• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Korean Chemical Engineering Research
• /
• v.58 no.4
• /
• pp.541-549
• /
• 2020

The Drug Delivery System (DDS) is defined as a technology for designing existing or new drug formulations and optimizing drug treatment. DDS is designed to efficiently deliver drugs for the care of diseases, minimize the side effects of drug, and maximize drug efficacy. In this study, the optimization of tripolyphosphate (TPP) concentration on the size of Chitosan nanoparticles (CNPs) produced by crosslinking with chitosan was measured. In addition, the characteristics of Fe₃O₄-CNPs according to the amount of iron oxide (Fe₃O₄) were measured, and it was confirmed that the higher the amount of Fe₃O₄, the better the characteristics as a magnetic drug carrier were displayed. Through the ninhydrin reaction, a calibration curve was obtained according to the concentration of γ-aminobutyric acid (GABA) of Y = 0.00373exp(179.729X)-0.0114 (R² = 0.989) in the low concentration (0.004 to 0.02 wt%) and Y = 21.680X-0.290 (R² = 0.999) in the high concentration (0.02 to 0.1 wt%). Absorption was constant at about 62.5% above 0.04 g of initial GABA. In addition, the amount of GABA released from GABA-Fe₃O₄-CNPs over time was measured to confirm that drug release was terminated after about 24 hr. Finally, GABA-Fe₃O₄-CNPs performed under the optimal conditions were spherical particles of about 150 nm, and it was confirmed that the properties of the particles appear well, indicating that GABA-Fe₃O₄-CNPs were suitable as drug carriers.

• KSBB Journal
• /
• v.22 no.5
• /
• pp.297-304
• /
• 2007

For large and rapid screening of high-yielding mutants of lovastatin produced by filamentous fungal cells of Aspergillus terreus, one of the most important stage is to test as large amounts of mutated strains as possible. For this purpose, we intended to develop a miniaturized cultivation method using $7m{\ell}$ culture tube instead of traditional $250m{\ell}$ flask (working volume $50m{\ell}$). For obtaining large amounts of conidiospores to be used as inoculums for miniaturized cultures, 4 components i.e., glucose, sucrose, yeast extract and $KH_2PO_4$ were intensively investigated, which had been observed to show positive effect on enhancement of spore production through Plackett-Burman design experimet. When optimum concentrations of these components that were determined through application of response surface method (RSM) based on central composite design (CCD) were used, maximum spore numbers amounting to $1.9\times10^{10}$ spores/plate were obtained, resulting in approximately 190 fold increase as compared to the commonly used PDA sporulation medium. Using the miniaturized cultures, intensive strain development programs were carried out for screening of lovastatin high-yielding as well as highly reproducible mutants. It was observed that, for maximum production of lovastatin, the producers should be activated through 'PaB' adaptation process during the early solid culture stage. In addition, they should be proliferated in condensed filamentous forms in miniaturized growth cultures, so that optimum amounts of highly active cells could be transferred to the production culture-tube as reproducible inoculums. Under these highly controlled fermentation conditions, compact-pelleted morphology of optimum size (less than 1 mm in diameter) was successfully induced in the miniaturized production cultures, which proved essential for maximal utilization of the producers' physiology leading to significantly enhanced production of lovastatin. As a result of continuous screening in the miniaturized cultures, lovastatin production levels of the 81% of the daughter cells derived from the high-yielding producers turned out to be in the range of 80%$\sim$120% of the lovastatin production level of the parallel flask cultures. These results demonstrate that the miniaturized cultivation method developed in this study is efficient high throughput system for large and rapid screening of highly stable and productive strains.

• KSBB Journal
• /
• v.22 no.5
• /
• pp.288-296
• /
• 2007

Monascus pilosus (KCCM 60160) in submerged culture was optimized based on culture medium and fermentation conditions. Monacolin-K (Iovastatin), one of the cholesterol lowing-agent which was produced by Monascus pilosus may maintain a healthy lipid level by inhibiting the biosynthesis of cholesterol. Plackett-Burman design and response surface method were employed to study the culture medium for the desirable monacolin-K production. As a result of experimental designs, optimized production medium components and concentrations (g/L) were determined on soluble starch 96, malt extract 44.5, beef extract 30.23, yeast extract 15, $(NH_4)_2SO_4$ 4.03, $Na_2HPO_4{\cdot}12H_2O$ 0.5, L-Histidine 3.0, $KHSO_4$ 1.0, respectively. Monacolin-K production was improved about 3 times in comparison with shake flask fermentation of the basic production medium. The effect of agitation speed (300, 350, 400 and 450 rpm) on the monacolin-K production were also observed in a batch fermenter. Maximum monacolin-K production with the basic production medium was 68 mg/L when agitation speed was 500 rpm. And it was found that all spherical pellets (average diameter of $1.0{\sim}1.5mm$) were dominant during fermentation. Based on the results, the maximum production of 185 mg/L of monacolin-K with the optimized production medium was obtained at pH (controlled) 6.5, agitation rate 400 rpm, aeration rate 1 vvm, and inoculum size 3%.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.14 no.1
• /
• pp.13-17
• /
• 2010

