• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.59-71
• /
• 2014

System trading is becoming more popular among Korean traders recently. System traders use automatic order systems based on the system generated buy and sell signals. These signals are generated from the predetermined entry and exit rules that were coded by system traders. Most researches on system trading have focused on designing profitable entry and exit rules using technical indicators. However, market conditions, strategy characteristics, and money management also have influences on the profitability of the system trading. Unexpected price deviations from the predetermined trading rules can incur large losses to system traders. Therefore, most professional traders use strategy portfolios rather than only one strategy. Building a good strategy portfolio is important because trading performance depends on strategy portfolios. Despite of the importance of designing strategy portfolio, rule of thumb methods have been used to select trading strategies. In this study, we propose a SVM-based strategy portfolio management system. SVM were introduced by Vapnik and is known to be effective for data mining area. It can build good portfolios within a very short period of time. Since SVM minimizes structural risks, it is best suitable for the futures trading market in which prices do not move exactly the same as the past. Our system trading strategies include moving-average cross system, MACD cross system, trend-following system, buy dips and sell rallies system, DMI system, Keltner channel system, Bollinger Bands system, and Fibonacci system. These strategies are well known and frequently being used by many professional traders. We program these strategies for generating automated system signals for entry and exit. We propose SVM-based strategies selection system and portfolio construction and order routing system. Strategies selection system is a portfolio training system. It generates training data and makes SVM model using optimal portfolio. We make $m{\times}n$ data matrix by dividing KOSPI 200 index futures data with a same period. Optimal strategy portfolio is derived from analyzing each strategy performance. SVM model is generated based on this data and optimal strategy portfolio. We use 80% of the data for training and the remaining 20% is used for testing the strategy. For training, we select two strategies which show the highest profit in the next day. Selection method 1 selects two strategies and method 2 selects maximum two strategies which show profit more than 0.1 point. We use one-against-all method which has fast processing time. We analyse the daily data of KOSPI 200 index futures contracts from January 1990 to November 2011. Price change rates for 50 days are used as SVM input data. The training period is from January 1990 to March 2007 and the test period is from March 2007 to November 2011. We suggest three benchmark strategies portfolio. BM1 holds two contracts of KOSPI 200 index futures for testing period. BM2 is constructed as two strategies which show the largest cumulative profit during 30 days before testing starts. BM3 has two strategies which show best profits during testing period. Trading cost include brokerage commission cost and slippage cost. The proposed strategy portfolio management system shows profit more than double of the benchmark portfolios. BM1 shows 103.44 point profit, BM2 shows 488.61 point profit, and BM3 shows 502.41 point profit after deducting trading cost. The best benchmark is the portfolio of the two best profit strategies during the test period. The proposed system 1 shows 706.22 point profit and proposed system 2 shows 768.95 point profit after deducting trading cost. The equity curves for the entire period show stable pattern. With higher profit, this suggests a good trading direction for system traders. We can make more stable and more profitable portfolios if we add money management module to the system.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2017.05a
• /
• pp.165-165
• /
• 2017

