양 시스템 중에 가장 효율적인 시스템임올 알 수 있었다 하지만 이 시스템 에서 포도당을 낮은 level로 유지할 수 있었으나, 초산의 과도한 축적으로 항체 생산성의 향상은 예상에 비해 크지 않았다. 81%), C18 0(12.38%), C18: 1(25.93%), C22:6(9.95%)이며 결합지방질(結合脂肪質)은 C14 : 0(11.60%), C16 : 0(18.94%), C16: 1(10.42%). C18 : 1(10.89%), C22 : 6(23.44%)이었다. 총필수지방산(總必須脂肪酸) 함량(含量)은 극성지방질(極成脂肪質)$(20.14{\sim}31.12%)$이 비극성지방질(非極成脂肪質)$(6.97{\sim}11.13%)$보다 훨씬 높았고, 결합지방질(結合脂肪質)이 유리지방질(遊離脂肪質)보다 높았으며 부위별(部位別)로는 피부(皮部)$(15.18{\sim}15.41%)$가 육질부(肉質部)$(6.97{\sim}11.13%)$보다 높았다. 또${\omega}3$고도부포화지방산(高度不飽和脂肪酸) 함량(含量)은 육질부(肉質部)$(15.15{\sim}28.32%)$가 피부(皮部)$(6.77{\sim}18.18%)$나 내장부(內臟部)$(8.35{\sim}9.74%)$보다 높았으며, 육질부(肉質部)에서는 극성지방질(極成脂肪質)$(26.28{\sim}34.18%)$이 비극성지방질(非極成脂肪質)$(15.15{\sim}28.32%)$보다 높았다.veral world-wide prediction models. Based on the analysis, we can easilty know

• Journal of the Earthquake Engineering Society of Korea
• /
• v.1 no.2
• /
• pp.1-15
• /
• 1997

This paper presents substructural identification methods for the assessment of local damages in complex and large structural systems. For this purpose, an auto-regressive and moving average with stochastic input (ARMAX) model is derived for a substructure to process the measurement data impaired by noises. Using the substructural methods, the number of unknown parameters for each identification can be significantly reduced, hence the convergence and accuracy of estimation can be improved. Secondly, the damage index is defined as the ratio of the current stiffness to the baseline value at each element for the damage assessment. The indirect estimation method was performed using the estimated results from the identification of the system matrices from the substructural identification. To demonstrate the proposed techniques, several simulation and experimental example analyses are carried out for structural models of a 2-span truss structure, a 3-span continuous beam model and 3-story building model. The results indicate that the present substructural identification method and damage estimation methods are effective and efficient for local damage estimation of complex structures.

• Geophysics and Geophysical Exploration
• /
• v.13 no.1
• /
• pp.102-108
• /
• 2010

The internal structure of a river embankment must be delineated as part of investigations to evaluate its safety. Geophysical methods can be most effective means for that purpose, if they are used together with geotechnical methods such as the cone penetration test (CPT) and drilling. Since the dyke body and subsoil in general consist of material with a wide range of grain size, the properties and stratification of the soil must be accurately estimated to predict the mechanical stability and water infiltration in the river embankment. The strength and water content of the levee soil are also parameters required for such prediction. These parameters are usually estimated from CPT data, drilled core samples and laboratory tests. In this study we attempt to utilise geophysical data to estimate these parameters more effectively for very long river embankments. S-wave velocity and resistivity of the levee soils obtained with geophysical surveys are used to classify the soils. The classification is based on a physical soil model, called the unconsolidated sand model. Using this model, a soil profile along the river embankment is constructed from S-wave velocity and resistivity profiles. The soil profile thus obtained has been verified by geotechnical logs, which proves its usefulness for investigation of a river embankment.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.3
• /
• pp.287-298
• /
• 2014

