• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.227-249
• /
• 2003

Prediction of corporate failure using past financial data is a well-documented topic. Early studies of bankruptcy prediction used statistical techniques such as multiple discriminant analysis, logit and probit. Recently, however, numerous studies have demonstrated that artificial intelligence such as neural networks can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. In building neural network model, the selection of independent and dependent variables should be approached with great care and should be treated as model construction process. Irrespective of the efficiency of a teaming procedure in terms of convergence, generalization and stability, the ultimate performance of the estimator will depend on the relevance of the selected input variables and the quality of the data used. Approaches developed in statistical methods such as correlation analysis and stepwise selection method are often very useful. These methods, however, may not be the optimal ones for the development of neural network model. In this paper, we propose a genetic algorithms approach to find an optimal or near optimal input variables fur neural network modeling. The proposed approach is demonstrated by applications to bankruptcy prediction modeling. Our experimental results show that this approach increases overall classification accuracy rate significantly.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.17 no.1
• /
• pp.1-6
• /
• 2011

The underlying principle of environmental conservation and restoration is to receive continuous services from nature. In this context, the basic objective of oil spill response and recovery activities is to allow affected residents to retain sustainability of their daily livelihood and productive environment. Hence, monitoring the status of socio-economic impact and the extent of restoration is an important parameter in the restoration effort to repair the damaged functions of environmental services with oil spill accident. However, assessment of socio-economic impact poses investigators with much difficulties in selecting the most appropriate approaches because the process often involves various stakeholders, directly and indirectly. Moreover, the analyses and interpretation of the results also pose a great challenge. The present study monitored fisheries and tourism numbers which were considered as major local socio-economic indicators of living and production environment affected by M/T Hebei Spirit oil-spill accident. This monitoring was conducted by examining the published papers and statistical reports. This was supplemented by surveying how the local residents actually felt about the damage and recovery for the first time in Korea. The results showed that the rate of the recovery was about 40~50 %, and the rate of the recovery seemed to be slowed or decreased. However, what the local residents actually felt was 2~10 points less than the literature surveys and statistical reports. These results suggested limits to using only the literature and statistical surveys for the traditional socio-economic impact assessment. The study also showed the need to include in the impact assessment process what and how the local residents actual feel about the oil spill damage and recovery process.

• The Journal of Korean Academy of Prosthodontics
• /
• v.43 no.5
• /
• pp.671-683
• /
• 2005

Statement of problem: The most commonly reported problem associated with dental implant restoration is the loosening of the screws. Purpose: This study compared the efficacy of an implant system incorporating an anti-rotational locking sleeve(Anti-Rotating Inner Post Screw System(ARIPS-system)) with other, traditional implant systems as a means of minimizing vibration loosening. Materials and methods: Three implant systems were examined; the conventional external hex type, the ARIPS-system, and the internal taper type implant system 30 specimens(10 samples per group)were fabricated and each abutment screw was secured to the implant future with 32Ncm of torque force and loosening torque was measured using a Torque Gauge. The procedure was repeated 3 times, recording initial loosening torque each time. The re-tightened abutment screw was subjected to a cyclic load having a maximum forte of 200N and minimum of 20N at 2Hz over a period of 12,600 cycles. after which the loosening torque was measured. Measured values were calaulated for statistical analysis. Analysis of measured value was performed by 3 methods: (i) as a percentage average of the initial 3 loosening-torque values(initial loosening value) to the tightening torque of 32Ncm, (ii) as a percentage of the loosening torque value after a load of 200N(experimental value) to the initial loosening value, and (iii) as a percentage of the experimental value to the 32Ncm of tightening torque. The analyses shows the amount of initial loosening at the screw, loosening by repetitive load and the the final loosening value. Results: The results of this study were as follows (1) Percentage of initial loosening value to tightening-torque was increased in order of external hex, ARIPS-system and internal taper and all values between each groups showed statistical significance (p<0.05). (2) Percentage of experimental value to initial loosening value was increased in order of external hex, ARIPS-system and internal taper. Value of internal taper showed significant difference with those of external hex and ARIPS-system (p<0.05). (3) Percentage of experimental value to tightening torque was increased in order of external hex, ARIPS-system and internal taper and all values between each groups showed statistical significance (p<0.05). Conclusion: The results of the analysis of the final loosening level value, which are closely correlated to clinical use, show that the ARIPS-system can be a useful means of minimizing abutment screw loosening when compared to the external hex type system. Although further clinical studies need to be made, the ARIPS-system should be considered to maximize the long-term success of the implant prosthesis.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.13 no.2
• /
• pp.88-116
• /
• 2009

