• The Journal of Information Systems
• /
• v.26 no.3
• /
• pp.63-90
• /
• 2017

Purpose This study proposes a novel system trading model using case-based reasoning (CBR) based on absolute similarity threshold. The proposed model is designed to optimize the absolute similarity threshold, feature selection, and instance selection of CBR by using genetic algorithm (GA). With these mechanisms, it enables us to yield higher returns from stock market trading. Design/Methodology/Approach The proposed CBR model uses the absolute similarity threshold varying from 0 to 1, which serves as a criterion for selecting appropriate neighbors in the nearest neighbor (NN) algorithm. Since it determines the nearest neighbors on an absolute basis, it fails to select the appropriate neighbors from time to time. In system trading, it is interpreted as the signal of 'hold'. That is, the system trading model proposed in this study makes trading decisions such as 'buy' or 'sell' only if the model produces a clear signal for stock market prediction. Also, in order to improve the prediction accuracy and the rate of return, the proposed model adopts optimal feature selection and instance selection, which are known to be very effective in enhancing the performance of CBR. To validate the usefulness of the proposed model, we applied it to the index trading of KOSPI200 from 2009 to 2016. Findings Experimental results showed that the proposed model with optimal feature or instance selection could yield higher returns compared to the benchmark as well as the various comparison models (including logistic regression, multiple discriminant analysis, artificial neural network, support vector machine, and traditional CBR). In particular, the proposed model with optimal instance selection showed the best rate of return among all the models. This implies that the application of CBR with the absolute similarity threshold as well as the optimal instance selection may be effective in system trading from the perspective of returns.

• The Journal of Fisheries Business Administration
• /
• v.22 no.2
• /
• pp.75-99
• /
• 1991

A quantitative analysis was carried out to monitor the commercial yield level of walleye pollock Theragra chalcogramma in the east coast of Korea, based on available data on catch and fishing effort, catch per unit of effort including fish prices from 1911 to 1988, using a traditional yield model. The results from the quantitative assessment were based to estimate maximum economic yield (MEY) and optimal fishing effort (E-opt) at MEY. On the other hand, interaction aspects between danish seine fishery and trawl fishery mainly targeting walleye pollock in the east coast of Korea were studied to predict optimal situation in fishing effort level from economic point of view which gives the most benefits to the two fisheries. Total production of walleye pollock in 1911 when its catch record was begun for the first time was about 12, 000 metric tons(M/T), and then the catch trend maintained nearly at the level of 50, 000 M/T per annum, showing a decreasing trend until 1930. The highest production from historical data base on walleye pollock fishery statistics was from the years in 1939 and 1940, about 270, 000 M/T and 26, 000 M/T, respectively. No production of the fish species was recorded during the years from 1943 to 1947, and from 1949 to 1951. From 1952 onwards annual production was only available from the southern part of 38$^{\circ}$N in the east coast. During two decades from 1952 to 1970, the production had sustained about less than 30, 000 M/T every year. Annual production showed an increasing trend from 1971, reaching a maximum level of approximately 162, 000 M/T in 1981. Afterwards, it has deceased sharply year after year and amounted to 180, 000 M/T in 1988. The catch composition of walleye pollock for different fishery segments during 1970~1988 showed that more than 70% of the total catch was from danish seine fishery until 1977 but from 1978 onwards, the catch proportion did not differ from one another, accounting for the nearly same proportion. Catch per unit of effort (CPUE) for both danish seine fishery and trawl fishery maintained a decline tendency after 1977 when the values of CPUE were at level of 800 kg/haul for the former fishery and 1, 300 kg/haul for the latter fishery, respectively. CPUEs of gillnet fishery during 1980~1983 increased to about 3.5 times as high value as in the years, 1970~1979 and during 1987~1988 it decreased again to the level of the years, 1970~1978. The bottom longline fishery's CPUE wa at a very low level (20 kg/basket) through the whole study years, with exception of the value (60 kg/basket) in 1980. Fishing grounds of walleye pollock in the east coast of Korea showed a very limited distribution range. Danish seine fishery concentrated fishing around the coastal areas of Sokcho and Jumunjin during January~February and October~December. Distributions of fishing grounds of trawl fishery were the areas along the coastal regions in the central part of the east coast. Gillnet and bottom longline fisheries fished walleye pollock mainly in the areas of around Sokcho and Jumunjin during January~February and December. Relationship between CPUEs' values from danish seine fishery and trawl fishery was used to standardize fishing effort to apply to surplus production model for estimating maximum sustainable yield (MSY) and optimum fish effort (F-opt) at MSY. The results suggested a MSY of 114, 000 M/T with an estimated F-opt of 173, 000 hauls per year. Based on the estimates of MSY and F-opt, MEY was estimated to be about 94, 000 M/T with a range of 81, 000 to 103, 000 M/T and E-opt 100, 000 hauls per year with a range of 80, 000 to 120, 000 hauls. The estimated values of MEY and E-opt corresponded to 82% of MSY and 58% of F-opt, respectively. An optimal situation in the fishing effort level, which can envisage either simultaneously maximum yield or maximum benefit for both danish seine fishery and trawl fishery, was determined from relationship between revenue and cost of running the fleet : the optimal fishing effort of danish seine fishery was about 52, 000 hauls per year, corresponding to 50 danish seiners and 27, 000 hauls per year which is equal nearly to 36 trawlers, respectively. It was anticipated that the net income from sustainable yield estimated from the respective optimal fishing effort of the two fisheries will be about 3, 800 million won for danish seine fishery and 1, 000 million won for trawl fishery.

