• 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.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.16 no.4
• /
• pp.285-296
• /
• 2014

The impacts of high temperature and drought were studied on the seedlings of three families (superiorgangwon74, intermediate-gangwon77 and inferior-gangwon132) of P. densiflora which had been selected by the based on the growth indexes of 32-year-old. The seedlings were grown in controlled-environment growth chambers with combinations of four temperatures ($-3^{\circ}C$, $0^{\circ}C$, $+3^{\circ}C$ $+6^{\circ}C$; based on the monthly average for 30 years in Korea) and two water conditions (control, drought). The growth performance, photosynthetic parameters and photosynthetic pigment contents were measured at every 30 days under four temperatures and drought condition, and the end of each treatment. The superior family showed higher relative diameter at root collar growth rate and the dry weight than intermediate and inferior family in all treatments. Under elevated temperature and drought condition, growth rate was decreased, and seedlings showed lower growth rate than that of control in three families under low temperature. Photosynthetic rate, stomatal conductance and transpiration rate of three families decreased with the increase of temperature and drought condition, and that of seedlings under low temperature was lower than control. But under elevated temperature and drought condition, water use efficiency increased in three families. Photosynthetic pigment contents of leaves decreased under the increase of temperature and drought condition, but chlorophyll a/b ratio increased with the increase of temperature and drought condition in three families. The superior family showed higher total chlorophyll content than intermediate and inferior family in all treatments. In conclusion, P. densiflora is under changed temperature and drought condition, growth was decreased, seedlings more affected in elevated temperature than that of decreased temperature. The increase in monthly average temperature in Korea of more than $6^{\circ}C$, P. densiflora seedling growth in depending on region may decrease. In this study, the superior family(gangwon74) showed more excellent growth and physiological responses than intermediate (gangwon77) and inferior(gangwon132) family under changes temperature and drought.

• Korean Journal of Poultry Science
• /
• v.15 no.3
• /
• pp.211-218
• /
• 1988

Data on egg number from time of first lay to 71 week of age were obtained from samples of single comb white leghorn breeder and brown layer breeder populations which were raised at manny breeding Co. These data were used to estimate the heritabilities of age at sexual maturity, early egg number, residual egg number and annual egg number. Also, the genetic correlation coefficients between these traits were estimated and selection efficiencies of each segment in early part record were estimated by use of the heritabilities and generic correlations. The estimated heritabilities and standard errors in two lines(W and B) were $0.30\pm0.07$ and $0.33\pm0.08$ at early records, $0.19\pm0.06$ and $0.18\pm$0.05 at residual records and $0.37\pm0.09$ and $0.49\pm0.10$ at time of first lay. Those at annual records were $0.24\pm0.06$ equally. The estimated correlation coefficients and standard errors between early record and annual record were $0.76\pm0.08$ and $0.77\pm0.07$. Those between early record and residual record were $0.46\pm0.15$ and $0.39\pm0.16$ respectively. At improving annual egg production per year, selection based on early part record(SM to 40 week of age) would be 69% more efficient than on annual record in line W and 80% more efficient than on annual record in line B. But, if it were considered that egg weight decreased due to sexual maturity and cost for data collection, use of selected segment from 35~40week of age in line W and from 31~40 week of age in line B would be desired in spite of a. small loss in relative selection efficiency. The generation interval would not be shortened.

