• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.785-794
• /
• 2002

Automatic stock trading systems should be able to solve various kinds of optimization problems such as market trend prediction, stock selection, and trading strategies, in a unified framework. But most of the previous trading systems based on supervised learning have a limit in the ultimate performance, because they are not mainly concerned in the integration of those subproblems. This paper proposes a stock trading system, called R-Trader, based on reinforcement teaming, regarding the process of stock price changes as Markov decision process (MDP). Reinforcement learning is suitable for Joint optimization of predictions and trading strategies. R-Trader adopts two popular reinforcement learning algorithms, temporal-difference (TD) and Q, for selecting stocks and optimizing other trading parameters respectively. Technical analysis is also adopted to devise the input features of the system and value functions are approximated by feedforward neural networks. Experimental results on the Korea stock market show that the proposed system outperforms the market average and also a simple trading system trained by supervised learning both in profit and risk management.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2396-2402
• /
• 2015

Air compressor, as an essential equipment used in the factory and plant operations, accounts for around 30% of the total electricity consumption in U.S.A, thereby being proposed advanced technologies to reduce electricity consumption. When the fluctuation of the compressed airflow rate is small, the system stability is increased followed by the reduction of the electricity consumption which results in the efficient design of the energy system. In the statistical analysis, the normal distribution, log normal distribution, gamma distribution or the like are generally used to identify system characteristics. However a single distribution may not fit well the data with long tail, representing sudden air flow rate especially in extremes. In this paper, authors decouple the compressed airflow rate into two parts to present a mixture of distribution function and suggest a method to reduce the electricity consumption. This reduction stems from the fact that a general pareto distribution estimates more accurate quantile value than a gaussian distribution when an airflow rate exceeds over a large number.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.247-247
• /
• 2011

도시유역에서의 일반적인 우수관거 설계 및 기존의 연구들은 수리학적 조건을 만족시키는 범위 내에서 최소의 비용을 위한 관거 설계에 초점을 맞추어왔다. 그러나 최적의 우수관거 설계는 우수관거의 근본적 목적인 내수배제를 최대화 하고자 하는 것이며, 이것은 관망 구성에 따른 시스템 내 유입 수문곡선들 간의 중첩효과를 제어함으로써 가능하다. 본 연구에서는 관내 흐름의 변화를 관망의구성에 따라서 제어될 수 있는 목적함수로서 다루고 있는 이정호(2010)의 우수관망 최적설계 모형에 대하여 각기 다른 유역 특성을 나타내는 실제 도시유역에서의 적용성을 검토하였다. 본 연구에서 이용한 최적 우수관망 노선 결정 모형은 이정호(2010)가 개발한 모형으로 도시유역에서의 우수관망의 노선 결정을 유출구 첨두유출량 최소화를 목적으로 최적화기법을 이용한 모형이다. 이정호(2010)는 개발된 모형을 통하여 관망 노선을 결정한 결과 설계빈도를 초과하는 강우에 대해서 내수침수 발생이 저감되는 효과를 가져올 수 있음을 분석하였다. 본 연구에서는 이러한 이정호(2010)의 모형에 대한 적용성을 검증하기 위하여 각기 다른 유역 특성을 갖는 실제 도시유역들에 대하여 해당 모형을 적용하였다. 이때 유역의 특성은 지표유출 및 첨두유출량에 지배적인 영향을 미치는 유역의 지표 경사에 대하여 고려되었다. 적용된 도시유역은 총 3개 배수분구로서 평균 지표 경사는 0.008, 0.006, 0.002로 각기 높은 경사, 보통 경사 및 완만한 경사 지대를 염두에 둔 유역 선정에 해당한다. 이에 따라 각 유역에 대하여 우수관망 노선을 최적화한 결과 설계빈도의 강우지속기간 30분 강우에 대하여 현재의 관망 대비 최적화된 관망에서의 첨두유출량 저감 비율은 지표경사 0.008인 유역에서는 약 7%, 지표경사 0.006인 유역에서는 약 17%, 지표경사 약 0.002인 유역에서는 약 8%로 나타났다. 따라서 본 연구결과 유역의 경사 특성에 따른 최적 우수관망을 통한 첨두유출량의 저감 비율간에는 상관관계를 정의할 수 없으며, 단지 우수관망에서의 노선 변경이 가능한 맨홀 지점이 어떤 중요한 지점에 얼마나 위치하느냐에 따라 달라지게 되는 것으로 분석되었다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.4
• /
• pp.1211-1216
• /
• 2000

