• Journal of The Korean Society of Clinical Toxicology
• /
• v.21 no.2
• /
• pp.128-134
• /
• 2023

Purpose: The Prescott nomogram has been utilized to forecast hepatotoxicity from acute acetaminophen poisoning. In developing countries, emergency medical centers lack the resources to report acetaminophen concentrations; thus, the commencement and cessation of treatment are based on the reported dose. This study investigated risk factors that can predict acetaminophen detection after 15 hours for safe treatment termination. Methods: Data were collected from an urban emergency medical center from 2010 to 2020. The study included patients ≥14 years of age with acute acetaminophen poisoning within 15 hours. The correlation between risk factors and detection of acetaminophen 15 hours after ingestion was evaluated using logistic regression, and the area under the curve (AUC) was calculated. Results: In total, 181 patients were included in the primary analysis; the median dose was 150.9 mg/kg and 35 patients (19.3%) had acetaminophen detected 15 hours after ingestion. The dose per weight and the time to visit were significant predictors for acetaminophen detection after 15 hours (odds ratio, 1.020 and 1.030, respectively). The AUCs were 0.628 for a 135 mg/kg cut-off value and 0.658 for a cut-off 450 minutes, and that of the combined model was 0.714 (sensitivity: 45.7%, specificity: 91.8%). Conclusion: Where acetaminophen concentrations are not reported during treatment following the UK guidelines, it is safe to start N-acetylcysteine immediately for patients who are ≥14 years old, visit within 15 hours after acute poisoning, and report having ingested ≥135 mg/kg. Additional N-acetylcysteine doses should be considered for patients visiting after 8 hours.

• 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.

• Journal of the Daesoon Academy of Sciences
• /
• v.42
• /
• pp.109-141
• /
• 2022

As many perhaps already know, in East Asian thought there are two aspects of all things such as light and darkness coexist and are called Yin-Yang (陰陽). The initial concept of Yin-Yang was just a simple expression meant to depict natural phenomena, but it gradually became the central concept in explanations of creation and the changes that undergo all things in the universe. The study of the ordering principle of nature that was known as Myeongli (命理) also examined the interrelation between the sky and the earth and divided the two into Ten Celestial Stems (天干 cheongan) and the Twelve Earth Branches (地支 jiji) based on Yin-Yang theory. This thesis analyzed contents of the relationship between Ten Celestial Stems and the Twelve Earth Branches in terms of the patterns of Mutual Aid (相助 sangjo) and Mutual Contention (相剋 sanggeuk) through a literature review and exploration of their common features and differences. Different categorized phenomena under the pattern of Mutual Aid include Tonggeun (通根 root downward) and Tugan (透干 appearance of the upward). Tonggeun means that signs in the Celestial Stems took root in their counterparts of the Earthly Branches. In the Celestial Stems, there is also Tonggeuncheo (通根處 a place to root downward) which in relation to the Earthly Branches show that the same five phases become Samhap (三合 combined three ways to gain power) and Banghap (方合 gathering in the same season). The methods of seeing Tonggeunryeok (通根力 power of a downward root) are as follows: First, it is seen by the places where Tonggeun takes hold. Ilgan (日干 the Celestial Stem of a birthday) is ordered as month (月 wol) > day (日 il) > hour (時 shi) > year (年 nyeon), and other Celestial Stems appear ordered as month > sitting > close place. Second, it can be seen by the characteristics of Earthly Branches that Tonggeun has taken hold. The Earthly Branches are ordered as Rokwangji (祿旺支 vigorous land) and Jangsaengji (長生支 newborn land) > Yeogi (餘氣 remaining energy) > Myogo (墓庫 storage and burial grounds). Tugan is the concept that the main agent was changed to Tonggeun, which means that the spirit of the Earthly Branches is manifested in the Celestial Stems. And the five phases hidden in the Earthly Branches will be able to play their roles as they are revealed. There are also the phenomena of Gaedu (蓋頭 the heavenly destroying the earthly) and Jeolgak (截脚 the earthly destroying the heavenly) which are concepts that convey that the Heavenly Stems and Earthly Branches can mutually destroy one another. There are different opinions on Gaedu because some adopt viewpoints of just focusing on the Celestial Stems and considering it only in terms the Celestial Stems destroying the Earthly Branches. But, the vast majority of scholars think that the Celestial Stems weakens the role of the roots by destroying the Earthly Branches. Jeolgak, the reverse concept of Gaedu, weakens the spirit of the Celestial Stems as the Earthly Branches destroy them, and this is associated with the strong possibility that one is fated to experience disharmony.

• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1239-1249
• /
• 2013

According to development of weather radar, researches about observation, analysis or forecast of weather phenomena such as tornado, flash-flood etc. were encouraged by reducing frequency interferences, transmission noises, attenuations of radar signal. In contrast, there is a growing interest in the visualization and expression methods for weather radar data but weather radar manufacturers or the organs of government for weather are just busy interpreting expressed weather images projected on GIS. We propose an effective high definition weather radar information visualization method able to apply various GIS platforms to observe and take actions against rapid local weather changes effectively. In this paper, first we change information acquired from weather radar to raster or vector type high definition data structures using specific algorithms. And then, we quadrate our processed raster/vector type weather data with various GIS platforms accurately to make observers can recognize and check weather situations over exact geographical positions and elevations intuitively. Experimental results verify that our method make observers can recognize and analyze weather changes, tornados, local downpours or flash floods accurately by analyzing high definition weather radar data combined with GIS platform including detailed target locations and elevations.

• Journal of the Korean earth science society
• /
• v.30 no.3
• /
• pp.294-304
• /
• 2009

A statistical prediction model for the typhoon intensity and track in the Northwestern Pacific area was developed based on the artificial neural network scheme. Specifically, this model is focused on the 5-day prediction after tropical cyclone genesis, and used the CLIPPER parameters (genesis location, intensity, and date), dynamic parameters (vertical wind shear between 200 and 850hPa, upper-level divergence, and lower-level relative vorticity), and thermal parameters (upper-level equivalent potential temperature, ENSO, 200-hPa air temperature, mid-level relative humidity). Based on the characteristics of predictors, a total of seven artificial neural network models were developed. The best one was the case that combined the CLIPPER parameters and thermal parameters. This case showed higher predictability during the summer season than the winter season, and the forecast error also depended on the location: The intensity error rate increases when the genesis location moves to Southeastern area and the track error increases when it moves to Northwestern area. Comparing the predictability with the multiple linear regression model, the artificial neural network model showed better performance.

• Korean System Dynamics Review
• /
• v.2 no.2
• /
• pp.25-40
• /
• 2001

This paper describes the forecast of power plant construction in a competitive korean electricity market. In Korea, KEPCO (Korea Electric Power Corporation, fully controlled by government) was responsible for from the production of the electricity to the sale of electricity to customer. However, the generation part is separated from KEPCO and six generation companies were established for whole sale competition from April 1st, 2001. The generation companies consist of five fossil power companies and one nuclear power company in Korea at present time. Fossil power companies are scheduled to be sold to private companies including foreign investors. Nuclear power company is owned and controlled by government. The competition in generation market will start from 2003. ISO (Independence System Operator will purchase the electricity from the power exchange market. The market price is determined by the SMP(System Marginal Price) which is decided by the balance between demand and supply of electricity in power exchange market. Under this uncertain circumstance, the energy policy planners such as government are interested to the construction of the power plant in the future. These interests are accelerated due to the recent shortage of electricity supply in California. In the competitive market, investors are no longer interested in the investment for the capital intensive, long lead time generating technologies such as nuclear and coal plants. Large unclear and coal plants were no longer the top choices. Instead, investors in the competitive market are interested in smaller, more efficient, cheaper, cleaner technologies such as CCGT(Combined Cycle Gas Turbine). Electricity is treated as commodity in the competitive market. The investors behavior in the commodity market shows that the new investment decision is made when the market price exceeds the sum of capital cost and variable cost of the new facility and the existing facility utilization depends on the marginal cost of the facility. This investors behavior can be applied to the new investments for the power plant. Under these postulations, there is the potential for power plant construction to appear in waves causing alternating periods of over and under supply of electricity like commodity production or real estate production. A computer model was developed to sturdy the possibility that construction will appear in waves of boom and bust in Korean electricity market. This model was constructed using System Dynamics method pioneered by Forrester(MIT, 1961) and explained in recent text by Sternman (Business Dynamics, MIT, 2000) and the recent work by Andrew Ford(Energy Policy, 1999). This model was designed based on the Energy Policy results(Ford, 1999) with parameters for loads and resources in Korea. This Korea Market Model was developed and tested in a small scale project to demonstrate the usefulness of the System Dynamics approach. Korea electricity market is isolated and not allowed to import electricity from outsides. In this model, the base load such as unclear and large coal power plant are assumed to be user specified investment and only CCGT is selected for new investment by investors in the market. This model may be used to learn if government investment in new unclear plants could compensate for the unstable actions of private developers. This model can be used to test the policy focused on the role of unclear investments over time. This model also can be used to test whether the future power plant construction can meet the government targets for the mix of generating resources and to test whether to maintain stable price in the spot market.

