• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.139-157
• /
• 2016

Bankruptcy involves considerable costs, so it can have significant effects on a country's economy. Thus, bankruptcy prediction is an important issue. Over the past several decades, many researchers have addressed topics associated with bankruptcy prediction. Early research on bankruptcy prediction employed conventional statistical methods such as univariate analysis, discriminant analysis, multiple regression, and logistic regression. Later on, many studies began utilizing artificial intelligence techniques such as inductive learning, neural networks, and case-based reasoning. Currently, ensemble models are being utilized to enhance the accuracy of bankruptcy prediction. Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving the generalization ability of the classifier. Base classifiers in the ensemble must be as accurate and diverse as possible in order to enhance the generalization ability of an ensemble model. Commonly used methods for constructing ensemble classifiers include bagging, boosting, and random subspace. The random subspace method selects a random feature subset for each classifier from the original feature space to diversify the base classifiers of an ensemble. Each ensemble member is trained by a randomly chosen feature subspace from the original feature set, and predictions from each ensemble member are combined by an aggregation method. The k-nearest neighbors (KNN) classifier is robust with respect to variations in the dataset but is very sensitive to changes in the feature space. For this reason, KNN is a good classifier for the random subspace method. The KNN random subspace ensemble model has been shown to be very effective for improving an individual KNN model. The k parameter of KNN base classifiers and selected feature subsets for base classifiers play an important role in determining the performance of the KNN ensemble model. However, few studies have focused on optimizing the k parameter and feature subsets of base classifiers in the ensemble. This study proposed a new ensemble method that improves upon the performance KNN ensemble model by optimizing both k parameters and feature subsets of base classifiers. A genetic algorithm was used to optimize the KNN ensemble model and improve the prediction accuracy of the ensemble model. The proposed model was applied to a bankruptcy prediction problem by using a real dataset from Korean companies. The research data included 1800 externally non-audited firms that filed for bankruptcy (900 cases) or non-bankruptcy (900 cases). Initially, the dataset consisted of 134 financial ratios. Prior to the experiments, 75 financial ratios were selected based on an independent sample t-test of each financial ratio as an input variable and bankruptcy or non-bankruptcy as an output variable. Of these, 24 financial ratios were selected by using a logistic regression backward feature selection method. The complete dataset was separated into two parts: training and validation. The training dataset was further divided into two portions: one for the training model and the other to avoid overfitting. The prediction accuracy against this dataset was used to determine the fitness value in order to avoid overfitting. The validation dataset was used to evaluate the effectiveness of the final model. A 10-fold cross-validation was implemented to compare the performances of the proposed model and other models. To evaluate the effectiveness of the proposed model, the classification accuracy of the proposed model was compared with that of other models. The Q-statistic values and average classification accuracies of base classifiers were investigated. The experimental results showed that the proposed model outperformed other models, such as the single model and random subspace ensemble model.

• Journal of Korean Society of Forest Science
• /
• v.105 no.4
• /
• pp.510-516
• /
• 2016

This study was conducted to investigate the physiological responses of newly-germinated seedlings of Fraxinus rhynchophylla Hance, Zelkova serrata (Thunb.) Makino, Betula costata Trautv. and Quercus variabilis Blume to open-field experimental warming. The seedlings in the warmed plots were warmed with $2.7^{\circ}C$ higher air temperature than those in the control plots using infrared heaters since April, 2015. Physiological responses (stomatal conductance, transpiration rate, chlorophyll content and net photosynthetic rate) to experimental warming varied with the species and the time of the measurement. Stomatal conductance ($mmol{\cdot}m^{-2}{\cdot}s^{-1}$) tended to decrease for F. rhynchophylla (Control: $158.97{\pm}42.76$; Warmed: $42.07{\pm}8.24$), Z. serrata (Control: $170.53{\pm}27.22$; Warmed: $101.17{\pm}42.27$) and B. costata (Control: $249.93{\pm}47.39$; Warmed: $150.73{\pm}26.52$). Transpiration rate ($mmol{\cdot}m^{-2}{\cdot}s^{-1}$) also decreased for F. rhynchophylla (Control: $4.08{\pm}0.62$; Warmed: $1.74{\pm}0.39$), Z. serrata (Control: $4.32{\pm}0.44$; Warmed: $3.24{\pm}1.14$) and B. costata (Control: $6.21{\pm}0.38$; Warmed: $4.66{\pm}0.28$). However, warming exhibited only minimal effects on stomatal conductance and transpiration rate of Q. variabilis seedlings. Chlorophyll content increased by the warming treatment while the effect of warming was not significant on net photosynthetic rate, since the warming treatment had a weak influence for changing net photosynthetic rate.