지난 수 십 년 동안, 전 세계적으로 자원의 소비가 급격히 증가하게 되면서 최근 자원 고갈은 물론 환경오염이 커다란 이슈로 문제가 되고 있다. 이에 따라 재료 관련 분야에 있어서는 보다 효율적이고 친환경적인 방법으로 자원을 활용해야 된다는 필요성이 대두되었고 이와 같은 관점에서 목적하는 성분이 우수하고 환경 친화적인 표면처리 재료 개발연구가 활발하게 진행되고 있는 실정이다. 그 중 플라즈마 전해 산화(Plasma Electrolytic Oxidation, PEO)는 알루미늄, 마그네슘 등의 경금속의 경도를 향상시키고 높은 내마모성, 내식성을 갖게 하는 표면처리로써 그 관심이 증가하고 있다. 이 플라즈마 전해 산화는 일반적으로 공정비용 대비 효과적이고 환경 친화적이며 코팅 성능 면에서 우수하다고 알려져 있다. 이러한 고유한 특성으로 인해 플라즈마 전해 산화 코팅은 최근 몇 년 동안 기계, 자동차, 우주항공, 의학 및 전기 산업 등의 분야에서 그 적용이 점차 증가하고 있는 상황이다. 한편, 플라즈마 전해 산화 코팅을 하는 모재들의 경우 부동태 산화피막을 용이하게 형성할 수 있는 특성의 모재에 한정되고 있어서 그 응용확대에 한계가 있는 것이 사실이다. 따라서 본 연구에서는 플라즈마 전해 산화법을 사용하여 용융알루미늄도금 강판 상에 산화피막 형성을 시도하였다. 전원공급 장치의 양극은 전해질 속에 잠겨있는 작동전극에 연결하고 음극은 대전극 역할을 하는 스테인레스강 전해질 용기에 연결되었다. 전해질은 Sodium Aluminate 및 기타 첨가제를 함유한 것을 사용하였고 온도는 열교환기를 사용하여 $30^{\circ}C$ 이하로 유지되었다. 또한 여기서 전류밀도는 $5{\sim}10A/dm^2$, 실험 주파수는 700Hz, Duty cycle은 30 및 90%의 각 조건에서 공정처리 시간을 각각 30분 및 60분 동안 진행하였다. 이와 같은 조건에서 형성한 막들에 대해서는 주사형전자현미경(SEM)을 이용하여 코팅 막의 표면 및 단면의 모폴로지를 관찰하였음은 물론 EDS 및 XRD 측정을 통하여 원소조성분포 및 결정구조를 각각 분석하였다. 또한 이 코팅 막들에 대한 내식성은 5% 염수분무 환경 중 노출시험(Salt spray test), 3% NaCl 용액에서의 침지 시험 및 전기화학적 동전위 양극분극(Potentiodynamic Polarization) 시험을 진행하여 평가하였다. 이상의 실험결과에 의하면, 제작조건별 플라즈마 전해 산화 코팅 막의 모폴로지 및 결정구조가 상이하게 나타나는 것을 알 수 있었다. 코팅 막의 모폴로지 관찰 결과, 공정 시간에 비례하여 표면에 존재하는 원형 기공의 수는 감소하였으나 그 크기가 커지고 크레이터의 직경 또한 커진 것이 확인되었다. 이 기공은 마이크로 방전에 의해 형성된다고 알려져 있는데 공정 시간이 증가함에 따라 코팅 두께가 점차 증가하여 마이크로 방전의 빈도수가 줄어들고 그 강도는 증가하게 되어 기공 크기가 증가한 것으로 사료된다. 또한 공정시간이 긴 시편에서 표면에 크랙이 다수 존재하는 것으로 확인되었다. 이것은 방전에 의해 고온이 된 소재가 차가운 전해질과 만나게 되어 생긴 큰 온도구배로 인해 강한 열응력이 발생하여 균열을 초래한 것으로 보인다. 조성원소 분석 결과 원형 기공 주변의 크레이터 영역에는 알루미늄이 풍부하였으며 그 주변에 결절상을 갖는 구조에서는 전해질 성분의 원소가 포함되어 있는 것이 확인되었다. 이러한 코팅 막의 표면 특성은 내식성에 영향을 주게 된 원인으로 사료된다. 동전위 분극측정 결과에 의하면 플라즈마 전해 산화 공정 시간이 길어질수록 부식전류밀도가 증가하였다. 이것은 공정시간이 길어짐에 따라 강한 방전이 발생하여 기공의 크기가 증가하고 크랙이 발생하게 되면서 내식성이 저하된 것으로 판단된다. 종합적으로 재료특성 분석 및 내식성 평가를 분석한 결과, 플라즈마 전해 산화의 공정 시간이 너무 길게 되면 오히려 내식성은 저하되는 것이 확인되었다. 이상의 연구를 통하여 고내식 특성을 갖는 플라즈마 전해 산화 막의 유효성을 확인하였으며 용융알루미늄강판 상에 실시한 플라즈마 전해 산화 처리에 대한 기초적인 응용 지침을 제시할 수 있을 것으로 사료된다.

• Journal of Animal Science and Technology
• /
• v.46 no.4
• /
• pp.603-612
• /
• 2004

This study was carried out to investigate the replacing fish meal or soybean meal effect of with feather meal or Bacillus sp. inoculated feather meal in broiler diets on the performances and nutrient utilization. One hundred and eighty broilers were randomly allotted to six dietary treatments(1) control, basal diet; (2) BFMl00, Fish meal replacing at 100% level with bacillus sp. inoculated feather meal; (3) BSM20, Soybean meal replacing at 20% level with bacillus sp. inoculated feather meal; (4) BFMl00+BSM20, Fish meal and soybean meal replacing at 100% level and 20% level with bacillus sp. inoculated feather meal, respectively; (5) GFMl00, Fish meal replacing at 100% level with general feather meal; and (6) GSM20, Soybean meal replacing at 20% level with general feather meal) in a 5 week feeding trial. In overall period, body weight gain of control was the highest(1,623g) and those of BFM 100, BFM 100+ BSM 20 and GFM 100 were 1,572g, 1,564g, and 1,078g, respectively. And that of GFM 100(1,078.3g) was the lowest(p<0.05) among treatments. Digestibility of dry matter for BFM 100+BSM 20(81.46%) was higher(p<0.05) than that for other treatments, and that of crude protein was the lowest (p<0.05). Digestibilities of organic matter were significantly(p<0.05) improved when Bacillus sp. inoculated feather meal was replaced at 100% level with fish meal in the basal diet. Methane and hydrogen sulfide gases from the feces were significantly(p<0.05) decreased in chicks fed the control, BFM 100 and GFM 100 diets, when observed after 3 weeks of feeding trials. Feed costs of the control and BFM 100 were 417 and 384 won, respectively but that of BSM 20 was 558 won. Therefore, replacement of fish meal with Bacillus sp. inoculated feather meal in the diets for chicks could be useful for economic production.