Background : EBM (the evidence based medicine) is the direction of the development for oriental medicine. The pulse meter-analyzer is the important part to standardize the pulse diagnosis. When we set up the direction of the study on the pulse meter-analyzer, the awereness about the pulse meter and analyzer of the clinical oriental medical doctors as consumers is very important. Objectives : In order to prepare for the mutual study and the export strategy on the pulse meter-analyzer of Korea and China, the attitude of the study and the grasp of the awereness about the pulse meter-analyzer of the Chinese medical doctors are very important. Methods : We developed the several items as the important factor of the development of the pulse meter and analyzer. They were translated by chinese medical doctor. The investigation for demend was conducted during 3 months in Guangzhou City, Guangdong Province, China. The results of the investigation was done the statistical method of frequency analysis, Chi-squared test, correspondence analysis. Results : The most important differentiation of symptom is the symptom of JANG-BU(臟腑). The method of the utility in the pulse diagnosis is Chon-Gu (寸口) pulse diagnosis and the research on Chon-Kwan-Cheok(寸關尺) is the most important measurement factor. And the typical the old pulse is the little-fine weak pulse. The pulse meter-analyzer is most suitable to the diagnosis of the hypertension and the arteriosclerosis. Conclusion : The development of the pulse analyzer including the requests of Korean and Chinese medical doctors is very important. Specially the researches on the influence factors of the traditional diagnosis and the environment of the measurement are important for developing the pulse analyze.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.26 no.2
• /
• pp.58-67
• /
• 2013

Objective : Allergic rhinitis(AR) is an inflammation or irritaion of nasal mucosa. Usually, serum cytokine is regarded as one of the most important factors in AR. Coisis semen have been used for the diseases in digestive organs in traditional chinese medicine. Nowaday, there were some studies reported about the effects of coisis semens on serum cytokine. However the results of theses studies were varies, and moreover there was no study which have used AR animal model. Therefore this study is aimed to determine therapeutic effects of coisis semen extract by observing changes of serum cytokine(IgE, TNF-${\alpha}$, IL-$1{\beta}$, IFN-${\gamma}$ and IL-13) with AR animal model. Methods : Thirty BALB/c mice were divided into six groups : Normal group, Control group, sample I, sample II, sample III, sample IV. Except for Normal group, all the mice in other 5 groups were sensitized intraperionealy by 0.1% ovalbumin solution three times at intervals of one week. Then intranasal sensitization was performed by diffusing 0.1% ovalbumin solution three times at intervals of two days. Normal group were used Normal Saline instead of ovalbumin solution. After the first day of study, sample I, sample II, sample III, and sample IV were orally administrated coisis semen extract by 100mg/kg, 200mg/kg, 500mg/kg, and 1g/kg respectively for 28days. Then, the changes of serum IgE, TNF-${\alpha}$, IL-$1{\beta}$, IFN-${\gamma}$ and IL-13 were observed in 6 groups. We used the statistical methods of ANOVA, post hoc by duncun, and Kruskal-Wallis test(p<0.05) Results : There were statistical changes in IgE and TNF-${\alpha}$. But, there were no statistical changes in IL-$1{\beta}$, IL-13 and IFN-${\gamma}$. Conclusions : According to above results, it is supposed that coisis semen extract has not some significant effects on cytokine of AR animal model. There was no evidence for using coisis semen in relieving symptoms of allergic rhinitis.

• Journal of the Korean Society of Radiology
• /
• v.17 no.7
• /
• pp.1025-1031
• /
• 2023

We aimed to evaluate the radiation dose and image quality by changing the Scout view voltage in low-dose chest CT (LDCT) and applying scan parameters such as AEC (auto exposure control) and ASIR (adaptive statistical iterative reconstruction) to find the optimal protocol. Scout view voltage was varied at 80, 100, 120, 140 kV and after measuring the dose 5 times using the existing low-dose chest CT protocol, the appropriate kV was selected for the study using the Dose report provided by the equipment. After taking a basic LDCT shot at 120 kV, 30 mAs, ASIR 50% was applied to this condition. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were assessed by measuring Background noise (B/N). For dose comparison, CTDI_vol and DLP provided by the equipment were compared and analyzed using the formulas. The results indicated that the protocol of scout 140 + LDCT + ASIR 50 + AEC reduced radiation exposure and improved image quality compared to traditional LDCT, providing an optimal protocol. As demonstrated in the experiment, LDCT screenings for asymptomatic normal individuals are crucial, as they involve concerns over excessive radiation exposure per examination. Therefore, applying appropriate parameters is important, and it is expected to contribute positively to the public health in future LDCT based health screenings.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.6
• /
• pp.543-551
• /
• 2023

