• The Transactions of the Korea Information Processing Society
• /
• v.1 no.2
• /
• pp.225-236
• /
• 1994

Many research result conducted by neural network researchers claimed that the degree of generalization of the neural network system is higher or at least equal to that of statistical methods. However, those successful results could be brought only if the neural network was trained by appropriately sound data, having a little of noisy data and being large enough to control noisy data. Real data used in a lot of fields, especially business fields, were not so sound that the network have frequently failed to obtain satisfactory prediction accuracy, the degree of generalization. Enhancing the degree of generalization with noisy data is discussed in this study. The suggestion, which was obtained through a series of experiments, to enhance the degree of generalization is to remove inconsistent data by checking overlapping and inconsistencies. Furthermore, the previous conclusion by other reports is also confirmed that the learning mechanism of neural network takes average value of two inconsistent data included in training set［2］. The interim results of on-going research project are reported in this paper These are ann architecture of the neural network adopted in this project and the whole idea of developing on-line credit evaluation system,being intergration of the expert(resoning)system and the neural network(learning system.Another definite result is corroborated through this study that quickprop,being agopted as a learing algorithm, also has more speedy learning process than does back propagation even in very noisy environment.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.4 s.304
• /
• pp.33-42
• /
• 2005

This paper proposes a classification method for gene expression data, using membership function and neural network. The gene expression is a process to produce mRNA and protains which generate a living body, and the gene expression data is important to find out the functions and correlations of genes. Such gene expression data can be obtained from DNA 칩 massively and quickly. However, thousands of gene expression data may not be useful until it is well organized. Therefore a classification method is necessary to find the characteristics of gene data acquired from the gene expression. In the proposed method, a set of gene data is extracted according to the fisher's criterion, because we assume that selected gene data is the well-classified data sample. However, the selected gene data does not guarantee well-classified data sample and we calculate feature values using membership function to reduce the influence of outliers in gene data. Feature vectors estimated from the selected feature values are used to train back propagation neural network. The experimental results show that the clustering performance of the proposed method has been improved compared to other existing methods in various gene expression data.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.5 s.305
• /
• pp.27-34
• /
• 2005

Ventricular fibrillation(VF) is generally caused by chaotic behavior of electrical propagation in heart and may result in sudden cardiac death. In this study, we proposed a ventricular fibrillation detection algorithm based on support vector machine classifier, which could offer benefits to reduce the teaming costs as well as good classification performance. Before the extraction of input features, raw ECG signal was applied to preprocessing procedures, as like wavelet transform based bandpass filtering, R peak detection and segment assignment for feature extraction. We selected input features which of some are related to the rhythm information and of others are related to wavelet coefficients that could describe the morphology of ventricular fibrillation well. Parameters for SVM classifier, C and ${\alpha}$, were chosen as 10 and 1 respectively by trial and error experiments. Each average performance for normal sinus rhythm ventricular tachycardia and VF, was 98.39%, 96.92% and 99.88%. And, when the VF detection performance of SVM classifier was compared to that of multi-layer perceptron and fuzzy inference methods, it showed similar or higher values. Consequently, we could find that the proposed input features and SVM classifier would one of the most useful algorithm for VF detection.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.38 no.7
• /
• pp.647-656
• /
• 2014

To supplement the ISO-GUM method for the evaluation of measurement uncertainty, a simulation program using the Monte Carlo method (MCM) was developed, and the MCM and GUM methods were compared. The results are as follows: (1) Even under a non-normal probability distribution of the measurand, MCM provides an accurate coverage interval; (2) Even if a probability distribution that emerged from combining a few non-normal distributions looks as normal, there are cases in which the actual distribution is not normal and the non-normality can be determined by the probability distribution of the combined variance; and (3) If type-A standard uncertainties are involved in the evaluation of measurement uncertainty, GUM generally offers an under-valued coverage interval. However, this problem can be solved by the Bayesian evaluation of type-A standard uncertainty. In this case, the effective degree of freedom for the combined variance is not required in the evaluation of expanded uncertainty, and the appropriate coverage factor for 95% level of confidence was determined to be 1.96.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.3
• /
• pp.312-317
• /
• 2015