• Journal of Bio-Environment Control
• /
• v.28 no.1
• /
• pp.46-54
• /
• 2019

Experiments of local cooling and heating on crown and root zone of forcing cultivation of strawberry 'Seolhyang' using heat pump and root pruning before planting were conducted. During the daytime, the crown surface temperature of the crown local cooling treatment was maintained at $18{\sim}22^{\circ}C$. This is suitable for flower differentiation, while those of control and root zone local cooling treatment were above $30^{\circ}C$. Budding rate of first flower clusters and initial yields were in the order of crown local cooling, root zone local cooling and control in root pruning plantlet and non pruning plantlet, except for purchase plantlet. Those of root pruning plantlet were higher than those of non pruning plantlet. These trends were evident in the yield of the first flower cluster until February 14, 2018, and the effect of local cooling and root pruning decreased from March 9, 2018. The budding rates of the second flower cluster according to the local cooling and root pruning treatments were not noticeable compared to first flower cluster but showed the same tendency as that of first flower cluster. In the heating experiment, root zone local heating(root zone $20^{\circ}C$+inside greenhouse $5^{\circ}C$) and crown local heating(crown $20^{\circ}C$+inside greenhouse $5^{\circ}C$) saved 59% and 65% of heating fuel, respectively, compared to control(inside greenhouse $9^{\circ}C$). Considering the electric power consumption according to the heat pump operation, the heating costs were reduced by 55% and 61%, respectively.

• Journal of Korean Society of Transportation
• /
• v.20 no.4
• /
• pp.83-93
• /
• 2002

To improve the performance of estimation, the research that uses additional information addition to traffic count and target OD with additional survey cost have been studied. The purpose of this paper is to improve the performance of OD estimation by reducing the feasible solutions with cost-efficiently additional information addition to traffic counts and target OD. For this purpose, we Propose the OD estimation method with sample link use proportion as additional information. That is, we obtain the relationship between OD trip and link flow from sample link use proportion that is high reliable information with roadside survey, not from the traffic assignment of target OD. Therefore, this paper proposes OD estimation algorithm in which the conservation of link flow rule under the path-based non-equilibrium traffic assignment concept. Numerical result with test network shows that it is possible to improve the performance of OD estimation where the precision of additional data is low, since sample link use Proportion represented the information showing the relationship between OD trip and link flow. And this method shows the robust performance of estimation where traffic count or OD trip be changed, since this method did not largely affected by the error of target OD and the one of traffic count. In addition to, we also propose that we must set the level of data precision by considering the level of other information precision, because "precision problem between information" is generated when we use additional information like sample link use proportion etc. And we Propose that the method using traffic count as basic information must obtain the link flow to certain level in order to high the applicability of additional information. Finally, we propose that additional information on link have a optimal counting location problem. Expecially by Precision of information side it is possible that optimal survey location problem of sample link use proportion have a much impact on the performance of OD estimation rather than optimal counting location problem of link flow.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.7 no.1
• /
• pp.63-69
• /
• 1987

This field experiment was undertaken to assess the effectiveness of magnesium- and boronenriched complex fertilizer ($N-P_2O_5-K_2O-MgO-B_2O_3$ : 8-25-7-3-0.2) compared with some straight fertilizers on the hilly pasture establishment. This second part was concerned with the changes in the forage yields, yield components, botanical and chemical compositions in a mixed grassclover sward (orchardgrass, tall fescue, Kentucky bluegrass, and ladino clover). The results from a two-year experiment are summarized as follows: 1. Dry matter yields of whole mixed forages were significantly reduced in control by 54.5% and the NK-plot ($P_o$ by 35.0%, compared with the normal NPK-plots. 2. The yields of oversown grasses were significantly reduced in control by 79.7% and the NKplot ($P_o$) by 52.196, compared with the normal NPK applications. At the normal NPK applications, the oversown grasses were lowest in the yields when provided with double superphosphate with no significant differences. The yields of weeds were not significantly influenced by the treatments. 3. The significant differences in the legume yields (relative yield, %) were laid in the follow. ing increasing order; complex fertilizer (178.5%) > NPK-fused superphosphate (139.5%) > NPK-double superphosphate (100.0%) = control > NK (51.1%). The legume yield was much more depressed in the NK-plot ($P_o$) than in control ($N_oP_oK_o$). 4. The rate of oversown grasses and whole forages were increased by the normal NPK applications, showing little difference among the kinds of fertilizers. It was recognized that the application of complex fertilizer contributed to the increasing of legume rate in the mixed sward. This contribution turned out to be due to the rather enhanced performance and yield-increase of legume, compared with the straight fertilizers. 5. With the NK-treatment ($P_o$) the P concentration in mixed forages dropped below the critical level (0.2%). The Mg concentrations in mixed forages were lower in all the plots than the critical level (0.2%). Therefore, a sufficient amount of Mg was desirably to be applied It is recommended that, in relation to its effectiveness and simplification of fertilizer application, the application of this complex fertilizer for pasture establishment be carried out. The change of the constituent ratio of complex fertilizer to the standard of "8 - 15-20 - 7 - 5-10 - 0.2" considering the need of sufficient Mg supply and the continuous accumulation of P in the top-surface soil is possibly recommended.commended.

