• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.

• Journal of Chest Surgery
• /
• v.37 no.4
• /
• pp.297-306
• /
• 2004

Current artificial heart valves have several disadvantages, such as thromboembolism, limited durability, infection, and inability to grow. The solution to these problems would be to develop a tissue-engineered heart valves containing autologous cells. The aim of this study was to optimize the protocol to obtain a porcine acellular matrix and seed goat autologous endothelial cells on it, and to evaluate the biological responses of xenograft and xeno-autograft heart valves in goats. Material and Method: Fresh porcine pulmonic valves were treated with one method among 3 representative decellularization protocols (Triton-X, freeze-thawing, and NaCl-SDS). Goat venous endothelial cells were isolated and seeded onto the acellularized xenograft leaflets. Microscopic examinations were done to select the most effective method of decellularizing xenogeneic cells and seeding autologous endothelial cells. Two pulmonic valve leaflets of. 6 goats were replaced by acellularized porcine leaflets with or without seeding autologous endothelial cells while on cardiopulmonary bypass. Goats were sacrificed electively at 6 hours, 1 day, 1 week, 1 month, 3 months, and 6. months after operation. Morphologic examinations were done to see the biological responses of replaced valve leaflets. Result: The microscopic examinations showed that porcine cells were almost completely removed in the leaflets treated with NaCl-SDS. The seeded endothelial cells were more evenly preserved in NaCl-SDS treatment. All 6 goats survived the operation without complications. The xeno- autografts and xenografts showed the appearance, the remodeling process, and the cellular functions of myofibroblasts, 1 day, 1 month, and 3 months after operation, respectively. They were compatible with the native pulmonary leaflet (control group) except for the increased cellularity at 6 months. The xenografts revealed the new endothelial cell lining at that time. Conclusion: Treatment with NaCl-SDS was most effective in obtaining decellularized xenografts and facilitate seeding autologous endothelial cells. The xenografts and xeno-autografts were repopulated with myofibroblasts and endothelial cells in situ serially. Both of grafts served as a matrix for a tissue engineered heart valve and developed into autologous tissue for 6 months.

• Applied Chemistry for Engineering
• /
• v.18 no.2
• /
• pp.155-161
• /
• 2007

In this study, the reactivity of a $SnO_2-ZrO_2$(Sn/Zr = 2/1) catalyst for $SO_2$ reduction by CO was investigated in order to optimize the various reaction conditions such as temperature, gas hourly space velocity (GHSV), and [CO]/[$SO_2$] molar ratio. The reaction temperature in the range of $300{\sim}550^{\circ}C$, space velocity in the range of $5000{\sim}30000cm^3/[g_{-cat}{\cdot}h]$ and [CO]/[$SO_2$] molar ratio in the range of 1.0~4.0 were employed. The optimum temperature, GHSV, and [CO]/[$SO_2$] molar ratio were determined to be $325^{\circ}C$, $10000cm^3/[g_{-cat}{\cdot}h]$, and 2.0, respectively; under these conditions, $SO_2$ conversion was over 99% and sulfur selectivity was over 95%. In addition, the effect of $H_2O$ content on the $SO_2$ reduction by CO was also investigated. As the $H_2O$ content increased from 2 vol% up to 6 vol%, the reactivity and sulfur selectivity decreased. In case of 2 vol% $H_2O$ content, the reaction temperature and [CO]/[$SO_2$] molar ratio were varied in the range of $300{\sim}400^{\circ}C$ and 1.0~3.0. The optimum temperature and [CO]/[$SO_2$] molar ratio were $340^{\circ}C$ and 2.0, respectively under which $SO_2$ conversion and sulfur selectivity were about 90% and 87%, respectively.

• Korean Journal of Ecology and Environment
• /
• v.44 no.1
• /
• pp.31-41
• /
• 2011