Asynchronous transfer mode (ATM) can be efficiently used to transport packet data services. The switching system will support voice and packet data services simultaneously from end to end applications. To guarantee quality of service (QoS) of the offered services, source rateot send packet data is needed to control the network overload condition. Most existing control algorithms are shown to provide the threshold-based feedback control technique. However, real-time voice calls can be dynamically connected and released during data services in the network. If the feedback control information delays, quality of the serviced voice can be degraded due to a time delay between source and destination in the high speed link. An adaptive algorithm based on the optimal least mean square error technique is presented for the predictive feedback control technique. The algorithm attempts to predict a future buffer size from weight (slope) adaptation of unknown functions, which are used fro feedback control. Simulation results are presented, which show the effectiveness of the algorithm.

• Journal of Internet Computing and Services
• /
• v.3 no.3
• /
• pp.67-74
• /
• 2002

Asynchronous transfer mode (ATM) can be efficiently used to transport packet data services. The switching system will support voice and packet data services simultaneously from end to end applications. To guarantee quality of service (QoS) of the offered services, source rate to send packet data is needed to control the network overload condition. Most existing control algorithms are shown to provide the threshold-based feedback control technique. However, real-time voice calls can be dynamically connected and released during data services in the network. If the feedback control information delays, quality of the serviced voice can be degraded due to a time delay between source and destination in the high speed link, An adaptive algorithm based on the optimal least mean square error technique is presented for the predictive feedback control technique. The algorithm attempts to predict a future buffer size from weight (slope) adaptation of unknown functions, which are used for feedback control. Simulation results are presented, which show the effectiveness of the algorithm.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2010.02a
• /
• pp.297-297
• /
• 2010

KSTAR 토카막의 두번째 실험 캠페인 동안 고속파 전자가열 (FWEH)을 위한 ICRF 고주파입사 실험을 실시하였다. 토로이달 자기장은 2 T, 플라즈마 전류는 200-300 kA, 주반경은 1.8 m, 부반경은 0.5 m의 원형 플라즈마가 가열 대상이 되었으며, 네개의 ICRF 안테나 전류띠 가운데 중심부의 두개의 전류띠를 최대 300 kW로 구동하기 위한 운전 주파수는 44.2 MHz가 선택 되었다. 이 주파수는 플라즈마의 모든 영역에서 이온 사이클로트론 공명을 일으키지 않으므로 플라즈마에 흡수되는 대부분의 출력은 전자에게 전달될 것으로 기대되었다. 낮은 고주파-플라즈마 결합으로 인하여 전송선의 최대 고주파 전압이 허용치를 초과하기 때문에 비교적 낮은 최대 출력만이 허용 되었으나, ECE에 의해 관측된 전자의 온도는 국지적으로 최대 150 % 까지 증가하는 것을 확인 할 수 있었다. 낮은 고주파-플라즈마 결합의 첫번째 원인은 FWEH의 효율이 이온을 가열할 때 보다 상대적으로 낮기 때문이다. 플라즈마 내에 이온 사이클로트론 공명층이 형성되면 높은 효율로 고주파를 입사 할 수 있다는 것은 잘 알려진 사실이다. 또다른 원인은 D 형상의 플라즈마에 맞도록 만들어진 안테나와, 원형 플라즈마간의 부조화로 인하여 고속파 차단층이 (Fast Wave Cutt-off Layer) 평균적으로 넓게 형성되기 때문이다. 플라즈마 외곽에 반드시 존재하는 낮은 플라즈마 밀도의 고속파 차단층 내부에서, 중심부로 향하는 고주파의 진폭은 지수함수로 감쇠하므로 가능하면 플라즈마 밀도를 높여 차단층 자체의 폭을 줄이거나, 안테나 전류띠를 플라즈마에 바짝 접근시켜야만 한다. 고주파 진단 장치로는 송출기의 출력과 반사파 측정 장치, 공명루프의 전압 측정 장치가 있는데, 이것들을 이용하여 안테나에 전달되는 출력 및 고주파-플라즈마 결합 효율을 나타내는 플라즈마에 대한 고주파 부하 저항을 구할 수 있다. 측정 결과, 부하 저항의 최소값은 진공시 또는 ICRF만의 방전시의 값 0.25 Ohm 보다 큰 0.5 Ohm을 나타냈으며, 최대값은 플라즈마의 상태에 따라 1 Ohm에서 2 Ohm 사이에서 매우 빠르게 요동하는 것을 확인했다. Mm 파 반사계의 측정에 의하면 플라즈마 언저리의 위치가 약 3 cm 정도의 크기로 요동하는 것으로 나타났는데, 부하 저항과 언저리 위치의 파형이 정확하게 일치하지 않지만 유사한 경향성을 가진 것으로 보인다. 따라서 플라즈마 언저리 위치의 제어를 통하여 가열 효율을 높게 유지할 수 있음을 알 수 있다. 본 발표에서는 실험의 소개와 함께 부하 저항의 관점에서 가열 효율을 높일 방안을 토론하도록 한다.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.8 no.1
• /
• pp.109-120
• /
• 2000

