• Journal of the Korean Operations Research and Management Science Society
• /
• v.34 no.2
• /
• pp.35-54
• /
• 2009

The recent economic crisis not only reduces the profit of department stores but also incurs the significance losses caused by the increasing late-payment rate of credit cards. Under this pressure, the scope of credit prediction needs to be broadened from the simple prediction of whether this customer has a good credit or not to the accurate prediction of how much profit can be gained from this customer. This study classifies the delinquent customers of credit card in a Korean department store into homogeneous clusters. Using this information, this study analyzes the repayment patterns for each cluster and develops the credit prediction system to manage the delinquent customers. The model presented by this study uses Kohonen network, which is one of artificial neural networks of data mining technique, to cluster the credit delinquent customers into clusters. Cox proportional hazard model is also used, which is one of survival analysis used in medical statistics, to analyze the repayment patterns of the delinquent customers in each cluster. The presented model estimates the repayment period of delinquent customers for each cluster and introduces the influencing variables on the repayment pattern prediction. Although there are some differences among clusters, the variables about the purchasing frequency in a month and the average number of installment repayment are the most predictive variables for the repayment pattern. The accuracy of the presented system leaches 97.5%.

• Computers and Concrete
• /
• v.10 no.2
• /
• pp.197-217
• /
• 2012

This research deals with the prediction of compressive strength of normal and high strength concrete using neural networks. The compressive strength was modeled as a function of eight variables: quantities of cement, fine aggregate, coarse aggregate, micro-silica, water and super-plasticizer, maximum size of coarse aggregate, fineness modulus of fine aggregate. Two networks, one using raw variables and another using grouped dimensionless variables were constructed, trained and tested using available experimental data, covering a large range of concrete compressive strengths. The neural network models were compared with regression models. The neural networks based model gave high prediction accuracy and the results demonstrated that the use of neural networks in assessing compressive strength of concrete is both practical and beneficial. The performance of model using the grouped dimensionless variables is better than the prediction using raw variables.

• Journal of Korean Academy of Nursing
• /
• v.28 no.3
• /
• pp.550-562
• /
• 1998

The purpose of this study was to test the Theory of Planned Behavior in the prediction of contraceptive behavior among married women. This study used a descriptive correlational design to examine the relationships among the study variables. Eighty married women in Seoul and Kyungki-do participated in this study, Research instruments used were the tool for measuring TPB variables search as attitude toward contraception, subjective norm, perceived behavioral control, and intention ; and the tool for measuring contraceptive behavior. The former was modified by the researcher according to Ajzen & Fishbein(1980)'s guidelines for tool development and Jee (1993)'s tool. The latter was developed by the researcher Data was collected from July 20, 1996 to October 25, 1996. The results are as follows ; The three factors, attitude, subjective norm and perceived behavioral control of contraception can explain 30% of the variance in contraceptive intention. Inspection of path coefficient for each of the three predictor variables revealed that subjective norm and perceived behavioral control were the predictor variables on intention, while attitude was not. ; and intention and percevied behavioral control factors can explain 42% of the variance in contraceptive behavior. Inspection of path coefficient for each of the two predictor variables revealed that intention and perceived behavioral control were the predictor variables on behavior. In conclusion, this study identified that Theory of Planned Behavior was a useful model in the prediction of contraceptive behavior, and the contraceptive service program based on the TPB variables would be an effective nursing intervention for the change in contraceptive behavior.

• Journal of the Ergonomics Society of Korea
• /
• v.19 no.2
• /
• pp.87-99
• /
• 2000

This study aims to examine a fuzzy logic-based human expert EMG prediction model (FLHEPM) for predicting electromyographic responses of trunk muscles due to manual lifting based on two task (control) variables. The FLHEPM utilizes two variables as inputs and ten muscle activities as outputs. As the results, the lifting task variables could be represented with the fuzzy membership functions. This provides flexibility to combine different scales of model variables in order to design the EMG prediction system. In model development, it was possible to generate the initial fuzzy rules using the neural network, but not all the rules were appropriate (87% correct ratio). With regard to the model precision, the EMG signals could be predicted with reasonable accuracy that the model shows mean absolute error of 8.43% ranging from 4.97% to 13.16% and mean absolute difference of 6.4% ranging from 2.88% to 11.59%. However, the model prediction accuracy is limited by use of only two task variables which were available for this study (out of five proposed task variables). Ultimately, the neuro-fuzzy approach utilizing all five variables to predict either the EMG activities or the spinal loading due to dynamic lifting tasks should be developed.