• Journal of radiological science and technology
• /
• v.31 no.1
• /
• pp.55-60
• /
• 2008

Purpose: This study is to decide a quality control and calibration period of LCD display devices used for reading diagnostic images. Materias and Methods: The assessment test of 20 flat panel LCD color display devices used for reading diagnostic images were performed based on AAPM TG 18 protocol over the total six sessions at one month intervals from three months after primary calibration, in terms of geometric distortion, reflection test, luminance response evaluation, luminance uniformity, resolution, noise, veiling glare and chromaticity test. Results: The results of geometric distortion, reflection test, luminance uniformity, resolution, noise, veiling glare and chromaticity test were within the criteria recommended by AAPM TG 18, except for luminance response evaluation. In the measured luminance deviation of luminance response evaluation, 4(25%) of 20 display devices were passed a criterion from four months after calibration, and 11 (55%) were passed from eight months. Also in the contrast response of the luminance response evaluation, 1(5%) display device was passed a criterion from four months after calibration, and 3(15%) were passed from eight months. Conclusion: Considering the passing deviation after calibration, the time required and a manpower, the quality control and calibration period of LCD display devices used for reading diagnostic images should be a three months and six months after calibration.

• Journal of Nutrition and Health
• /
• v.51 no.4
• /
• pp.275-286
• /
• 2018

Purpose: Our previous study demonstrated that persimmon (Diospyros kaki Thumb.) at different stages of ripening provided different protective effects against high-fat/cholesterol diet (HFD)-induced dyslipidemia in rats. In this study, we compared the metabolites profile and gene expressions related to triglyceride (TG)/cholesterol metabolism in vitro and in vivo after treating with persimmon water extracts (PWE) or tannin-enriched persimmon concentrate (TEP). Methods: Primary and secondary metabolites in test materials were determined by GC-TOF/MS, UHPLC-LTQ-ESI-IT-MS/MS, and UPLC-Q-TOF-MS. The expression of genes related to TG and cholesterol metabolism were determined by RT-PCR both in HepG2 cells stimulated by oleic acid/palmitic acid and in liver tissues obtained from Wistar rats fed with HFD and PWE at 0, 150, 300, and 600 mg/d (experiment I) or TEP at 0, 7, 14, and 28 mg/d (experiment II) by oral gavage for 9 weeks. Results: PLS-DA analysis and heatmap analysis demonstrated significantly differential profiling of metabolites of PWE and TEP according to processing of persimmon powder. In vitro, TEP showed similar hypolipidemic effects as PWE, but significantly enhanced hypocholesterolemic effects compared to PWE in sterol regulatory element-binding protein 2 (SREBP2), HMG-CoA reductase (HMGCR), proprotein convertase subtilisin/kexin type 9 (PCSK9), cholesterol $7{\alpha}-hydroxylase$ (CYP7A1), and low density lipoprotein receptor (LDLR) gene expression. Consistently, TEP and PWE showed similar hypolipidemic capacity in vivo, but significantly enhanced hypocholesterolemic capacity in terms of SREBP2, HMGCR, and bile salt export pump (BSEP) gene expression. Conclusion: These results suggest that column extraction after hot water extraction may be a good strategy to enhance tannins and long-chain fatty acid amides, which might cause stimulation of hypocholesterolemic actions through downregulation of cholesterol biosynthesis gene expression and upregulation of LDL receptor gene expression.