• The Korean Journal of Mycology
• /
• v.31 no.3
• /
• pp.192-199
• /
• 2003

This study was carried out to investigate the artificial cultivation of Pleurotus eryngii on the optimal medium vessel, periods of cultivation and the optimal method of pinheading for both yield and quality of fruiting body were also performed. The optimal composition of sawdust medium in polypropylene(PP) bottle was combination of sawdust(70%) and corncob(30%) but increased amount of corncob delayed the period of mycelial growth. The mycelial growth and the yield of fruiting body in the medium with beat pulp were worse than that without beat pulp. The optimal composition of nutrients for both yield and quality of fruit body tuned out to be a combination of rice bran(12%), wheat bran(12%) and cottonseed cake(6%). Additions of zeolite, shell lime and bean curd dregs were not effective in mycelial growth and yield of fruit body. When testing size of PP bottle for cultivation, the larger of bottle mouth is, the more pinheading number found, but the number of available fruit body is not significantly different. The culture in $1100\;ml-{\phi}75\;mm$ bottle is the best in the yield and quality of fruit body than those in $555\;ml-{\phi}50\;mm,\;850\;ml-{\phi}58\;mm,\;850\;ml-{\phi}65\;mm\;and\;1100\;ml-{\phi}65\;mm$ bottle. Using the PP bag for cultivation, a square shaped bag was better than a round shaped and black square shaped in mycelial growth and yield of fruit body. The most suitable period of incubation was 35 days after inoculation at $22{\pm}2^{\circ}C$. When the incubation periods was decreased less than 35 days, the pileus formation and yields were very bad but a pinheading condition looked similar, For an optimal pinheading, turning upside down was better than standing and covering.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.45 no.1
• /
• pp.14-19
• /
• 2000