Purpose: Partial volume effect (PVE) is the phenomenon to lower the accuracy of image due to low estimate, which is to occur from PET/CT 3D image acquisition. The more resolution is declined and the lesion is small, the more it causes a big error. So that it can influence the test result. Studied the optimum image reconstruction method by using variation of parameter, which can influence the PVE. Materials and Methods: It acquires the image in each size spheres which is injected $^{18}F$-FDG to hot site and background in the ratio 4:1 for 10 minutes by using NEMA 2001 IEC phantom in GE Discovey STE 16. The iterative reconstruction is used and gives variety to iteration 2-50 times, subset number 1-56. The analysis's fixed region of interest in detail part of image and compute % difference and signal to noise ratio (SNR) using $SUV_{max}$. Results: It's measured that $SUV_{max}$ of 10 mm spheres, which is changed subset number to 2, 5, 8, 20, 56 in fixed iteration to times, SNR is indicated 0.19, 0.30, 0.40, 0.48, 0.45. As well as each sphere's of total SNR is measured 2.73, 3.38, 3.64, 3.63, 3.38. Conclusion: In iteration 6th to 20th, it indicates similar value in % difference and SNR ($3.47{\pm}0.09$). Over 20th, it increases the phenomenon, which is placed low value on $SUV_{max}$ through the influence of noise. In addition, the identical iteration, it indicates that SNR is high value in 8th to 20th in variation of subset number. Therefore, to reduce partial volume effect of small lesion, it can be declined the partial volume effect in iteration 6 times, subset number 8~20 times, considering reconstruction time.

• Journal of the Korean Geographical Society
• /
• v.29 no.3
• /
• pp.233-252
• /
• 1994

One of major advantages of Lumped model is its ability to simulate extended flows. A further advantage is that it requires only conventional, readily available hydrological data (rainfall, evaporation and runoff). These two advantages commend the use of this type of model for the analysis of the hydrological effects of landuse change. Experimental Catchment(K11) of Kimakia site in Kenga experienced three phases of landuse change for sixteen and half years. The Institute of Hydrology offered the hydrological data from the catchment for this research. On basis of Blackie's(l972) 9-parameter model, a new model(R1131) was reorganized in consideration of the following aspects to reflect the hydrological characteristics of the catchment: 1) The evapotranspiration necessary for the landuse hydrology, 2) high permeable soils, 3) small catchment, 4) input option for initial soil moisture deficit, and 5) othel modules for water budget analysis. The new model is constructed as a 11-parameter, 3-storage, 1-input option model. Using a number of initial conditions, the model was optimized to the data of three landuse phases. The model efficiencies were 96.78%, 97.20%, 94.62% and the errors of total flow were -1.78%, -3.36%, -5.32%. The bias of the optimized models were tested by several techniques, The extended flows were simulated in the prediction mode using the optimized model and the data set of the whole series of experimental periods. They are used to analyse the change of daily high and low-flow caused by landuse change. The relative water use ratio of the clearing and seedling phase was 60.21%, but that of the next two phases were 81.23% and 83.78% respectively. The annual peak flows of second and third phase at a 1.5-year return period were decreased by 31.3% and 31.2% compared to that of the first phase. The annual peak flow at a 50-year return period in the second phase was an increase of only 4.8%, and that in the third phase was an increase of 12.9%. The annual minimum flow at a 1.5-year return period was decreased by 34.2% in the second phase, and 34.3% in the third phase. The changes in the annual minimum flows were decreased for the larger return periods; a 20.2% decrease in the second phase and 20.9% decrease in the third phase at a 50-year return period. From the results above, two aspects could be concluded. Firstly, the flow regime in Catchment K11 was changed due to the landuse conversion from the clearing and seedling phade to the intermediate stage of pine plantation. But, The flow regime was little affected after the pine trees reached a certain height. Secondly, the effects of the pine plantation on the daily high- and low-flow were reduced with the increase in flood size and the severity of drought.

• 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.