Seafarers can confront to evacuate from the ship with many reasons such as collision, grounding and fire accident. It believes that evacuation time from ship is very important element in order to increase survival rate in the contingency circumstance, however narrow and complex structure of ship is one of obstacle element against prompt evacuation. Taking into consideration the unique structure of ship compared to the structure of other facilities, speed of fire propagation on board ship is faster than the same size of other type facilities. Therefore, measures to prompt evacuation are required. But it comes with the behavioral constraints of the crews and passengers of the nature of operating in a complex structure with narrow vessels. Therefore, in this study, we propose a formula to be analyzed by theoretical approach and simulation methods to improve the survival rate for the crew and passenger of the ship through the ship's structural modification. We analyzed the temperature rise and visibility which are the most influential effects on the life safety in the event of fire by using a three-dimensional analysis of sight-only program Fire Dynamic Simulator (FDS) as analytical tools.

• Journal of the Korean Society of Groundwater Environment
• /
• v.7 no.2
• /
• pp.89-96
• /
• 2000

Slug tests are the most widely used field method for quantification of hydraulic conductivity of porous media. Well recovery is affected by well casing, borehole radii, screened length, hydraulic conductivity, and specific storage of porous media. In this study, a new slug tests model was developed through finite element approximation and the validity and usefulness of the model were tested in various ways. Water level fluctuation in a well under slug test and cons-equent groundwater flow in the surrounding porous medium were appropriately coupled through estimation of well-flux using an iteration technique. Numerical accuracy of the model was verified using the Cooper et al. (1967) solution. The model has advantages in simulations for monitored slug tests, partial penetration, and inclusion of storage factor. Volume coverage of slug tests is significantly affected by storage factor. Magnitude and speed of propagation of head changes from a well increases as storage factor becomes low. It will be beneficial to use type curves of monitored head transients in the surrounding porous formation for estimation of specific storage. As the vertical component of groundwater flow is enhanced, the influence of storage factor on well recovery decreases. For a radial-vertical flow around a partially penetrated well, deviations between hydraulic estimates by various methods and data selection of recovery curve are negligible on practical purposes, whereas the deviations are somewhat significant for a radial flow.

• The Korean Journal of Pesticide Science
• /
• v.19 no.4
• /
• pp.440-449
• /
• 2015

Pine wood nematode (PWN), Bursaphelenchus xylophilus is one of the most serious pests of pine tree. Trunk injection of some nematicides in tree is well known as an effective control method. However there are some limitating factors which hindering the efficacy of trunk injection in field or potted tree. In this study we suggested easy and useful alternative screening methods of nematicides against PWN. Reproduction of PWN was influenced by tree twig moisture (high reproduction in high moisture trig) and paraffin coating was 78.6% reduced moisture loss in tested twig. There were no reproduction different in up and down site from infection site of twig at 1 month after inoculation of PWN and also distance (5 and 10 cm) from inoculation site of PWN did not influence the reproduction of PWN. Numbers of reproduced PWN were higher with decreasing diameter of twig. Numbers of reproduced PWN were similar to P. thunbergii and P. densiflora. However reproduction was increased depending on high inoculation density and longer propagation period. When inoculation of PWN on cut twig injected with emamectin benzoate 2.15% EC and morantel tartrate 8% SL in trunk of Pinus thunbergii in the field, PWN number were significantly reduced than untreated control. We suggest this screening method for PWN control agents.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.2 no.3
• /
• pp.37-45
• /
• 2000

In recent years two reflection methods, i.e. GPR and seismic Impact-Echo, are usually performed to obtain the information about tunnel lining structures composed of concrete lining, shotcrete, water barrier, and voids at the back of lining. However, they do not lead to a desirable resolution sufficient for the inspection of tunnel safety, due to many problems of interest including primarily (1) inner thin layers of lining structure itself in comparison with the wavelength of source wavelets, (2) dominant unwanted surface wave arrivals, (3) inadequate measuring strategy. In this sense, seismic physical modeling is a useful tool, with the use of the full information about the known physical model, to handle such problems, especially to study problems of wave propagation in such fine structures that are not amenable to theory and field works as well. Thus, this paper deals with various results of seismic physical modeling to enable to show a possibility of detecting the inner layer boundaries of tunnel lining structures. To this end, a physical model analogous to a lining structure was built up, measured and processed in the same way as performed in regular reflection surveys. The evaluated seismic section gives a clear picture of the lining structure, that will open up more consistent direction of research into the development of an efficient measuring and processing technology.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.7
• /
• pp.1167-1179
• /
• 2020