In order to develop an appropriate cultural practice for a newly bred 2-rowed, waxy, naked barley cultivar 'Duwonchapssalbori' in the southern region, 2 varieties, 3 seeding dates, 4 seeding rates were designed with 2 replications. The heading and maturity dates of 'Duwonchapssalbori' were' earlier than 'Saessalbori by 2-5 and 4 days, respectively. Culm length of 'Duwonchapssalbori' was 60 to 66cm with lodging resistance. Grain yields of both varieties were 4.28-4.33 ton/ha in the plot of Oct. 20 seeding, 4.11-4.18 ton in the plot of Oct. 28 seeding, and 3.7-13.89 ton/ha in the Nov. 5 seeding. Grain yield with different seeding rates highly significantly fitted with secondary polynomial equations in the plots of Oct. 20 and Oct. 28 seedings ($R^2$=0.84-0.85), showing the greatest yield with seeding rate of 140kg per ha. However, the grain yield with various seeding rates in the plot of Nov. 5 seeding showed simple linear regression ($R^2$=0.71), showing the seeding rate over 160kg in the case of later seeding to be optimal. Number of spikes per $m^2$ significantly contributed to grain yield, and fitted to simple linear regression ($R^2$=0.881-0.891), suggesting that plenty of early stands should be established at early seedling stage for high grain yield. Young spikes of 'Duwonchapssalbori' in the plot of Oct. 20 seeding elongated with linear increments since Feb. 10 (6.7mm), and showed rapid increment since March 7 (15.1mm). However, elongation of young spikes of 'Saessalbori' began from March 15 with slow increments. From these studies, the optimum seeding date and seeding rate in 'Duwonchapssalbori' were Oct. 20-28 and 140kg per ha for high grain yield in the southern regions.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.53 no.3
• /
• pp.297-302
• /
• 2008

Application of genotype by environment ($G\;{\times}\;E$) interaction would be used for identifying optimum test condition of the varietal adaptation in the establishment of breeding purpose. Yield and yield components were used to perform additive main effect and multiplicative interaction (AMMI) analysis. Significant difference for $G\;{\times}\;E$ interaction were observed for all variable examined. For yield, 0.18 of total sum of squares corresponded to $G\;{\times}\;E$ interaction. Correlation analysis was carried out between genotypic scores of the first interaction principal component axis (IPCA 1) for agronomic characters. Significant correlations were observed between IPCA 1 for yield and capsule bearing stem length (CBSL), number of capsule per plant (NOC). The biplot of grain yield means for IPCA1 which accounted for 34% of the variation in total treatment sums of squares showed different reaction according to $G\;{\times}\;E$ interaction, genotypes and environments. Taegu showed relatively lower positive IPCA1 scores, and it also showed smaller coefficient variation of yield mean where it is recommendable as a optimal site for the sesame cultivar adaptation and evaluation trial. In case of variables, Yangbaek and M1 showed relatively lower IPCA1 scores, but the score direction showed opposite each other on the graph. Ansan, Miryang1, Miryang4, and Miryang6 seemed to be similar group in view of yield response against IPCA1 scores. These results will be helpful to select experimental site for sesame in Korea to minimize $G\;{\times}\;E$ interaction for the selection of promising genotype with higher stability.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2006.06b
• /
• pp.295-303
• /
• 2006

The pulp yield was improved by about 4.5-5% when polysulfide (PS) and anthraquinone (AQ) were added to the kraft cooking liquor (white liquor). The exchange of the black liquor with fresh white liquor further increased the yield. The highest pulp yield was obtained when the PS cooking liquor containing 70% of total active alkali (AA) and 100% of AQ was used from the beginning of the reaction and the black liquor was exchanged with fresh white liquor containing the residual 30% of AA just after temperature reached $135^{\circ}C$. There was a good correlation between kraft pulp yields of a hardwood species and the ratios of the amount of xylose to glucose (X/G ratio), liberated by an acid hydrolysis of the pulps. However, the correlation was dependent on raw material wood species. Therefore, it is required in advance to establish a correlation between the yields and X/G ratios for raw material wood species of a target pulp in order to estimate pulp yield using X/G ratio. The X/G ratios of relatively high yield pulps showed higher values than those expected from the correlation. In a mill trial, the superiority of the PS-AQ isothermal cooking (ITC) process over the kraft ITC process was confirmed by examining X/G ratio of pulps obtained. The pulp yield in the PS-AQ ITC process was estimated at about 57.0%. This yield is very high, which indicates that reaction conditions of the PS-AQ ITC process are optimal.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.7
• /
• pp.1234-1242
• /
• 2003

