• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.445-453
• /
• 2002

Past and current customer behavior is the best predicator of future customer behavior. This paper introduces a procedure on personalized defection detection and prevention for an online game site. The basic idea for our defection detection and prevention is adopted from the observation that potential defectors have a tendency to take a couple of months or weeks to gradually change their behavior (i.e. trim-out their usage volume) before their eventual withdrawal. For this purpose, we suggest a SOM (Self-Organizing Map) based procedure to determine the possible states of customer behavior from past behavior data. Based on this representation of the state of behavior, potential defectors are detected by comparing their monitored trajectories of behavior states with frequent and confident trajectories of past defectors. The key feature of this study includes a defection prevention procedure which recommends the desirable behavior state for the ext period so as to lower the likelihood of defection. The defection prevention procedure can be used to design a marketing campaign on an individual basis because it provides desirable behavior patterns for the next period. The experiments demonstrate that our approach is effective for defection prevention and efficient for defection detection because it predicts potential defectors without deterioration of prediction accuracy compared to that of the MLP (Multi-Layer Perceptron) neural network.

• Preventive Nutrition and Food Science
• /
• v.13 no.4
• /
• pp.348-353
• /
• 2008

Aerobic bacterial growth on Korean pan.fried meat patties as a primary quality deterioration factor was modeled as a function of temperature to estimate microbial spoilage on a real.time basis under dynamic storage conditions. Bacteria counts in the stretch.wrapped foods held at constant temperatures of 0, 5, 10 and $15^{\circ}C$ were measured throughout storage. The bootstrapping method was applied to generate many resampled data sets of mean microbial counts, which were then used to estimate the parameters of the microbial growth model of Baranyi & Roberts in the form of differential equations. The temperature functions of the primary model parameters were set up with confidence limits. Incorporating the temperature dependent parameters into the differential equations of bacterial growth could produce predictions closely representing the experimental data under constant and fluctuating temperature conditions.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2005.05b
• /
• pp.469-472
• /
• 2005

With all ensuring the fire resistance structure as a method of setting the required cover thickness to fire, the RC is significantly affected from the standpoint of its structural stability that the compressive strength and elastic modulus is reduced by fire. Normally, the degradation of concrete member exposed to fire is largely dependent on the fire scale and fire condition. There is therefore a need to precisely predict the deterioration and fire damage of the exposed member. Thus, this work estimated the temperature distribution inside a member taking into consideration of the thermal properties by means of finite element method(FEM). The estimation results in a little higher prediction value than the experimental value in surface layer and is almost coincident with the experiment as the heating depth increase. From this work it can be known that the simulation application of FEM using the thermal properties of concrete member in high temperature gives rise to the confident prediction in the prediction of temperature distribution.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2017.05a
• /
• pp.160-162
• /
• 2017

When rubber elastomer has contact with fuel, since the component and additive having low molecular weight can flow out, the physical properties of both elastomer and fuel could be hindered. In order to predict the life of the rubber elastomer, this study is to determine the change of weight, thickness, hardness, strain, and compression set as mechanical properties of the sealant rubber O-ring, which was dependent on volume, temperature, and storage time of the contacted fuel. We also determined purity of fuel via GC analysis and measured gross heat of combution. The results could be used as a reference to evaluate the life of the rubber elastomer.

• Journal of the Korean Solar Energy Society
• /
• v.37 no.5
• /
• pp.65-75
• /
• 2017

In this study, the change of heat loss due to the degree of deterioration of the XPS insulation in KEPCO's office buildings is analyzed. The acceleration aging test of the XPS insulation was carried out according to the test method A of KS M ISO 11561: 2009. The performance of the insulation was analyzed by applying it to the three - dimensional steady state heat transfer analysis program. The acceleration aging test of the XPS insulation, show that the thermal resistance performance decreased by 1.44% at the A regional headquarters, 0.85% at the B regional headquarters, 6.41% at the C branch office, 7.76% at the D regional headquarters, 8.51% at the E branch office, and by 8.54% at the F branch office respectively. Using simulation, we determined that the thermal resistance value of E branch office decreased by 8.04%, while its heat loss increased by 8.52%. At A regional headquarters, the thermal resistance decreased by 1.38%, and the heat loss increased by 1.51%. At D regional headquarters, these value are 6.82% and 7.17%, respectively.