In the analysis of the common categories, moisture contents and organic concentrations were not much different according to the types of industry or treatment facilities. When heavy metals contribution of the sludge from domestic and industrial wastewater treatment facilities was analyzed, As, Hg and Cr concentrations were relatively high among 42 standards of the fertilizer law. As concentration war higher in 28 of 42 facilities (67%) than limits of the fertilizer law. Hg concentration was not acceptable in the 21 of 42 facilities (50%). Cr concentration was not acceptable in 9 of 42 facilities (21%). From these results, It is found that As is the most frequently detectable component and contaminant than any other heavy metals in sludges. The data from this experiment was also compared with the guidelines of harmful organics and the rest of heavy metals that are regulated by some of the foreign countries. Be, Se and Mo concentrations were lower than the limits. Among the organics, the average concentration of PCB (10 samples) was 26.2 ppb. The highest concentration was 162.6 ppb in the sludge of the municipal wastewater treatment facilities and the lowest concentration was 2.14 ppb from the skin manufacturing industry. From the leaching analysis of re-manufacturing goods from the sludge, most of them was acceptable on the regulation law but Cr concentration was over the limit.

• Journal of Nutrition and Health
• /
• v.46 no.1
• /
• pp.50-60
• /
• 2013

The aims of this study were to estimate daily intake of macrominerals from beverages, liquid teas, and liquid coffees and to evaluate their potential health risks for Korean children and adolescents (1-to 19 years old). Assessment of dietary intake was conducted using the actual level of sodium, calcium, phosphorus, potassium, and magnesium in non-alcoholic beverages and (207 beverages, 19 liquid teas, and 24 liquid coffees) the food consumption amount drawn from "The Fourth Korea National Health and Nutrition Examination Survey (2007-2009)". To estimate the dietary intake of non-alcoholic beverages, 6,082 children and adolescents (Scenario I) were compared with 1,704 non-alcoholic beverage consumption subjects among them (Scenario II). Calculation of the estimated daily intake of macrominerals was based on point estimates and probabilistic estimates. The values of probabilistic macromineral intake, which is a Monte-Carlo approach considering probabilistic density functions of variables, were presented using the probabilistic model. The level of safety for macrominerals was evaluated by comparison with population nutrient intake goal (Goal, 2.0 g/day) for sodium, tolerable upper intake level (UL) for calcium (2,500 mg/day) and phosphorus (3,000-3,500 mg/day) set by the Korean Nutrition Society (Dietary Reference Intakes for Koreans, KDRI). For total children and adolescents (Scenario I), mean daily intake of sodium, calcium, phosphorus, potassium, and magnesium estimated by probabilistic estimates using Monte Carlo simulation was, respectively, 7.93, 10.92, 6.73, 23.41, and 1.11, and 95th percentile daily intake of those was, respectively, 28.02, 44.86, 27.43, 98.14, and 3.87 mg/day. For consumers-only (Scenario II), mean daily intake of sodium, calcium, phosphorus, potassium, and magnesium estimated by probabilistic estimates using Monte Carlo simulation was, respectively, 19.10, 25.77, 15.83, 56.56, and 2.86 mg/day, and 95th percentile daily intake of those was, respectively, 62.67, 101.95, 62.09, 227.92, and 8.67 mg/day. For Scenarios I II, sodium, calcium, and phosphorus did not have a mean an 95th percentile intake that met or exceeded the 5% of Goal and UL.