As climate change continues to prompt an increasing demand for advancements in disaster and safety management technologies to address abnormal high water temperatures, typhoons, floods, and droughts, sea surface temperature has emerged as a pivotal factor for swiftly assessing the impacts of summer harmful algal blooms in the seas surrounding Korean Peninsula and the formation and dissipation of cold water along the East Coast of Korea. Therefore, this study sought to gauge predictive performance by leveraging statistical methods and deep learning algorithms to harness sea surface temperature data effectively for marine anomaly research. The sea surface temperature data employed in the predictions spans from 2018 to 2022 and originates from the Heuksando Tidal Observatory. Both traditional statistical ARIMA methods and advanced deep learning models, including long short-term memory (LSTM) and gated recurrent unit (GRU), were employed. Furthermore, prediction performance was evaluated using the attention LSTM technique. The technique integrated an attention mechanism into the sequence-to-sequence (s2s), further augmenting the performance of LSTM. The results showed that the attention LSTM model outperformed the other models, signifying its superior predictive performance. Additionally, fine-tuning hyperparameters can improve sea surface temperature performance.

• Advances in Traditional Medicine
• /
• v.1 no.2
• /
• pp.14-20
• /
• 2000

This study was designed to investigate the effect of dietary Platycodon grandiflorum on plasma glucose and lipid metabolism in $KK-A^y$ mice and STZ-induced diabetic rats. Both plasma triglyceride and plasma cholesterol levels in STZ-induced diabetic rats were significantly decreased by dietary Platycodon grandiflorum feeding for 4 weeks compared to those of control rats, but there were no marked differences in $KK-A^y$ mice. However, for plasma glucose values, Platycodon grandiflorum feeding resulted in a significant decrease in both STZ-induced diabetic rats and $KK-A^y$ mice. Also, dietary Platycodon grandiflorum slightly decreased the postprandial glucose level at 30 and 60 mins during oral glucose tolerance test in $KK-A^y$ mice. Although there was no statistical significance, the fasting plasma insulin levels of Platycodon grandiflorum dieted $KK-A^y$ mice tended to decrease when compared to that of control mice. Therefore, the present results suggested that dietary Platycodon grandiflorum may have a beneficial effect on preventing hypercholesterolemia and hyperlipidemia.

• The Korean Journal of Food And Nutrition
• /
• v.21 no.4
• /
• pp.536-544
• /
• 2008

The principal objectives of this study were to identify diet problems associated with dining out, and to suggest dining out strategies for groups with diet problems. The data collected from adults(all over 20 years old) from the third Korea National Health and Nutrition Examination Survey III(KNHANES III), conducted in 2005, were used in this study. A total of 6,497 data were included in our statistical analyses, using SPSS 14.0. The results of this study demonstrated that there were significant differences in dining out frequency between different genders(p<0.001), ages(p<0.001), and economic status (p<0.001). With the crosstabulation analysis using the Chi-square statistics, the middle class males aged $20{\sim}29$(p<0.05), and lower class females aged 65 and over evidenced different degrees of compliance with the following guidelines. 'Eat a variety of foods' varied by frequency of dining out. In addition, the degree of compliance with the guidelines 'Increase activity and eat an adequate amount of foods for weight control', 'Enjoy the Korean traditional diet', and 'Control consumption of alcohol' also differed by dining out frequency in certain populations. With these results, dining out strategies were suggested for the groups with diet problems associated with dining out.

• Water Engineering Research
• /
• v.1 no.2
• /
• pp.95-105
• /
• 2000

A method is presented which enables easily the computation of the suspended sediment discharge as the mean sediment concentration and mean flow velocity. This method has significant advantages over the traditional method, which principally depend on a set of measured concentration data. The method is based on both a new sediment concentration and mean sediment concentration equations which have been derived from the entropy concept used in statistical mechanics and information theory: (1) The sediment concentration distribution equations derived, are capable of describing the variation of the concentration in the vertical direction. (2) The mean concentration equation derived, is capable of calculating easily the mean concentration by using only one measured concentration in open channel. The present study mainly addresses the following two subjects : (1) new sediment concentration and mean sediment concentration equations are derived from the entropy concept : (2) An efficient and useful method of suspended sediment-discharge measurements is developed which can facilitate the estimation of suspended sediment-discharge in open channel. Flume and laboratory data are used to carry out the research task outlined above. An efficient method for determining the suspended sediment-discharge in the open channel has been developed. The method presented also is efficient and applicable in estimating the sediment transport in rivers and the sediment deposit in the reservoirs, and can drastically reduce the time and cost of sediment measurements.