• Progress in Medical Physics
• /
• v.26 no.2
• /
• pp.79-86
• /
• 2015

The purpose of this study is to evaluate efficacy and feasibility of adaptive radiotherapy according to tumor volume change (TVC) in early stage non-small cell lung cancer (NSCLC) using stereotactic body radiotherapy (SBRT). Twenty-two lesions previously treated with SBRT were selected. SBRT was usually performed with a total dose of 48 Gy or 60 Gy in four fractions with an interval of three to four days between treatments. For evaluation of TVC, gross tumor volume (GTV) was contoured on each cone-beam computed tomography (CBCT) image used for image guidance. Intensity modulated radiotherapy (IMRT) planning was performed in the first CBCT (CBCT1) using a baseline plan. For ART planning (ART), re-optimization was performed at $2^{nd}$, $3^{rd}$, and $4^{th}$ CBCTs (CBCT2, CBCT3, and CBCT4) using the same angle and constraint used for the baseline plan. The ART plan was compared with the non-ART plan, which generated copying of the baseline plan to other CBCTs. Average GTV volume was 10.7 cc. Average TVC was -1.5%, 7.3%, and -25.1% in CBCT2, CBCT3, and CBCT4 and the TVC after CBCT3 was significant (p<0.05). However, the nine lesions were increased GTV in CBCT2. In the ART plan, $V_{20\;Gy}$, $D_{1500\;cc}$, and $D_{1000\;cc}$ of lung were significantly decreased (p<0.05), and $V_{30\;Gy}$ and $V_{32\;Gy}$ of the chest wall were also decreased (p<0.05). While D min of planning target volume (PTV) decreased by 8.3% in the non-ART plan of CBCT2 compared with the baseline plan in lesions with increased tumor size (p=0.021), PTV coverage was not compromised in the ART plan. Based on this result, use of the ART plan may improve target coverage and OAR saving. Thus ART using CBCT should be considered in early stage NSCLC with SBRT.

• Journal of Life Science
• /
• v.12 no.3
• /
• pp.242-249
• /
• 2002

The optimal culture conditions in 500$m\ell$ flask suture, 5$\ell$ jar fermenter and 2,000 $\ell$ large stale culture were investigated to maximize the production of antibiotic on Rhizoctonia solani AC4, the causal agent of vegetables damping-off, by the strain Bacillus ehimensis YJ-37. Starch (1.5%) as a carbon source, peptone (0.6%) as a nitrogen source and MgC1$_2$(0.15%) as a metal ion in the medium containing N $a_2$HP $O_4$(0.3%) showed the highest production of the antibiotic(s) in a rotary shake (200 rpm). Optimal initial pH of the culture medium, culture temperature and culture time for the antibiotic(s) production were pH 8.0, 32$^{\circ}C$ and 54hrs, respertively. Under the optimal renditions in flask culture, cell growth and antifungal activity (clear zone size) were 1.42 $\times$ 10$^{8}$ cfu/$m\ell$ (21g-DCW/ $\ell$) and 13.9 mm, respectively. In 5 $\ell$ jar fermenter (medium 3 $\ell$), optimal air flow, agitation speed and culture time for the antibiotic(s) production were 2 vvm, 200 rpm and 48hrs, respectively. Under the optimal conditions in 5 $\ell$ jar fermenter, tell growth and antifungal activity were 2.06 $\times$ 10$^{8}$ cfu/$m\ell$ (30g-DCW/ $\ell$) and 13.4 mm, respectively. Under the culture conditions of air flow (30 vvm) and agitation speed (200 rpm) at 32$^{\circ}C$ for 10 days in 2,000 $\ell$ large scale culture (medium 1,800 $\ell$, pH 8.0), cell growth and antifungal activity were 0.81$\times$10$^{8}$ cfu/$m\ell$ (12g-DCW/ $\ell$) and 8.6 mm, respectively.

• Clean Technology
• /
• v.27 no.4
• /
• pp.332-340
• /
• 2021

With the recent reinforcement of emission standards, it is necessary to make efforts to reduce NOx from air pollutant-emitting workplaces. The NOx reduction method mainly used in industrial facilities is selective catalytic reduction (SCR), and the most commercial SCR catalyst is the ceramic honeycomb catalyst. This study was carried out to reduce the NOx emitted from steel plants by applying De-NOx catalyst coated on metallic monolith. The De-NOx catalyst was synthesized through the optimized coating technique, and the coated catalyst was uniformly and strongly adhered onto the surface of the metallic monolith according to the air jet erosion and bending test. Due to the good thermal conductivity of metallic monolith, the De-NOx catalyst coated on metallic monolith showed good De-NOx efficiency at low temperatures (200 ~ 250 ℃). In addition, the optimal amount of catalyst coating on the metallic monolith surface was confirmed for the design of an economical catalyst. Based on these results, the De-NOx catalyst of commercial grade size was tested in a semi-pilot De-NOx performance facility under a simulated gas similar to the exhaust gas emitted from a steel plant. Even at a low temperature (200 ℃), it showed excellent performance satisfying the emission standard (less than 60 ppm). Therefore, the De-NOx catalyst coated metallic monolith has good physical and chemical properties and showed a good De-NOx efficiency even with the minimum amount of catalyst. Additionally, it was possible to compact and downsize the SCR reactor through the application of a high-density cell. Therefore, we suggest that the proposed De-NOx catalyst coated metallic monolith may be a good alternative De-NOx catalyst for industrial uses such as steel plants, thermal power plants, incineration plants ships, and construction machinery.