• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.526-532
• /
• 2023

Falls are fatal accidents that occur more than 420,000 times a year worldwide. Therefore, to study patients with falls, we found the association between extrinsic injury codes and principal diagnosis S-codes of patients with falls, and developed a prediction model to predict extrinsic injury codes based on the data of principal diagnosis S-codes of patients with falls. In this study, we received two years of data from 2020 and 2021 from Institution A, located in Gangneung City, Gangwon Special Self-Governing Province, and extracted only the data from W00 to W19 of the extrinsic injury codes related to falls, and developed a prediction model using W01, W10, W13, and W18 of the extrinsic injury codes of falls, which had enough principal diagnosis S-codes to develop a prediction model. 80% of the data were categorized as training data and 20% as testing data. The model was developed using MLP (Multi-Layer Perceptron) with 6 variables (gender, age, principal diagnosis S-code, surgery, hospitalization, and alcohol consumption) in the input layer, 2 hidden layers with 64 nodes, and an output layer with 4 nodes for W01, W10, W13, and W18 exogenous damage codes using the softmax activation function. As a result of the training, the first training had an accuracy of 31.2%, but the 30th training had an accuracy of 87.5%, which confirmed the association between the fall extrinsic code and the main diagnosis S code of the fall patient.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.165-186
• /
• 2024

Despite the growing attention on artificial intelligence-based automated scoring technology as a support method for the introduction of descriptive items in school environments and large-scale assessments, there is a noticeable lack of foundational research in mathematics compared to other subjects. This study developed an automated scoring model for two descriptive items in first-year middle school mathematics using the Random Forest algorithm, evaluated its performance, and explored ways to enhance this performance. The accuracy of the final models for the two items was found to be between 0.95 to 1.00 and 0.73 to 0.89, respectively, which is relatively high compared to automated scoring models in other subjects. We discovered that the strategic selection of the number of evaluation categories, taking into account the amount of data, is crucial for the effective development and performance of automated scoring models. Additionally, text preprocessing by mathematics education experts proved effective in improving both the performance and interpretability of the automated scoring model. Selecting a vectorization method that matches the characteristics of the items and data was identified as one way to enhance model performance. Furthermore, we confirmed that oversampling is a useful method to supplement performance in situations where practical limitations hinder balanced data collection. To enhance educational utility, further research is needed on how to utilize feature importance derived from the Random Forest-based automated scoring model to generate useful information for teaching and learning, such as feedback. This study is significant as foundational research in the field of mathematics descriptive automatic scoring, and there is a need for various subsequent studies through close collaboration between AI experts and math education experts.

• Neonatal Medicine
• /
• v.16 no.2
• /
• pp.154-162
• /
• 2009

Purpose: Death is an important problem for physicians and parents in neonatal intensive care unit. This study was intended to evaluate the mortality rate, causes of death, and the change of mortality rate by year for infants admitted to the neonatal intensive care unit. Methods: We retrospectively surveyed the medical records of the infants who were admitted to the neonatal intensive care unit at Asan Medical Center and who died before discharge between 1998 and 2007. Gestational age, birth weight, gender, time to death and the underlying diseases related to the causes of infant deaths and obtained from the medical records and analyzed according to year. Results: A total of 6,289 infants were admitted and 264 infants died during the study period. The overall mortality rate was 4.2%. For very low and extremely low birth weight infants, the mortality rate was 10.6% and 21.4%, respectively. There was no significant change in the mortality rate during the study period. Prematurity related complications and congenital anomalies were the conditions most frequently associated with death in the neonatal intensive care unit. of the infant deaths 37.1% occurred within the first week of life. Conclusion: Even though a remarkable improvement in neonatal intensive care has been achieved in recent years, the overall mortality rate has not changed. To reduce the mortality rate, it is important to control sepsis and prevent premature births. The first postnatal week is a critical period for deaths in the neonatal intensive care unit.

• Neonatal Medicine
• /
• v.16 no.2
• /
• pp.172-181
• /
• 2009

Purpose: To identify trends in causative bacterial organisms for neonatal sepsis and antimicrobial susceptibilities over 10 years in one neonatal intensive care unit. Methods: We retrospectively reviewed the cases of culture-proven neonatal sepsis between January 1998 and December 2007. The 10-year period was divided into two phases (phase I, 1998-2002; phase II, 2003-2007) to distinguish the differences during the entire period. Results: Total 350 episodes of neonatal sepsis were identified in 315 neonates. The common pathogens of early-onset sepsis were S. epidermidis, S. aureus, P. aeruginosa, and E. cloacae in phase I, and S. epidermidis and E. cloacae in phase II. In cases of late-onset sepsis, coagulase negative Staphylococcus, S. aureus, and K. pneumoniae were isolated frequently in both phases. The incidence of sepsis caused by multi-drug resistant organisms decreased with strict infection control. Gram positive organisms showed 0-20% susceptibility to penicillin, ampicillin, and cefotaxime in both phases. Sensitivity to amikacin for Enterobacter spp. increased, whereas P. aeruginosa showed decreased sensitivity in phase II. Between 50% and 60% of other gram negative bacteria, except P. aeruginosa, were susceptible to cefotaxime in phase II in contrast to phase I. Greater than 80% of gram negative bacteria were sensitive to imipenem except P. aeruginosa and ciprofloxacin in both phases. Conclusion: The trend in causative microorganisms and antimicrobial susceptibilities can be used as a guideline for selection of appropriate antibiotics. A particular attention should be paid to infection control, especially to reduce sepsis caused by multi-drug resistant organisms.