In order to develop SFRC TBM tunnel segment, evaluating the SFRC mixture was conducted through flexural tests of SFRC beams without ordinary steel reinforcement in this study. Considered variables were compressive strengths of SFRC, aspect and mix ratio of steel fibers and total 16 specimens were fabricated and tested until failure. The load-vertical displacement results demonstrates that the effect of aspect ratio is minor when compared to results form small beam test(Moon et al, 2013). A SFRC beam resists the vertical load until the width of crack reaches to 7 mm due to steel fibers across cracked surfaces. Moreover, it is found that flexural moment estimated by equation of TR No. 63(Concrete Society, 2011) is useful for prediction of nominal strength for SFRC structure. From the investigation of fiber distribution in cracked section, it is found that dispersion improved in actual size beam compared to in standard small beam for evaluation of flexural strength.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.7
• /
• pp.4960-4968
• /
• 2015

In this study to improve the chloride durability of the shotcrete structure depending on types and contents of mineral admixture chloride resistance was evaluated by NT BUILD 492 of european test standards. It was also evaluated with the mechanical properties such as static strength and chloride penetration resistance. For shotcrete mixed crushed stone aggregate of the maximum size 10mm of coarse aggregates was produced. Based on 28days compression strength the variable mixed with 15% silica fume showed the highest strength in 67.55MPa. As the content of fly ash and blast furnace slag increased, the strength lowered. In the chloride penetration resistance test, OPC showed "high grade" and In the case of admixture, the penetration resistance tended to increase in all variables except the fly ash. In order to evaluate the service life, the accelerated chloride penetration test was conducted by the standards of KCL, ACI, FIB. Test results were obtained with the lowest spreading factor in a variable mixed with silica fume of 15%. At the KCI standards, It was found to have a service life of about 65 years and at the FIB standards, It was found to have a service life of 131 years. Among standards, the service life of KCI standard in all of the variables was evaluated as the lowest.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.3
• /
• pp.203-222
• /
• 2011

The characteristics of flood damages have been increasingly strengthened and take the form of unpredictable and unusual weather phenomena caused by climate change and climate anomalies. To prevent inundation damage caused by breach of hydraulic structure such as dam or levee, and trouble of drainage of inner basin, the prediction necessity of flood inundation area, flood risk analysis, and drawing flood risk maps have been on the rise, and the national flood risk maps have been produced. In this study, the quantitative flood vulnerability analysis was performed, which represents population living within flood-affected areas, types of economic activities, facilities affected by flood, in order to extend flood risk mapping from simple hazard concept into risk based idea. By applying it to Nakdong River basin, the flood vulnerability indices were estimated to draw flood risk maps subdivided into administrative districts. The result of this study can be applied to establish the disaster prevention measures and priority decision of disaster prevention project.

• Magazine of the Korea Concrete Institute
• /
• v.7 no.3
• /
• pp.187-198
• /
• 1995

This paper develops practical and reallstic reliabllity models and methods for the evaluation of system rehability and system rellabllity based ratlng of R.C box glrder bridge superstructures. The precise prediction of reberved carrying capacity of bridge as d system is extremely difficult especially when the brldges are highly redundant and slgnlficantly deter 1or;itcd or dainagetl. Thls papel proposes a nt2w approach for the evaluation of reseived system c,drrying capaaty of br~dges in terms ot equ~vdleiit system strength, which may b~ ddcflned as a brtdge system strength correipcmdlng tu the system rehability of the bridge. This cm be ticrAvcd from an Inverse process bami or1 the con~ept of FOSM(F1rst Order Second Moment) form of system reliabihty index. The sf rength llmt state models for K C box girder br~dges suggested In the paper dre based on the basi~ bending and shear strength And thc system reliatxllty pro,~lerri of box gritier super structure 1s formuldted as parallel serles models obtalncd f ~ o m thc FMA(Fdilure blode Rp proath) based on major failure mc>clmusrns or c~itlcal fdure ,>tatcs of each nuder .WOSM(Ad-vanced First Order Second Moment) and IST(1mportance Sampling Technique) simulation algorithm are used for the reliability analysis of the proposed models.