• Journal of Plant Biotechnology
• /
• v.38 no.4
• /
• pp.285-292
• /
• 2011

In plants, heteroblasty reflects the morphological adaptation during leaf development according to the external environmental condition and affects the final shape and size of organ. Among parameters displaying heteroblasty, leaf index is an important and typical one to represent the shape and size of simple leaves. Leaf index factor is eventually determined by cell proliferation and cell expansion in leaf blades. Although several regulators and their mechanisms controlling the cell division and cell expansion in leaf development have been studied, it does not fully provide a blueprint of organ formation and morphogenesis during environmental changes. To investigate genes and their mechanisms controlling leaf index during leaf development, we carried out molecular-genetic and physiological experiments using an Arabidopsis mutant. In this study, we identified macrophylla (mac) which had enlarged leaves. In detail, the mac mutant showed alteration in leaf index and cell expansion in direction of width and length, resulting in not only modification of leaf shape but also disruption of heteroblasty. Molecular-genetic studies indicated that mac mutant had point mutation in ROTUDIFOLIA3 (ROT3) gene involved in brassinosteroid biosynthesis and was an allele of rot3-1 mutant. We named it mac/rot3-5 mutant. The expression of ROT3 gene was controlled by negative feedback inhibition by the treatment of brassinosteroid hormone, suggesting that ROT3 gene was involved in brassinosteroid biosynthesis. In dark condition, in addition, the expression of ROT3 gene was up-regulated and mac/rot3-5 mutant showed lower response, compare to wild type in petiole elongation. This study suggests that ROT3 gene has an important role in control of leaf index during leaf expansion process for proper environmental adaptation, such as shade avoidance syndrome, via the control of brassinosteroid biosynthesis.

• Journal of agriculture & life science
• /
• v.51 no.2
• /
• pp.117-126
• /
• 2017

Hanwoo young bulls are selected based on performance test using the weight at 12 months and pedigree index comprising marbling score. Pedigree index was not based on the progeny tested data but the breeding value of the proven bulls; resulting a lower accuracy. The progeny testing of the young bulls was categorized into testing at farm and at the test station. The farm tested data was difficult to compare with those from test station data. Farm tested bulls had different slaughter ages than those for test station bulls. Therefore, this study had considered a different age at slaughter for respective records on ultrasound traits. Records on body weight at 12 months, ultrasound measures at 12 and 24 months(uIMF, uEMA, uBFT, and uRFT), and carcass traits(CWT, EMA, BFT, and MS) were collected from steers and bulls of Hanwoo national improvement scheme between 2008 and 2013. Fixed effects of batch, test date, test station, personnel for measurement, personnel for judging, and a linear covariate of weight at measurement were fitted in the animal models for ultrasound traits. The ranges of heritability estimates of the ultrasound traits at 12 and 24 months were 0.21-0.43 and 0.32-0.47, respectively. Ultrasound traits at 12 and 24 months between similar carcass traits was genetically correlated at 0.52-0.75 and 0.86-0.89, respectively.

• Journal of Animal Science and Technology
• /
• v.49 no.5
• /
• pp.569-576
• /
• 2007

receptor(MC4R) gene and carcass traits was examined in randomly selected commercial pigs. A porcine MC4R gene was genotyped for Asp298Asn(nt. 892G>A) by polymerase chain reaction-restriction fragment length polymorphism(PCR-RFLP). A total of three genotypes, A/A, A/G, and G/G, were found with 28.8, 22.8, and 48.4% frequencies, respectively. In the whole population, pigs containing 892A/- showed significantly higher marbling score than those of homozygotes G/G(P<0.05). Two homozygotes, A/A and G/G showed lower in meat color score but higher in water holding capacity than those of heterozygotes A/G(P<0.01). However, the carcass weight of the barrows containing wild type -/G was significantly higher(i.e. more than 2.5kg) than those of homozygotes A/A(P<0.05). The effects of each genotype on carcass traits in the gilts were similar to those of the whole population, but not in barrows, suggesting an unknown sex-related effect on carcass traits. This study suggested that the genotype MC4R A/- could improve the meat quality in the commercial pig production. However, since the genetic polymorphism of MC4R gene differentially affected the carcass traits in sex-related manner, therefore, both parameters, the sex and genotype, should be considered for marker-assisted selection in commercial pig production.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.16 no.4
• /
• pp.368-383
• /
• 2014

Climate change is expected to affect population density, phenology, distribution, morphological traits, reproduction and genetics of insects, and even in the extinction of insects. To develop novel research subjects for predicting climate change effect, basic information about biological and ecological data on insect species should be compiled and reviewed. For this reason, this study was conducted to collect the biological information on insect pests that are essential for predicting potential damage caused by insect pests in future environment. In addition, we compared domestic and foreign research trends regarding climate change effect and suggested future research subjects. Domestic researchers were rather narrow in the subject, and were mostly conducted based on short-term monitoring data to determine relationship between insects and environmental variables. On the other hand, foreign researches studied on various subjects to analyze the effect of climate change, such as changes in distribution of insect using long-term monitoring data or their prediction using population parameters and models, and monitoring of the change of the insect community structure. To determine change of the phenology, distribution, overwintering characteristics, and genetic structures of insects under climate change through development of monitoring technique, in conclusion, further researches are needed. Also, development of population models for major or potential pests is important for prediction of climate change effects.