To optimize the natural chemical agents against nuisance phytoplankton, we examined algal removal activity (ABA) of Plant-Mineral Composite (PMC), which already developed by our teams (Kim et al., 2010), on various conditions. The PMC are consisted of extracted-mixtures with indigenous plants (Camellia sinensis, Quercusacutissima and Castanea crenata) and minerals (Loess, Quartz porphyry, and natural zeolite), and characterized by coagulation and floating of low-density suspended solids. A simple extraction process was adopted, such as drying and grinding of raw material, water-extraction by high temperature-sonication and filtering. All tests were performed in 3 L plastic chambers varying conditions; six different concentrations ($0{\sim}1.0\;mL\;L^{-1}$), six light intensities ($8{\sim}1,400\;{\mu}mol\;m^{-2}s^{-1}$), three temperatures ($10{\sim}30^{\circ}C$), four pHs (7~10), five water depths (10~50 cm), and three different waters dominated by cyanobacteria, diatom, and green algae, respectively. Results indicate that the highest ABA of PMC was seen at $0.05\;mL\;L^{-1}$ in treatment concentrations, where showed a reduction of more than 80% of control phytoplankton biomass, while $1,400\;{\mu}mol\;m^{-2}s^{-1}$ in light intensity (>90%), $20{\sim}30^{\circ}C$ temperature (>60%), 7~9 in pH (>90%), below 50 cm in water depth (>90%), and cyanobacterial dominating waters (>80%), respectively. Over the test, ABA of PMC were more obvious on the algal biomass (chlorophyll-${\alpha}$) than suspended solids, suggesting a selectivity of PMC to particle size or natures. These results suggest that PMC agents can play an important role as natural agents to remove the nuisant algal aggregates or seston of eutrophic lake, where occur cyanobacterial bloom in a shallow shore of lake during warm season.

• Journal of Life Science
• /
• v.27 no.7
• /
• pp.754-759
• /
• 2017

The 100 l culture system was made on the basis of LED light, and Nannochloropsis oculata was cultured in f/2 medium at light intensity ($100{\mu}mol/m^2/s$), culture temperature ($20^{\circ}C{\pm}1^{\circ}C$) and LD cycle (12hr). As a result, the maximum biomass of 1.07 g/l was cultured as a result of 100 l mass culture at $100{\mu}mol/m^2/s$ and 24 mg/l nitrate concentration in LED blue (475 nm). The extraction was carried out using sonicator, homogenizer and chemical method 0.5M HCl shredding method. The contents of chlorophyll a, chlorophyll b and carotenoid were 1.6, 0.5 and 0.3 mg/g cell. When using homogenizer, it was measured at 1.0, 0.6 and 0.2 mg/g cell. The chemical breakdown method of 0.5M HCl, chlorophyll a, b, and carotenoid contents were measured as 0.9, 0.8, 0 mg/g cell. The highest amount of biomass during the distruption time was measured at 3.6 mg/g cell at 15 min disintegration and acetone, 3.6 mg/g cell of acetone, methanol, and ethanol were measured as effective solvents. Concentration was measured by using microfilter, disk type continuous centrifuge and tubular type continuous centrifuge were 16.0, 1.1 and 0.5 g/l, respectively. Four kinds of equipment such as hot air dryer, vacuum dryer, spray dryer and freeze dryer were tested to optimize the drying process. As a result, the recovery rates of spray dryer and freeze dryer were 80% and 60%.

• Journal of Korean Society of Environmental Engineers
• /
• v.28 no.5
• /
• pp.549-557
• /
• 2006

The characteristics of supercritical water oxidation have been studied to decompose the waste anionic exchange resins which were produced from a power plant. The waste resins from a power plant were mixture of anionic and cationic exchange resins. The waste anionic exchange resins had been separated from the waste resins using a solid-liquid fluidized bed. It was confirmed that the cationic exchange resins were not included in the separated anionic exchange resins by the elemental and thermogravimetric analysis. A slurry of anionic exchange resins which could be fed continuously to a supercritical water oxidation apparatus by a high pressure pump was prepared using a wet ball mill. Although the COD of liquid effluent had been reduced more than 99.9% at 25.0 MPa and $500^{\circ}C$ within 2 min, the total nitrogen content was reduced only 41%. The addition of nitric acid to the slurry could reduce the total nitrogen content in treated water. The central composite design as a statistical desist of experiments had been applied to optimize the conditions of decomposing anionic resin slurry by means of the COD and total nitrogen contents in treated waters as the key process output variables. The COD values of treated waters had been reduced sufficiently to $99.9{\sim}100%$ af the reaction conditions of $500{\sim}540^{\circ}C$, 25.0 MPa within 2 min. The effects of temperature and nitric acid concentration on COD were not significant. However, the effect of nitric acid concentration on the total nitrogen was found to be significant. The regression equation for the total nitrogen had been obtained with nitric acid concentration and the coefficient of determination($r^2$) was 95.8%.