• Journal of the Korea Concrete Institute
• /
• v.15 no.2
• /
• pp.173-182
• /
• 2003

Recently, the durability of concrete structures has received great attention as the number of sea-side structures, such as new airport, bridges, and nuclear power plants, increases continuously. In this regards, many studies have been done on the chloride attack in concrete structures. However, those studies were confined mostly to the single deterioration due to chloride only, although actual environment is rather of combined type. The purpose of the present study is, therefore, to explore the effects of combined deterioration due to chlorides and sulfates in concrete structures. To this end, comprehensive experimental program has been set up to observe the chloride penetration behavior for various test series. The test results indicate that the chloride penetration is more pronounced for the case of combined attack than the case of single chloride attack. The surface chloride content is found to increase with time and the diffusion coefficient for chloride is found to decrease with time. The prediction equations for surface chloride content and diffusion coefficient were proposed according to test results. The equations for chloride penetration considering the time-dependent diffusion coefficients and surface chlorides were also suggested. The present study allows more realistic assessment of durability for such concrete structures which are subjected to combined attacks of chlorides and high concentration sulfates but the future studies for combined environment will assure the precise assessment.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.16 no.4
• /
• pp.33-41
• /
• 2012

The aim of the study is to investigate the method to estimate a shelf life of KM6 single base propellant by stochastic gamma process model. The state failure level is assumed that the degradation content of stabilizer is below 0.8%. The constant of time dependent shape function and the scale parameter of stationary gamma process are estimated by moment method. The state distribution at each storage time can be shown from probability density function of deterioration. It is estimated that the $B_{10}$ life, a time at which the cumulative failure probability is 10%, is 25 years and the $B_{50}$ life is 36 years from cumulative failure distribution function curve. The $B_{50}$ life can be treated as the average shelf life from the practical viewpoint and the lifetime can be expressed as distribution curve by using stochastic process theory.

• Korean Journal of Radiology
• /
• v.22 no.7
• /
• pp.1213-1224
• /
• 2021

Objective: To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. Materials and Methods: Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. Results: Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. Conclusion: CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.27 no.4
• /
• pp.246-257
• /
• 2015

The progressive degradation paths of structures have quantitatively been tracked by using stochastic processes, such as Wiener process, gamma process and compound Poisson process, in order to consider both the sampling uncertainty due to the usual lack of damage data and the temporal uncertainty associated with the deterioration evolution. Several important features of stochastic processes which should carefully be considered in application of the stochastic processes to practical problems have been figured out through assessing cumulative damage and lifetime distribution as a function of time. Especially, the Wiener process and the gamma process have straightforwardly been applied to armors of rubble-mound breakwaters by the aid of a sample path method based on Melby's formula which can estimate cumulative damage levels of armors over time. The sample path method have been developed to calibrate the related-parameters required in the stochastic modelling of armors of rubble-mound breakwaters. From the analyses, it is found that cumulative damage levels of armors have surely been saturated with time. Also, the exponent of power law in time, that plays a significant role in predicting the cumulative damage levels over time, can easily be determined, which makes the stochastic models possible to track the cumulative damage levels of armors of rubble-mound breakwaters over time. Finally, failure probabilities with respect to various critical limits have been analyzed throughout its anticipated service life.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.175-180
• /
• 2015

With progress in industrialization, facilities for generating, delivering, and receiving high levels of electric power are in great demand. The scale of electric power equipment is increasing in both size and complexity. This has contributed to the development of our modern, high-tech and information-based society. However, if the generation of electric power is suspended due to unexpected accidents at power facilities or power stations, a range of equipment the operations of which are dependent on electric power can be damaged, causing substantial socioeconomic losses in an industrial society. A great deal of time and money would be expended to repair damaged facilities at a power station, causing enormous economic loss.In order to detect the deterioration processes of power cables, and to prevent the destruction of power cables, the operation status of power cables should be monitored on a regular basis. We have installed equipment at Korea Western Power Co., Ltd., located in Taean, in order to predict and prevent the destruction of power cables. This is an entirely new installation: a set of equipment invented specifically to measure the insulation resistance of power cables. Installation of the equipment does not cause the flow of earth fault current. This ensures accurate measurement of insulation resistance values by the equipment. We have been studying this equipment in order to develop preventive technology that would show the deterioration processes of power cables.