• Journal of Korea Water Resources Association
• /
• v.31 no.6
• /
• pp.821-832
• /
• 1998

This study investigates the prediction of daily water supply, which is a necessary for the efficient management of water distribution system. Fuzzy neuron, namely artificial intelligence, is a neural network into which fuzzy information is inputted and then processed. In this study, daily water supply was predicted through an adaptive learning method by which a membership function and fuzzy rules were adapted for daily water supply prediction. This study was investigated methods for predicting water supply based on data about the amount of water supplied to the city of Kwangju. For variables choice, four analyses of input data were conducted: correlation analysis, autocorrelation analysis, partial autocorrelation analysis, and cross-correlation analysis. Input variables were (a) the amount of water supplied (b) the mean temperature, and (c)the population of the area supplied with water. Variables were combined in an integrated model. Data of the amount of daily water supply only was modelled and its validity was verified in the case that the meteorological office of weather forecast is not always reliable. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 18.35% and the average error was lower than 2.36%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.

• Korean Journal of Remote Sensing
• /
• v.12 no.2
• /
• pp.126-138
• /
• 1996

The characteristics of rapid development of the low pressure system over the East Sea from 06 to 08 Nov., 1995 has been analyzed in detail by the synoptic numerical products and satellite observations. The Low system was initially triggered the development of the baroclinic leaf cloud over the border of the northern part of Korea and China and moved eastward and then developed explosively com-ma or lambda type cloud system over the East Sea. To forecast well the general development and movement of the coastal winter cyclone over the East Sea popularly in a numerical simulation by several scientists, the large baroclinicity, continuous support of water vapor, and sequential cold outbreak over the warm sea surface have been more commonly concerned about. The cyclone which the central surface pressure was dropped 40hPa within 24 hours has often accompanied strong wind and heavy snow- or rain-fall in the winter season. In all successive observations with 12-hourly satellite imagery and analyzed meteorological variables in this period, the centers of the sea-level pressure and 500hPa geopotential height associated with this cyclone were typically illustrated by moving farther eastward using GMS combined enhanced IR images. The maxi-mum wind sustained by this system with the intensity and central pressure of tropical storm was about 60 knots with the center pressure drop of 44hPa/day similar to the North American cyclonic bomb and Atlantic storm.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.

• KDI Journal of Economic Policy
• /
• v.14 no.1
• /
• pp.147-165
• /
• 1992

This paper analyzes the macroeconomic effects of elections on the Korean economy and their future ramifications. It measures the shocks to the Korean economy caused by elections by taking the average of sample forecast errors from four major elections held in the 1980s. The seven variables' Bayesian Vector Autoregression Model which includes the Monetary Base, Industrial Production, Consumption, Consumer Price, Exports, and Investment is based on the quarterly time series data starting from 1970 and is updated every quarter before forecasts are made for the next quarter. Because of this updating of coefficients, which reflects in part the rapid structural changes of the Korean economy, this study can capture the shock effect of elections, which is not possible when using election dummies with a fixed coefficient model. In past elections, especially the elections held in the 1980s, $M_2$ did not show any particular movement, but the currency and base money increased during the quarter of the election was held and the increment was partly recalled in the next quarter. The liquidity of interest rates as measured by corporate bond yields fell during the quarter the election and then rose in the following quarter, which is somewhat contrary to the general concern that interest rates will increase during election periods. Manufacturing employment fell in the quarter of the election because workers turned into campaigners. This decline in employment combined with voting holiday produce a sizeable decline in industrial production during the quarter in which elections are held, but production catches up in the next quarter and sometimes more than offsets the disruption caused during the election quarter. The major shocks to price occur in the previous quarter, reflecting the expectational effect and the relaxation of government price control before the election when we simulate the impulse responses of the VAR model, imposing the same shocks that was measured in the past elections for each election to be held in 1992 and assuming that the elections in 1992 will affect the economy in the same manner as in the 1980s elections, 1992 is expected to see a sizeable increase in monetary base due to election and prices increase pressure will be amplified substantially. On the other hand, the consumption increase due to election is expected to be relatively small and the production will not decrease. Despite increased liquidity, a large portion of liquidity in circulation being used as election funds will distort the flow of funds and aggravate the fund shortage causing investments in plant and equipment and construction activities to stagnate. These effects will be greatly amplified if elections for the head of local government are going to be held this year. If mayoral and gubernatorial elections are held after National Assembly elections, their effect on prices and investment will be approximately double what they normally will have been have only congressional and presidential elections been held. Even when mayoral and gubernatorial elections are held at the same time as congressional elections, the elections of local government heads are shown to add substantial effects to the economy for the year. The above results are based on the assumption that this year's elections will shock the economy in the same manner as in past elections. However, elections in consecutive quarters do not give the economy a chance to pause and recuperate from past elections. This year's elections may have greater effects on prices and production than shown in the model's simulations because campaigners' return to industry may be delayed. Therefore, we may not see a rapid recall of money after elections. In view of the surge in the monetary base and price escalation in the periods before and after elections, economic management in 1992 should place its first priority on controlling the monetary aggregate, in particular, stabilizing the growth of the monetary base.