• Korean Journal of Microbiology
• /
• v.45 no.4
• /
• pp.411-415
• /
• 2009

Some microorganisms are capable of leaching Mn(II) from nonsulfidic manganese ores indirectly via nonenzymatic processes. Such reductive dissolution requires organic substrates, such as glucose, sucrose, or galactose, as a source of carbon and energy for microbial growth. This study investigated characteristics of Mn(II) leaching from manganese nodules by using heterotrophic Bacillus sp. strain MR2 provided with corn starch as a less-expensive substrate. Leaching of Mn(II) at 25.6 g Mn(II) $kg^{-1}$ nodule $day^{-1}$ was accompanied with cell growth, but part of the produced Mn(II) re-adsorbed onto residual $MnO_2$ particles after 24 h. Direct contact of cells to manganese nodule was not necessary as a separation between them with a dialysis tube produced similar amount [24.6 g Mn(II) $kg^{-1}$ nodule $day^{-1}$]. These results indicated an involvement of extracellular diffusible compound(s) during Mn(II) leaching by strain MR2. In order to optimize a leaching process we tested factors that influence the reaction, and the most efficient conditions were $25\sim35^{\circ}C$, pH 5~7, inoculum density of 1.5~2.5% (v/v), pulp density of 2~3 g/L, and particle size <75 ${\mu}m$. Although Mn(II) leaching was enhanced as particle size decrease, we suggest <212 ${\mu}m$ as a proper size range since more grinding means more energy consumption The results would help for the improvement of bioleaching of manganese nodule as a less expensive, energy-efficient, and environment-friendly technology as compared to the existing physicochemical metal recovery technologies.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.46 no.11
• /
• pp.1373-1385
• /
• 2017

The purpose of this study was to optimize the formulation for fish-meat noodles added with farmed olive flounder (Paralichthys olivaceus) using response surface methodology. Fish-meat (surimi) from P. olivaceus was prepared by a traditional washing process. Independent variables were Alaska pollack, fish-meat from P. olivaceus, and starch, whereas dependent variables were whiteness and texture. The results for whiteness and texture produced very significant values for whiteness (P<0.001), strength (P<0.001), hardness (P<0.05), breaking force (P<0.001), chewiness (P<0.001), brittleness (P<0.001), extensibility force (P<0.001), and extensibility distance (P<0.05). The optimal formula for fish-meat noodle was addition of 72.00 g Alaska pollack, 11.59 g P. olivaceus, and 15.86 g starch. Experimental values of whiteness, strength, hardness, breaking force, chewiness, brittleness, extensibility force, and extensibility distance under optimal conditions were $59.01{\pm}0.53$, $708.22{\pm}54.12g/cm^2$, $1,390.07{\pm}67.70g/cm^2$, $3,622.77{\pm}92.52g$, $2,686.94{\pm}103.22g$, $278,578.31{\pm}10,150.22g$, $52.22{\pm}2.97g$, $24.14{\pm}3.55mm$, respectively.

• Journal of Hospice and Palliative Care
• /
• v.22 no.3
• /
• pp.105-116
• /
• 2019

Purpose: Pediatric palliative care (PPC) is emphasized as standard care for children with life-limiting conditions to improve the quality of life. In Korea, a government-funded pilot program was launched only in July 2018. Given that, this study examined various PPC delivery models in other countries to refine the PPC model in Korea. Methods: Target countries were selected based on the level of PPC provided there: the United Kingdom, the United States, Japan, and Singapore. Relevant literature, websites, and consultations from specialists were analyzed by the integrative review method. Literature search was conducted in PubMed, Google, and Google Scholar, focusing publications since 1990, and on-site visits were conducted to ensure reliability. Analysis was performed on each country's process to develop its PPC scheme, policy, funding model, target population, delivery system, and quality assurance. Results: In the United Kingdom, community-based free-standing facilities work closely with primary care and exchange advice and referrals with specialized PPC consult teams of children's hospitals. In the United States, hospital-based specialized PPC consult teams set up networks with hospice agencies and home healthcare agencies and provide PPC by designating care coordinators. In Japan, palliative care is provided through several services such as palliative care for cancer patients, home care for technology-dependent patients, other support services for children with disabilities and/or chronic conditions. In Singapore, a home-based PPC association plays a pivotal role in providing PPC by taking advantage of geographic accessibility and cooperating with tertiary hospitals. Conclusion: It is warranted to identify unmet needs and establish an appropriate PPD model to provide need-based individualized care and optimize PPC in South Korea.