• The Journal of Korean Society for Radiation Therapy
• /
• v.27 no.1
• /
• pp.87-95
• /
• 2015

Purpose : This study presents the usefulness assessment of secondary shield for the lens exposure dose reduction during radiation treatment of peripheral orbit. Materials and Methods : We accomplished IMRT treatment plan similar with a real one through the computed treatment planning system after CT simulation using human phantom. For the secondary shield, we used Pb plate (thickness 3mm, diameter 25mm) and 3 mm tungsten eye-shield block. And we compared lens dose using OSLD between on TPS and on simulation. Also, we irradiated 200 MU(6 MV, SPD(Source to Phantom Distance)=100 cm, $F{\cdot}S\;5{\times}5cm$) on a 5cm acrylic phantom using the secondary shielding material of same condition, 3mm Pb and tungsten eye-shield block. And we carried out the same experiment using 8cm Pb block to limit effect of leakage & transmitted radiation out of irradiation field. We attached OSLD with a 1cm away from the field at the side of phantom and applied a 3mm bolus equivalent to the thickness of eyelid. Results : Using human phantom, the Lens dose on IMRT treatment plan is 315.9cGy and the real measurement value is 216.7cGy. And after secondary shield using 3mm Pb plate and tungsten eye-shield block, each lens dose is 234.3, 224.1 cGy. The result of a experiment using acrylic phantom, each value is 5.24, 5.42 and 5.39 cGy in case of no block, 3mm Pb plate and tungsten eye-shield block. Applying O.S.B out of the field, each value is 1.79, 2.00 and 2.02 cGy in case of no block, 3mm Pb plate and tungsten eye-shield block. Conclusion : When secondary shielding material is used to protect critical organ while irradiating photon, high atomic number material (like metal) that is near by critical organ can be cause of dose increase according to treatment region and beam direction because head leakage and collimator & MLC transmitted radiation are exist even if it's out of the field. The attempt of secondary shield for the decrease of exposure dose was meaningful, but untested attempt can have a reverse effect. So, a preliminary inspection through Q.A must be necessary.

• Journal of Korean Society of Forest Science
• /
• v.110 no.3
• /
• pp.406-418
• /
• 2021

This study was conducted to evaluate optimal storage techniques for bare root plants and container seedlings of Quercus variabilis and Zelkova serrata in order to maintain high quality of seedlings until planting. Refrigerated storage treatments were given at two temperatures (-2℃ [freezing] and 2℃ [cooling]) for nine different durations (0, 15, 30, 60, 120, 180, 240, 300, and 360 days after storage). We analyzed total nonstructural carbohydrate (TNC) content and measured shoot moisture content (SMC) during the storage stage and survival rate (SR) and dry weight during the planting stage of seedlings. The TNC content and SMC of the seedlings of the two species decreased with an increase in storage duration. The TNC content of seedlings rapidly decreased after 180~240 days of storage. The TNC reduction rate in the freezing treatment was lower than that in the cooling treatment. Also, with an increase in the storage duration of the two species, the SMC reduction rate in the cooling treatment increased in comparison with that in the freezing treatment. In both the species, the SR after planting decreased rapidly after 60 days of cooling storage and 180 days of freezing storage, respectively. The SR after planting was less than 60% when the TNC content for both the species dropped below 20 mg g^-1. In addition, the SR was lower than 80% when SMC measured before storage decreased by approximately 30% and 20% for Q. variabilis and Z. serrata, respectively. Our results suggest that cooling (1~2℃) storage is recommended for a short-term period (2 months or less), whereas freezing (-2~-4℃) storage is suitable for longer periods (2~6 months). These optimal storage techniques, allied with seedling harvesting and handling systems, will improve the quality of seedling production in nursery stages and increase seedling growth performances in plantations.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.3
• /
• pp.208-220
• /
• 2019