• Journal of Aquaculture
• /
• v.11 no.4
• /
• pp.573-580
• /
• 1998

Red spotted grouper, Epinephelus akaara is distributed in the south and west coasts of Korea. The natural stocks of the fish are decreasing sharply year by uear because of reckless overfishing. This research was carried out to understand general informations on maturation, sex composition and sex-reversals of the fish. Annual fishing uields of red spotted grouper in the castal area of Byonsan Peninsular of Kora decreased over 10% from 1992 to 1994. The main fishing season was from May to July with fishing gear of Hand-lines. Gonadosomatic index (GSI) and condition factor were highest on early and late July, respectively, thus main spawning reriod was assumed from late July to early August. The relationship between total length (X) and body weight (Y) for wild adults was represented as a regression, Y=$0.0169X^{2.9705}$, ($r^2$=0.96). Frequency of sex of wild red spotted gouper showed that the number of female below 38cm in total length was more than that of male, and hermaphrodite mainly occurred from 28cm to 32cm in total length the frequency of male and female were almost same. Also hermaphrodite occurred mainly between 25~29cm. Sex reversal ration of the adults reared in a tank for a year with different sexual compositions revealted that the frequency of female reversed from male was more than that of male reversed from female at 1:1 and 1:2 stocking densities of female and male, respectively. Also, about 20% of female was reversed to male when all females were reared. And the size of the fish reversed to male was larger than that of non-reversed female.

• Journal of Ginseng Research
• /
• v.26 no.2
• /
• pp.89-95
• /
• 2002

We screened biotic and abiotic preventative,i(preventers) from natural resources to prevent the rusty phenomenon in ginseng roots. To select preventatives(preventers), soil microbes such as Agrobacterium and certain microbes isolated from the rusty ginsengs and the soil in which the rusty ginsengs were planted and used. It is also performed with germination tests of the seeds of Latuca Sativa L. We identified that how selected preventatives(preventers) effect the germination of ginseng seeds. Furthermore, how these influence on the rusty phenomenon and the growth of 1 -year-old ginsengs treated in the pavement. The final preventatives; ICPE-C1$\sub$05/, ICPE-P$\^$107/ were effective in not only the growth of ginseng, but also inhibition of the rusty phenomenon. Moreover, we selected abiotic soil improvers; called P, R, and W, respectively; to promote the effects of preventatives. R and W was excellented among choring improvers. The germination rate of 2-year-old ginsengs treated with ICPE-C$\sub$105/P, and ICPE-P$\sub$107/P was the highest under the effects of naturally selected preventatives mixing with abiotic soil improvers. All treat which was compounding preventers & improvers were so excellented of growth ginseng. Especially treats of ICPE-C$\sub$105/R and ICPE-P$\sub$107/R showed growth increased of each 67.3% and 52.7% As well, the growth of ginseng was the highest in the treatment of ICPE-C$\sub$105/R, and ICPE-P$\sub$105/R. Though rusty of rate was emerged 35% in control, preventers ICPE-C$\sub$105/R and ICPE-P$\sub$107/R were emerged 5.3%. It was affirmed effective of preventer. On the other hands, amounts of ginsenoside treated with preventatives showed to be changed. The ginsenoside was increased to 14.2% with treatment with ICPE-P$\sub$107/R which is highest among groups compared to control, and ICPE-C$\sub$105/P was increased to 5.0%. To sum up with total results, it is judged that biotic preventatives (ICPE-C$\sub$105/R, and ICPE-P$\sub$107/R) which we created improve both a high yield of ginseng and the inhibition of the rusty phenomenon. phenomenon.