• The Korean Journal of Financial Management
• /
• v.22 no.1
• /
• pp.119-146
• /
• 2005

This study applies extreme value theory to get extreme value-VAR for Korean Stock market and showed the usefulness of the approach. Block maxima model and POT model were used as extreme value models and tested which model was more appropriate through back testing. It was shown that the block maxima model was unstable as the variation of the estimate was very large depending on the confidence level and the magnitude of the estimates depended largely on the block size. This shows that block maxima model was not appropriate for Korean Stock market. On the other hand POT model was relatively stable even though extreme value VAR depended on the selection of the critical value. Back test also showed VAR showed a better result than delta VAR above 97.5% confidence level. POT model performs better the higher the confidence level, which suggests that POT model is useful as a risk management tool especially for VAR estimates with a confidence level higher than 99%. This study picks up the right tail and left tail of the return distribution and estimates the EVT-VAR for each, which reflects the asymmetry of the return distribution of the Korean Stock market.

• Journal of Food Hygiene and Safety
• /
• v.25 no.4
• /
• pp.367-375
• /
• 2010

The bacteriological and physiochemical analysis of sea water and sediments in Tongyeong harbor was conducted to evaluate sanitary conditions. The samples were collected at 8 stations established once a month from June, 2008 to May, 2009. During the study period, the range of temperature was from 6.7 to $25.2^{\circ}C$, transparency ranged from 1.2 to 2.6 m, chemical oxygen demand ranged from 1.90 to 2.92 mg/L, dissolved oxygen ranged from 6.2 to 10.5 mg/L, dissolved nitrogen ranged from 0.052 to 0.098 mg/L, phosphate ranged from 0.044 to 0.065 mg/L, respectively. Seafood, if eaten raw, carries the risk of food poisoning. Seafood poisoning is often cause by pathogenic microorganism originating from fecal contamination, such as Salmonella sp., Shigella sp. and norovirus. Fecal coliforms are an important indicator of fecal contamination. Therefore, data on fecal coliform are very important for evaluating the safety of fisheries in coastal areas. So, we investigated the sanitary indicate bacteria. The coliform group and fecal coliform MPN's of sea water in Tongyeong harbor were ranged from < 1.8~22,000/100 mL (GM 164.9 MPN/100 mL) and < 1.8~7,900 MPN/100 mL (GM 33.7 MPN/100 mL), respectively. Total coliform were detected 97.0% in 96 of samples and 68.9% of total coliforms were fecal coliforms. These results similar to another seawater detection ratio of total coloforms and fecal coliforms. The Vibrios was isolated and identified with VITEK system. Four hundred eighty strains that were obtained from sea water samples in Tongyeong harbor Detection ratio Vibrio alginolyticus, 34.2%, Vibrio parahaemolyticus, 13.8%, Vibrio vulnificus 10.0%, and V. mimicus 12.5% respectively. Vibrio cholerae O1, was not detected. During the study period, the ranges of water content, ignition loss, COD, and acid volatile sulfates in sediments in Tongyeoung harbor were 41.0~57.4%, 7.8~10.5%, 6.51~9.30 mg/g, 0.04~0.09 mg/g, respectively. Heavy metals in sediment of Tongyeoung harbor were Cd, $0.10{\pm}0.05$; Cu, $4.79{\pm}8.20$; As, $1.95{\pm}0.17$; Hg, $0.10{\pm}0.07$; $Cr^{6+}$, $0.34{\pm}0.12$; Zn, $125.33{\pm}16.40$; Ni, $16.43{\pm}1.93$ mg/kg.