• Journal of Animal Environmental Science
• /
• v.17 no.1
• /
• pp.39-48
• /
• 2011

The present survey was conducted to provide basic information on automatic milking system (AMS) in relation to purchase motive, milk yield and quality, customer satisfaction, difficulties of operation and customer suggestions, etc. Purchase motives of AMS were insufficient labor (44%), planning of dairy experience farm (25%), better performance of high yield cows (19%) and others (6%), respectively. Average cow performance after using AMS was 30.9l/d for milk yield, 3.9% for milk fat, 9,100/ml for bacterial counts. Sixty-eight percentage of respondents were very positive in response to AMS use for their successors but 18% were negative. The AMS operators were owner (44%), successor (44%), wife (6%) and company worker (6%), respectively. The most difficulty (31%) in using AMS was operating the system and complicated program manual. The rate of response to system error and breakdown was 25%. The reasons for culling cow after using AMS were mastitis (28%), reproduction failure (19%), incorrect teat placement (12%), metabolic disease (7%) and others (14%), respectively. Fifty-six percentages of the respondents made AMS maintenance contract and 44% did not. Average annual cost of the maintenance contract was 6,580,000 won. Average score for AMS satisfaction measurement (1 to 5 range) was 3.2 with decrease of labor cost 3.7, company A/S 3.6, increase of milk yield 3.2 and decrease of somatic cell count 2.8, respectively. Suggestions for the higher efficiency in using AMS were selecting cows with correct udder shape and teat placement, proper environment, capital and land, and attitude for continuous observation. Systematic consulting was highly required for AMS companies followed by low cost for AMS setup and systematization of A/S.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.28 no.2
• /
• pp.99-106
• /
• 2008

This experiment was carried out to show a reform measures by grouping for problems by the survey of TMR plants. Twenty total mixed ration (TMR) plants (10 cooperation and 10 private plants) were surveyed, of which 13 plants, 65% of total TMR plants, committed TMR formulae to a outside nutrition specialist (TMR formulator). With respect to consulting fee for TMR formulae, $500{\sim}900$ thousands Won was paid monthly. On the basis of dry matter 1kg, the prices of TMR products were $325.6{\sim}347.0$Won, whereas those of wet TMR products $365.7{\sim}375.0$Won, which was appeared to be factors to increase management cost. And also, because the TMR plants did not provide TDN (total digestible nutrient) value on their products, nutritional balance feeding for cows could not be managed in farms. It was calculated, based on ADF (acid detergent fiber) value, that TDN value in dry type TMR was 63.0% and 73.2% fur private and cooperation TMR plants, respectively and that the corresponding figure in wet type TMR was 64.9% and 67.2%. According to TMR plant employee's opinion, a prier items to enlarge TMR utilization were TMR education, TMR advertisement, and improvement of ability to make TMR formula. Therefore, for the purpose of further development of TMR, special education of persons related to TMR should be supported.

• Journal of the East Asian Society of Dietary Life
• /
• v.17 no.6
• /
• pp.834-839
• /
• 2007

This study was designed to determine the optimal ratio of dropwort powder in castella by adding the powder at levels of 0, 3, 6, 9, and 12% respectively. The properties of the castella were analyzed by specific gravity, specific volume, color determinations, texture properties and sensory evaluation. The Specific gravity increased with increasing amount of dropwort powder. However, the specific volume decreased with increasing dropwort powder. For the color values, as more dropwort powder was added, the L-value decreased. The castella with 9% dropwort powder had a higher hardness, gumminess, and chewiness. A sensory panel perceived that the external and internal color of the castella become darker with the dropwort powder substitution and the grain size decreased with increasing amount dropwort powder, while sweet taste showed no significant difference. The order of overall preference was DP 9>DP 6>DP 12>CON>DP 3. Therefore, the substitution of 9% of wheat flour with dropwort powder was recommended in the production of castella.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.