In this paper we present a simple and efficient robust optimal design formulation for MEMS structures and its application to a resonant-type micro probe. The basic idea is to use the gradient index (GI) to improve robustness of the objective and constraint functions. In the robust optimal design procedure, a deterministic optimization for performance of MEMS structures is followed by design sensitivity analysis with respect to uncertainties such as fabrication errors and change of operating conditions. During the process of deterministic optimization and sensitivity analysis, dominant performance and uncertain variables are identified to define GI. The GI is incorporated as a term of objective and constraint functions in the robust optimal design formulation to make both performance and robustness improved. While most previous approaches for robust optimal design require statistical information on design variations, the proposed GI based method needs no such information and therefore is cost-effective and easily applicable to early design stages. For the micro probe example, robust optimums are obtained to satisfy the targets for the measurement sensitivity and they are compared in terms of robustness and production yield with the deterministic optimums through the Monte Carlo simulation. This method, although shown for MEMS structures, may as well be easily applied to conventional mechanical structures where information on uncertainties is lacking but robustness is highly important.

• Smart Structures and Systems
• /
• v.16 no.6
• /
• pp.1023-1047
• /
• 2015

In this study, the optimal location of the MR fluid segments in a partially treated laminated composite sandwich plate has been identified to maximize the natural frequencies and the loss factors. The finite element formulation is used to derive the governing differential equations of motion for a partially treated laminated composite sandwich plate embedded with MR fluid and rubber material as the core layer and laminated composite plate as the face layers. An optimization problem is formulated and solved by combining finite element analysis (FEA) and genetic algorithm (GA) to obtain the optimal locations to yield maximum natural frequency and loss factor corresponding to first five modes of flexural vibration of the sandwich plate with various combinations of weighting factors under various boundary conditions. The proposed methodology is validated by comparing the natural frequencies evaluated at optimal locations of MR fluid pockets identified through GA coupled with FEA and the experimental measurements. The converged results suggest that the optimal location of MR fluid pockets is strongly influenced not only by the boundary conditions and modes of vibrations but also by the objectives of maximization of natural frequency and loss factors either individually or combined. The optimal layout could be useful to apply the MR fluid pockets at critical components of large structure to realize more efficient and compact vibration control mechanism with variable damping.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.1254-1261
• /
• 2003

In this paper we present a simple and efficient robust optimal design formulation and its application to a resonant-type micro probe. The basic idea is to use the Gradient Index (GI) to improve robustness of the objective and constraint functions. In the robust optimal design procedure, a deterministic optimization for performance of MEMS structures is followed by design sensitivity analysis with respect to uncertainties such as fabrication errors and change of operating conditions. During the process of deterministic optimization and sensitivity analysis, dominant performance and uncertain variables are identified to define GI. The GI is incorporated as a term of objective and constraint functions in the robust optimal design formulation to make both performance and robustness improved. While most previous approaches for robust optimal design require statistical information on design variations, the proposed GI based method needs no such information and therefore is cost-efficient and easily applicable to early design stages. For the micro probe example, robust optimums are obtained to satisfy the targets for the measurement sensitivity and they are compared in terms of robustness and production yield with the deterministic optimums through the Monte Carlo simulation.

• Structural Engineering and Mechanics
• /
• v.15 no.6
• /
• pp.669-683
• /
• 2003

The stochastic optimal nonlinear control of coupled adjacent building structures is studied based on the stochastic dynamical programming principle and the stochastic averaging method. The coupled structures with control devices under random seismic excitation are first condensed to form a reduced-order structural model for the control analysis. The stochastic averaging method is applied to the reduced model to yield stochastic differential equations for structural modal energies as controlled diffusion processes. Then a dynamical programming equation for the energy processes is established based on the stochastic dynamical programming principle, and solved to determine the optimal nonlinear control law. The seismic response mitigation of the coupled structures is achieved through the structural energy control and the dimension of the optimal control problem is reduced. The seismic excitation spectrum is taken into account according to the stochastic dynamical programming principle. Finally, the nonlinear controlled structural response is predicted by using the stochastic averaging method and compared with the uncontrolled structural response to evaluate the control efficacy. Numerical results are given to demonstrate the response mitigation capabilities of the proposed stochastic optimal control method for coupled adjacent building structures.