• Journal of Embryo Transfer
• /
• v.30 no.2
• /
• pp.109-114
• /
• 2015

Cryopreservation of boar semen is continually researched in reproductive technologies and genetic resource banking in breed conservation. For evaluating the boar semen quality, sperm motility (MOT) is an important parameter because the movement of spermatozoa indicates active metabolism, membrane integrity and fertilizing capacity. Various researches have been trying to improve the quality of semen post-thawed in boar. Recently, polymorphism (g.358A>T) of cluster-of-differentiation antigen 9 (CD9) gene reported to be significant association with MOT. Also, CD9 gene was expressed in the male germ line stem cells is crucial for sperm-egg fusion, and was therefore selected as candidate gene for boar semen. This study was conducted to evaluate the pig SNP (g.358A>T) of CD9 gene as a positional controlling for semen parameters of post-thawed boar semen. To results, the g.358A>T SNP of the CD9 gene was significantly associated with the traits such as MOT, curve linear velocity, straight line velocity, average path velocity and amplitude of lateral head displacement. Particularly, the g.358A>T SNP significantly has the highest association with MOT and animals with AA genotype (p<0.001). Therefore, we suggest that the g.358A>T in the intron 6 region of the porcine CD9 may be used as a molecular marker for Duroc boar Post-thawed semen quality, although its functional effect was not defined yet.

• Development and Reproduction
• /
• v.12 no.2
• /
• pp.117-124
• /
• 2008

The efficient strategies to cope with unpredictable and/or harmful environmental changes have been developed by every organism in order to ensure its survival and continuity of it's own species. As a results, all living things on earth maintain dynamically internal stability via a process termed 'homeostasis' among physiological parameters despite of external environment changes. Stress is an emotional and physical response to threat homeostasis. Stress may have not only transient but rather permanent effect on the organism; recent evidence clearly show that prenatal stress could organize or imprint permanently physiological systems without any change in genetic codes, a process known as 'epigenetic programming'. In this review, a series of reproduction-associated events occurred in prenatally stressed male rats such as alteration in the structure of sexually dimorphic brain regions, modification of neurotransmitter metabolism, changes in reproductive endocrine status, and finally, disorders of sexual behavior will be introduced. The fetal brain is highly sensitive to prenatal programming and glucocorticoids in particular have powerful brain-programming properties. The chronic hyperactivation of fetal brain by maternal stress-induced glucocorticoid input will provide new program via increasing the neuroplasticities. This 'increased neuroplasticities' will be the basis for the 'increased phenotypic plasticities' rendering the organism's better adaptation to environmental challenges. In conclusion, organism who experienced 'harsh' environment in his fetal life seems to give up a certain portion of reproductive competence to make good chance of survival in his future life by epigenetic (re)programming.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.33 no.3
• /
• pp.523-532
• /
• 2004

The spontaneous frequency of genetic damage and the possible relationship of this damage to dietary and nutritional variables were investigated in peripheral blood lymphocytes from 45 elderly people using sister chromatid exchange (SCE). The relationship of dietary and nutritional factors on SCE was assessed by different degrees of smoking status such as smokers (n=14), ex-smokers (n=16) and non-smokers (n=15). Significant relationship of the SCE frequency to nutrient intake of the combined subjects (n=45) was found. When cigarette smoking status was taken into account, there were negative linear relationships between SCE and fat, phosphorus or vitamin A intakes of the non-smokers as well as SCE and the dietary quality scores. There was a positive linear relationship between SCE and food frequency of meat and fish among the smokers. Use of artificial sweetners in ex-smokers of the elderly people produced a significant increase of SCE in comparison with the mean SCE for those not using sweetners. Other dietary parameters, including intake of coffee, green tea and ginseng tea, alcohol consumption, use of processed foods, and administration of vitamin pills did not show any correlation with SCE. These results suggested that dietary fat, phosphorus or vitamin A status are the major determinants of spontaneous DNA damage in lymphocytes of the elderly people.