• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.1
• /
• pp.137-143
• /
• 2008

Thermal fatigue life prediction for solder joints becomes the most critical issue in present microelectronic packaging industry. And lead-free solder is quickly becoming a reality in electronic manufacturing fields. This trend requires life prediction models for new solder alloy systems. This paper describes the life prediction models for SnAgCu and SnPb solder joints, based upon non-linear finite element analysis (FEA). In case of analyses of the SnAgCu solder joints, two kinds of shapes are used. As a result, it is found that the SnAgCu solder has longer fatigue life than the SnPb solder in temperature cycling analyses.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.27 no.2
• /
• pp.10-16
• /
• 2004

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manufacturing Process. The Purpose of this Paper is to model the recognition of defect type Patterns and Prediction of each defect type before it occurs in manufacturing process. The proposed model consists of data handling, defect type analysis, and defect type prediction stages. The performance measurement shows that it is higher in prediction accuracy than logistic regression model.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.1
• /
• pp.55-74
• /
• 2005

Bankruptcy prediction has drawn a lot of research interests in previous literature, and recent studies have shown that machine learning techniques achieved better performance than traditional statistical ones. This paper employs a relatively new machine learning technique, support vector machines (SVMs). to bankruptcy prediction problem in an attempt to suggest a new model with better explanatory power and stability. To serve this purpose, we use grid search technique using 5-fold cross-validation to find out the optimal values of the parameters of kernel function of SVM. In addition, to evaluate the prediction accuracy of SVM. we compare its performance with multiple discriminant analysis (MDA), logistic regression analysis (Logit), and three-layer fully connected back-propagation neural networks (BPNs). The experiment results show that SVM outperforms the other methods.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2028-2030
• /
• 2003

This paper describes the results of reliability prediction analysis of control rod control system, which is being developed as part of KNICS project. The results of reliability prediction indicate MTBF(Mean Time Between Failure) of cards for control rod control system. A purpose of reliability prediction is to evaluate MTBF of cards, identify the design drawbacks of cards, and propose design improvement to a designer to help design the more reliable control rod control system. This reliability prediction analysis used the the part count and part stress method in the basis of MIL-HDBK-217F.

• Nuclear Engineering and Technology
• /
• v.53 no.8
• /
• pp.2610-2615
• /
• 2021

The prediction of irradiation-induced transition temperature shift for RPV steels is an important method for long term operation of nuclear power plant. Based on the irradiation embrittlement data, an irradiation-induced transition temperature shift prediction model is developed with machine learning method XGBoost. Then the residual, standard deviation and predicted value vs. measured value analysis are conducted to analyze the accuracy of this model. At last, Cu content threshold and saturation values analysis, temperature dependence, Ni/Cu dependence and flux effect are given to verify the reliability. Those results show that the prediction model developed with XGBoost has high accuracy for predicting the irradiation embrittlement trend of RPV steel. The prediction results are consistent with the current understanding of RPV embrittlement mechanism.

• Journal of information and communication convergence engineering
• /
• v.19 no.4
• /
• pp.241-247
• /
• 2021

Particulate matter has emerged as a serious global problem, necessitating highly reliable information on the matter. Therefore, various algorithms have been used in studies to predict particulate matter. In this study, we compared the prediction performance of neural network models that have been actively studied for particulate matter prediction. Among the neural network algorithms, a deep neural network (DNN), a recurrent neural network, and long short-term memory were used to design the optimal prediction model using a hyper-parameter search. In the comparative analysis of the prediction performance of each model, the DNN model showed a lower root mean square error (RMSE) than the other algorithms in the performance comparison using the RMSE and the level of accuracy as metrics for evaluation. The stability of the recurrent neural network was slightly lower than that of the other algorithms, although the accuracy was higher.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.20 no.2
• /
• pp.1-10
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis, a model can be constructed with various machine learning algorithms, including decision tree. And feature importance has been utilized in selecting better input features that can improve performance of data analysis models for several application areas. In this paper, a method of utilizing feature importance calculated from the MDI method and its effects are investigated in the credit card customer churn prediction problem with classification trees. Compared with several random feature selections from case data, a set of input features selected from higher value of feature importance shows higher predictive power. It can be an efficient method for classifying and choosing input features necessary for improving prediction performance. The method organized in this paper can be an alternative to the selection of input features using feature importance in composing and using classification trees, including credit card customer churn prediction.

• 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%.

• Atmosphere
• /
• v.17 no.1
• /
• pp.27-44
• /
• 2007

The purpose of this study is to investigate predictability of the seasonal simulation by the METRI (Meteorological Research Institute) AGCM (Atmospheric General Circulation Model), which is a long-term prediction model for the METRI 3-month prediction system. We examine the performance skill of climate simulation and predictability by the analysis of variance of the METRI AGCM, focusing on the precipitation, 850 hPa temperature, and 500 hPa geopotential height. According to the result, the METRI AGCM shows systematic errors with seasonal march, and represents large errors over the equatorial region, compared to the observation. Also, the response of the METRI AGCM by the variation of the sea surface temperature is obvious for the wintertime and springtime. However, the METRI AGCM does not show the significant ENSO-related signal in autumn. In case of prediction over the east Asian region, errors between the prediction results and the observation are not quite large with the lead-time. However, in the predictability assessment using the analysis of variance method, longer lead-time makes the prediction better, and the predictability becomes better in the springtime.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.3
• /
• pp.154-161
• /
• 2018

This study conducted to predict the stock market prices based on the assumption that internet news articles might have an impact and effect on the rise and fall of stock market prices. The internet news articles were tested to evaluate the accuracy by comparing predicted values of the actual stock index and the forecasting models of the companies. This paper collected stock news from the internet, and analyzed and identified the relationship with the stock price index. Since the internet news contents consist mainly of unstructured texts, this study used text mining technique and multiple regression analysis technique to analyze news articles. A company H as a representative automobile manufacturing company was selected, and prediction models for the stock price index of company H was presented. Thus two prediction models for forecasting the upturn and decline of H stock index is derived and presented. Among the two prediction models, the error value of the prediction model (1) is low, and so the prediction performance of the model (1) is relatively better than that of the prediction model (2). As the further research, if the contents of this study are supplemented by real artificial intelligent investment decision system and applied to real investment, more practical research results will be able to be developed.