• Journal of Embryo Transfer
• /
• v.26 no.1
• /
• pp.65-70
• /
• 2011

This study was conducted to investigate the survival rate of AndroMed and Tris-egg yolk extender for cryopreservation of Korean Native Bull Semen (Chick Cow). Semen was collected from a Korean Native Bull Semen over 3 year's old. The semen was diluted 1:1 by AndroMed and Tris-egg yolk extender. The pellet was diluted to final sperm concentration of $5{\times}10^7$ cell/ml by doubling in every 10 minutes at $4^{\circ}C$ cold chamber. The semen was equilibrated for 1 hrs at cold chamber and packed to 0.5 ml straw. The semen straws were located above 5 cm of liquid nitrogen for 5 minutes. And then the frozen straw was plunged to LN2. The presented straws were examined the viability and motility after thawed at $37^{\circ}C$ water bath. The survival rates was significantly higher (p<0.05) in Tris-egg yolk extender than AndroMed extender ($89.7{\pm}19.8$ vs. $73.4{\pm}11.2$). However, motility was no significant differences ($78.4{\pm}18.7$ vs. $67.9{\pm}14.6$). Survival rate in time of equilibration between visual and CASA program had higher in 2 h ($86.33{\pm}9.4$ vs. $92.32{\pm}12.4$) than in 5 h ($78.20{\pm}7.8$ vs. $88.28{\pm}13.1$) 15 h ($65.24{\pm}6.6$ vs. $76.48{\pm}17.3$) 20 h ($56.26{\pm}4.6$ vs. $67.73{\pm}18.4$). The development rates to cleavage was higher in Tris-egg yolk extender than AndroMed extender (82.2% vs. 81.7%). Similarly, the development rates to blastocyst was significantly higher (p<0.05) in Tris-egg yolk extender than AndroMed extender (42.3% vs. 29.6%). In conclusion, the obvious impact of this study will be its practical application to improve viability and fertilizing ability of cryopreserved spermatozoa used for in vitro fertilization (IVF) and AI, Which in turn will be beneficial to animal genetic resources conservation.

• Korean Journal of Animal Reproduction
• /
• v.24 no.2
• /
• pp.209-216
• /
• 2000

This study was carried out to investigate the effects of breed, age of boar, season, parity and mating system on boar semen characteristics and fertilizing capacity. A total of 4181 sows and 199 boars of Durocs (D), Landraces (L), and Yorkshires (Y) were used for this experiment at Darby Artificicial Insemination Center from 1996 through 1999. Semen volume per ejaculate was largest in Landrace (266.8 $m\ell$), followed by Yorkshire, and was smallest in Duroc. Sperm motility did not show significant differences among the above breeds. Sperm concentration was lowest in Landrace (4.7$\times$10$^{9}$ sperm/$m\ell$) and was highest in Duroc (5.7$\times$10$^{9}$ sperm/$m\ell$). Semen volume per ejaculate according to the age of boars was largest at the age of 2 years, followed by the age of 4 and 3 years, and was smallest at the age of I year. Semen volume per ejaculate according to the season in boars was largest in winter (228.6 $m\ell$), followed by autumn and summer, and was smallest in spring. Sperm concentration was highest in spring (5.9$\times$10$^{9}$ sperm/$m\ell$), followed by summer and winter, and was lowest in autumn. The average litter weight at birth did not show any differences according to the mating type. But the number of pigs born alive per litter was largest (9.5 pigs) in the natural mating ＋ artificial insemination group, followed by the artificial insemination group (9.2 pigs), and was smallest (8.9 pigs) in the natural mating group (P＜0.01). The average litter weight at birth and number of pigs born alive per litter did not show any differences between the natural mating and artificial insemination. The L (♀)$\times$Y (♂) and L (♀)$\times$L (♂) matings show $\varepsilon$ d higher average litter weight at birth and number of pigs born alive per litter than the Y (♀) $\times$ Y (♂) and Y (♀) $\times$ L (♂) matings. The pigs in the 2~6th parities had higher average litter weight at birth and number of pigs born alive per litter than those in the 1 st and 7~9th parities.

• Journal of Nutrition and Health
• /
• v.42 no.6
• /
• pp.577-595
• /
• 2009

This study aimed to reanalyze energy and nutrient intakes of 2007 Korean Nutrition and Health Examination Survey (KNHANES) using CAN-Pro 3.0, a commonly used nutrient analysis software in Korea. Food items and their codes were selected from 2007 KNHANES dietary intake file and converted to food codes of CAN-Pro 3.0 nutrient database (NDB). Of the 1,324 total food items, 1,155 items were converted by direct matching, 123 items were matched using other items in CAN-Pro 3.0 NDB and 42 items were matched using external sources. Consumption frequencies of items converted by direct matching contributed 94.5% of total consumption. Nutrient intakes of 4,091 participants of 2007 KNHANES, over 1 year old, were recalculated using CAN-Pro 3.0 NDB and compared with intakes in 2007 KNHANES dietary intake file. Intakes for energy and all nutrients except protein and Vitamin C calculated by two NDBs were significantly different by paired t-test (p < 0.001), but significantly correlated by Pearson' correlation coefficients (p < 0.001). Percent differences between the NDBs ranged from 0.3% to 15.1%, low for protein, energy, vitamin C, iron, vitamin B$_2$ (below 5%) but high for phosphorus, retinol, vitamin A, and $\beta$-carotene (over 10%). Age group, sex, and their interactions significantly influenced six nutrients (p < 0.05). Intake levels of zinc, vitamin B6, vitamin E, folate and cholesterol were not available in 2007 KNHANES but were calculated by CAN-Pro 3.0. Mean intake levels of zinc, vitamin B$_6$, vitamin E, and folate by age and sex groups revealed that some groups had mean levels below RI (Recommended Intake) or AI (Adequate Intake) levels. Intake level of cholesterol was higher than the recommended level (below 300 mg/day) in some groups, especially males. Results of the present study indicate the need for comparable and more comprehensive NDB to be used for dietary assessment of KNHANES and other researches. More rigorous evaluation of nutrients which have not been reported in KNHANES is needed.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.