• Journal of Korean Society for Quality Management
• /
• v.48 no.1
• /
• pp.171-186
• /
• 2020

Purpose: The purpose of this study is conducting of predictive models that considered multicollinearity of independent variables in order to carry out more efficient and reliable predictions about differential pressure in seawater reverse osmosis. Methods: The main variables of each RO system are extracted through factor analysis. Common variables are derived through comparison of RO system # 1 and RO system # 2. In order to carry out the prediction modeling about the differential pressure, which is the target variable, we constructed the prediction model reflecting the regression analysis, the artificial neural network, and the support vector machine in R package, and figured out the superiority of the model by comparing RMSE. Results: The number of factors extracted from factor analysis of RO system #1 and RO system #2 is same. And the value of variability(% Var) increased as step proceeds according to the analysis procedure. As a result of deriving the average RMSE of the models, the overall prediction of the SVM was superior to the other models. Conclusion: This study is meaningful in that it has been conducting a demonstration study of considering the multicollinearity of independent variables. Before establishing a predictive model for a target variable, it would be more accurate predictive model if the relevant variables are derived and reflected.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.4
• /
• pp.295-300
• /
• 2013

The noise map can be applied to predict the effect of noise and establish the noise reduction measure. But the predicted value in the noise map can vary depending on the input variables. Thus, we surveyed the several prediction models and analyzed the changes corresponding to the variables for obtaining the coherency and accuracy of prediction results. As a result, we know that the Schall03 and CRN model can be applied to predict the railway noise in Korea and the correction value, such as bridges correction, multiple reflection correction, curve correction must be used for reflecting the condition of the prediction site. Also, we know that the prediction guideline is an essential prerequisite in order to obtain the unified and accurate predicted value for railway noise.

• Journal of Korean Institute of Industrial Engineers
• /
• v.19 no.1
• /
• pp.39-46
• /
• 1993

In developing a multiple regression relationship, independent variables are frequently measured with error. For these situations the problem of estimating unknown parameters has been extensively discussed in the literature while little attention has been given to the prediction problem. In this paper a criterion is developed for assessing the severeness of measurement errors in each independent variable on the predicted values. Using the developed criterion we can present a guideline as to which measurement error should be controlled for a more accurate prediction. Proposed methods are illustrated with a standard data system in work measurement.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2003.05a
• /
• pp.176-179
• /
• 2003

The mean temperature prediction of strip is very important in hot strip finishing mill because of affecting on product quality and shape. Also, temperature can be used by basic information in other on-line control models with affecting control accuracy in factory. So, FE based on-line temperature model was developed for predicting strip mean temperature accurately in various process conditions and factory environments. There are many variables in affecting strip mean temperature in on-line states of factory. But some problems are occurred in considering all variables for making temperature model because of the bad efficiency of regression or fitting analysis. In this report, we have adopted dimensional analysis for solving these problems. We have many variables with dimensions affecting strip temperature but we are able to make non-dimensional variables less than dimensional variables from the combination of dimensional variables caused by PI-Theorem in fluid mechanics. The developed models are divided by two parts. The one is interstand temperature prediction model. The other is roll gap temperature model.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• pp.569-579
• /
• 2021

Purpose: The purpose of this study is the time series analysis for predicting the yield of crops applicable to each farm using environmental variables measured by smart farms cultivating tomato. In addition, it is intended to confirm the influence of environmental variables using a deep learning model that can be explained to some extent. Methods: A time series analysis was performed to predict production using environmental variables measured at 75 smart farms cultivating tomato in two periods. An LSTM-based encoder-decoder model was used for cases of several farms with similar length. In particular, Dual Attention Mechanism was applied to use environmental variables as exogenous variables and to confirm their influence. Results: As a result of the analysis, Dual Attention LSTM with a window size of 12 weeks showed the best predictive power. It was verified that the environmental variables has a similar effect on prediction through wieghtss extracted from the prediction model, and it was also verified that the previous time point has a greater effect than the time point close to the prediction point. Conclusion: It is expected that it will be possible to attempt various crops as a model that can be explained by supplementing the shortcomings of general deep learning model.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.33 no.2
• /
• pp.1-16
• /
• 2008

The purpose of this paper is to propose a new binary classification method for predicting corporate failure based on genetic algorithm, and to validate its prediction power through empirical analysis. Establishing virtual companies representing bankrupt companies and non-bankrupt ones respectively, the proposed method measures the similarity between the virtual companies and the subject for prediction, and classifies the subject into either bankrupt or non-bankrupt one. The values of the classification variables of the virtual companies and the weights of the variables are determined by the proper model to maximize the hit ratio of training data set using genetic algorithm. In order to test the validity of the proposed method, we compare its prediction accuracy with ones of other existing methods such as multi-discriminant analysis, logistic regression, decision tree, and artificial neural network, and it is shown that the binary classification method we propose in this paper can serve as a premising alternative to the existing methods for bankruptcy prediction.