Objective: This study was conducted to fathom the underlying mechanisms of nutrition intervention and redox sensitive transcription factors regulated by Antrodia cinnamomea fermented product (FAC) dietary supplementation in broiler chickens. Methods: Four hundreds d-old broilers (41±0.5 g/bird) assigned to 5 groups were examined after consuming control diet, or control diet replaced with 5% wheat bran (WB), 10% WB, 5% FAC, and 10% FAC. Liver mRNA expression of antioxidant, inflammatory and lipid metabolism pathways were analyzed. Prostaglandin E2 (PGE₂) concentration in each group were tested in the chicken peripheral blood mononuclear cells (cPBMCs) of 35-d old broilers to represent the stress level of the chickens. Furthermore, these cells were stimulated with 2,2'-Azobis(2-amidinopropane) dihydrochloride (AAPH) and lipopolysaccharide (LPS) to evaluate the cell stress tolerance by measuring cell viability and oxidative species. Results: Heme oxygenase-1, glutathione S-transferase, glutamate-cysteine ligase, catalytic subunit, and superoxide dismutase, and nuclear factor (erythroid-derived 2)-like 2 (Nrf2) that regulates the above antioxidant genes were all up-regulated significantly in FAC groups. Reactive oxygen species modulator protein 1 and NADPH oxygenase 1 were both rather down-regulated in 10% FAC group as comparison with two WB groups. Despite expressing higher level than control group, birds receiving diet containing FAC had significantly lower expression level in nuclear factor-kappa B (NF-κB) and other genes (inducible nitric oxide synthase, tumor necrosis factor-α, interleukin-1β, nucleotide-binding domain, leucine-richcontaining family, pyrin domain-containing-3, and cyclooxygenase 2) involving in inflammatory pathways. Additionally, except for 3-hydroxy-3-methyl-glutaryl-coenzyme A reductase that showed relatively higher in both groups, the WB, lipoprotein lipase, Acetyl-CoA carboxylase, fatty acid synthase, fatty acid binding protein, fatty acid desaturase 2 and peroxisome proliferator-activated receptor alpha genes were expressed at higher levels in 10% FAC group. In support of above results, promoted Nrf2 and inhibited NF-κB nuclear translocation in chicken liver were found in FAC containing groups. H₂O₂ and NO levels induced by LPS and AAPH in cPBMCs were compromised in FAC containing diet. In 35-d-old birds, PGE₂ production in cPBMCs was also suppressed by the FAC diet. Conclusion: FAC may promote Nrf2 antioxidant pathway and positively regulate lipid metabolism, both are potential inhibitor of NF-κB inflammatory pathway.

• Tunnel and Underground Space
• /
• v.22 no.1
• /
• pp.69-76
• /
• 2012

Theoretical backgrounds on the experimental methods of explosive welding, explosive forming and shock consolidation of powders are introduced. Explosive welding experiments of titanium (Ti) and stainless steel (SUS 304) plate were carried out. It was revealed that a series of waves of metal jet are generated in the contact surface between both materials; and that the optimal collision velocity and collision angle is about 2,100~2,800 m/s and $15{\sim}20^{\circ}$, respectively. Also, explosive forming experiments of Al plate were performed and compared to a conventional press forming method. The results confirmed that the shock-loaded Al plate has a larger curvature deformation than those made using conventional press forming. For shock consolidation of powders, the propagation behaviors of a detonation wave and underwater shock wave generated by explosion of an explosive are investigated by means of numerical calculation. The results revealed that the generation and convergence of reflected waves occur at the wall and center position of water column, and also the peak pressure of the converged reflected waves was 20 GPa which exceeds the detonation pressure. As results from the consolidation experiments of metal/ceramic powders ($Fe_{11.2}La_2O_3Co_{0.7}Si_{1.1}$), shock-consolidated $Fe_{11.2}La_2O_3Co_{0.7}Si_{1.1}$ bulk without cracks was successfully obtained by adapting the suggested water container and strong bonding between powder particles was confirmed through microscopic observations.