The seasonality of leaf fall has important implications for understanding the response of trees' phenology to climate change. In this study, we quantified the leaf fall pattern with a model to estimate the timing and speed of leaf litter according to species and considered the nutrient use strategy of canopy species. In the autumns of 2015 and 2016, leaf litter was collected periodically using 36 litter-traps from the deciduous forests in Gwangneung and sorted by species. The seasonal leaf fall pattern was estimated using the non-linear regression model of Dixon. Additionally, the resorption rate was calculated by analyzing the nitrogen concentration of the leaf litter at each collection time. The leaf litter generally began in early October and ended in mid-November depending on the species. At the peak time (T50) of leaf fall, on average, Carpinus laxiflora was first, and Quercus serrata was last. The rate of leaf fall was fastest (18.6 days) for Sorbus alnifolia in 2016 and slowest (40.8 days) for C. cordata in 2015. The nitrogen resorption rates at T50 were 0.45% for Q. serrata and 0.48% for C. laxiflora, and the resorption rate in 2015 with less precipitation was higher than in 2016. Since falling of leaf litter is affected by environmental factors such as temperature, precipitation, photoperiod, and $CO_2$ during the period attached foliage, the leaf fall pattern and nitrogen resorption differed year by year depending on the species. If we quantify the fall phenomena of deciduous trees and analyze them according to various conditions, we can predict whether the changes in leaf fall timing and speed due to climate change will prolong or shorten the growth period of trees. In addition, it may be possible to consider how this affects their nutrient use strategy.

• Radiation Oncology Journal
• /
• v.20 no.1
• /
• pp.41-52
• /
• 2002

Purpose : 3D conformal radiotherapy, the optimum dose delivered to the tumor and provided the risk of normal tissue unless marginal miss, was restricted by organ motion. For tumors in the thorax and abdomen, the planning target volume (PTV) is decided including the margin for movement of tumor volumes during treatment due to patients breathing. We designed the respiratory gating radiotherapy device (RGRD) for using during CT simulation, dose planning and beam delivery at identical breathing period conditions. Using RGRD, reducing the treatment margin for organ (thorax or abdomen) motion due to breathing and improve dose distribution for 3D conformal radiotherapy. Materials and Methods : The internal organ motion data for lung cancer patients were obtained by examining the diaphragm in the supine position to find the position dependency. We made a respiratory gating radiotherapy device (RGRD) that is composed of a strip band, drug sensor, micro switch, and a connected on-off switch in a LINAC control box. During same breathing period by RGRD, spiral CT scan, virtual simulation, and 3D dose planing for lung cancer patients were peformed, without an extended PTV margin for free breathing, and then the dose was delivered at the same positions. We calculated effective volumes and normal tissue complication probabilities (NTCP) using dose volume histograms for normal lung, and analyzed changes in doses associated with selected NTCP levels and tumor control probabilities (TCP) at these new dose levels. The effects of 3D conformal radiotherapy by RGRD were evaluated with DVH (Dose Volume Histogram), TCP, NTCP and dose statistics. Results : The average movement of a diaphragm was 1.5 cm in the supine position when patients breathed freely. Depending on the location of the tumor, the magnitude of the PTV margin needs to be extended from 1 cm to 3 cm, which can greatly increase normal tissue irradiation, and hence, results in increase of the normal tissue complications probabiliy. Simple and precise RGRD is very easy to setup on patients and is sensitive to length variation (+2 mm), it also delivers on-off information to patients and the LINAC machine. We evaluated the treatment plans of patients who had received conformal partial organ lung irradiation for the treatment of thorax malignancies. Using RGRD, the PTV margin by free breathing can be reduced about 2 cm for moving organs by breathing. TCP values are almost the same values $(4\~5\%\;increased)$ for lung cancer regardless of increasing the PTV margin to 2.0 cm but NTCP values are rapidly increased $(50\~70\%\;increased)$ for upon extending PTV margins by 2.0 cm. Conclusion : Internal organ motion due to breathing can be reduced effectively using our simple RGRD. This method can be used in clinical treatments to reduce organ motion induced margin, thereby reducing normal tissue irradiation. Using treatment planning software, the dose to normal tissues was analyzed by comparing dose statistics with and without RGRD. Potential benefits of radiotherapy derived from reduction or elimination of planning target volume (PTV) margins associated with patient breathing through the evaluation of the lung cancer patients treated with 3D conformal radiotherapy.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.