• KEPCO Journal on Electric Power and Energy
• /
• v.6 no.4
• /
• pp.413-418
• /
• 2020

It is necessary to manage the prediction accuracy of the machine learning model to prevent the decrease in the performance of the grid network condition prediction model due to overfitting of the initial training data and to continuously utilize the prediction model in the field by maintaining the prediction accuracy. In this paper, we propose an automation technique for maintaining the performance of the model, which increases the accuracy and reliability of the prediction model by considering the characteristics of the power grid state data that constantly changes due to various factors, and enables quality maintenance at a level applicable to the field. The proposed technique modeled a series of tasks for maintaining the performance of the power grid condition prediction model through the application of the workflow management technology in the form of a workflow, and then automated it to make the work more efficient. In addition, the reliability of the performance result is secured by evaluating the performance of the prediction model taking into account both the degree of change in the statistical characteristics of the data and the level of generalization of the prediction, which has not been attempted in the existing technology. Through this, the accuracy of the prediction model is maintained at a certain level, and further new development of predictive models with excellent performance is possible. As a result, the proposed technique not only solves the problem of performance degradation of the predictive model, but also improves the field utilization of the condition prediction model in a complex power grid system.

• Journal of Applied Reliability
• /
• v.18 no.3
• /
• pp.250-259
• /
• 2018

Purpose: Previously, missile reliability prediction is based on theoretical failure prediction model. It has shown that the predicted reliability is inadequate to real field data. Although an MTTF based reliability prediction method using real field data has recently been studied to overcome this issue. In this paper, we present a more realistic method, considering MTBF concept, to predict missile reliability. Methods: In this paper we proposed a modified survival model. This model is considering MTBF as its core concept, and failed missiles in the model are to be repaired and redeployed. We compared the modified model (MTBF) and the previous model (MTTF) in terms of fitness against the real failure data. Results: The reliability prediction result of MTBF based model is closer to fields failure data set than that of MTTF based model. Conclusion: The proposed MTBF concept is more fitted to real failure data of missile than MTTF concept. The methodology of this study can be applied to analyze field failure data of other similar missiles.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.101-104
• /
• 2007

All of noise prediction model have it's own features in the case of modeling conditions, so it is very important to know the features of each model case by case for a proper modeling, especially using at the Environmental Impact Assessment. For prediction of highway traffic noise and abating the noise by barriers, two kinds of prediction model, HW-NOISE, KHTN(Korea Highway Traffic Noise) has been mainly used in Korea. In this study, the features of these models were described at the same conditions. The properties of sound power from a road, diffraction characteristics from a barrier, sound pressure level decaying in each model were investigated. Using the results, it will be anticipated that the proper using of prediction models in the works of highway noise abating.

• Genomics & Informatics
• /
• v.16 no.4
• /
• pp.32.1-32.7
• /
• 2018

Ovarian cancer is one of the leading causes of cancer-related deaths in gynecological malignancies. Over 70% of ovarian cancer cases are high-grade serous ovarian cancers and have high death rates due to their resistance to chemotherapy. Despite advances in surgical and pharmaceutical therapies, overall survival rates are not good, and making an accurate prediction of the prognosis is not easy because of the highly heterogeneous nature of ovarian cancer. To improve the patient's prognosis through proper treatment, we present a prognostic prediction model by integrating high-dimensional RNA sequencing data with their clinical data through the following steps: gene filtration, pre-screening, gene marker selection, integrated study of selected gene markers and prediction model building. These steps of the prognostic prediction model can be applied to other types of cancer besides ovarian cancer.

• Journal of Korean Society of Forest Science
• /
• v.97 no.2
• /
• pp.140-143
• /
• 2008

This study compared the plywood demand prediction accuracy of econometric and vector autoregressive models using Korean data. The econometric model of plywood demand was specified with three explanatory variables; own price, construction permit area, dummy. The vector autoregressive model was specified with lagged endogenous variable, own price, construction permit area and dummy. The dummy variable reflected the abrupt decrease in plywood consumption in the late 1990's. The prediction accuracy was estimated on the basis of Residual Mean Squared Error, Mean Absolute Percentage Error and Theil's Inequality Coefficient. The results showed that the plywood demand prediction can be performed more accurately by econometric model than by vector autoregressive model.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.3
• /
• pp.393-403
• /
• 1999

In this research, a reach posture prediction based on a two-segment trunk model was made. Recently, reach posture prediction models have used inverse kinematics to provide a single posture that a person naturally takes, with a single segment trunk model that had some shortcomings. A two-segment trunk model was first developed with two links; pelvis link and lumbar-thoracic link. The former refers to the link from the hip joint to L5/S1 joint while the latter does the link from L5/S1 to the shoulder joint. Second, a reach prediction model was developed using the two-segment trunk model. As a result, more reliable equations for two-segment trunk motion were obtained, and the lean direction which refers to the movement direction of the trunk was not found to have a significant effect on the two-segment trunk motion. The results also showed that the hip joint is more preferred over L5/S1 to serve as a reference point for trunk models and the reach prediction model being developed predicted the real posture accurately.

• Proceedings of the KSME Conference
• /
• 2000.04b
• /
• pp.580-585
• /
• 2000

Recently TEIS model, Two-zone model aid Stanitz equations are often used for off-design performance prediction of centrifugal compressor and pump. The prediction results often agree well with experimental data. However these models and equations have some important variables which have a great influence on overall performance prediction me. But no systematic study about these variables has been performed. So, in this paper, a systematic study about these variables influence on overall performance prediction owe is peformed. Finally the meaning of the variables and the research to be undertaken are discussed.

• Journal of Korean Society of Forest Science
• /
• v.95 no.5
• /
• pp.601-604
• /
• 2006

This study compared the accuracy of partial multivariate and vector autoregressive models for lumber demand prediction in Korea. The partial multivariate model has three explanatory variables; own price, construction permit area and dummy. The dummy variable reflected the boom of lumber demand in 1988, and the abrupt decrease in 1998. The VAR model consists of two endogenous variables, lumber demand and construction permit area with one lag. On the other hand, the prediction accuracy was estimated by Root Mean Squared Error. The results showed that the estimation by partial multivariate and vector autoregressive model showed similar explanatory power, and the prediction accuracy was similar in the case of using partial multivariate and vector autoregressive model.

• Journal of Information Technology Services
• /
• v.21 no.4
• /
• pp.91-103
• /
• 2022

This study proposes a model for predicting contracted power using electric power data collected in real time from convenience stores nationwide. By optimizing the prediction model using machine learning, it will be possible to predict the contracted power required to renew the contract of the existing convenience store. Contracted power is predicted through the XGBoost regression model. For the learning of XGBoost model, the electric power data collected for 16 months through a real-time monitoring system for convenience stores nationwide were used. The hyperparameters of the XGBoost model were tuned using the GridesearchCV, and the main features of the prediction model were identified using the xgb.importance function. In addition, it was also confirmed whether the preprocessing method of missing values and outliers affects the prediction of reduced power. As a result of hyperparameter tuning, an optimal model with improved predictive performance was obtained. It was found that the features of power.2020.09, power.2021.02, area, and operating time had an effect on the prediction of contracted power. As a result of the analysis, it was found that the preprocessing policy of missing values and outliers did not affect the prediction result. The proposed XGBoost regression model showed high predictive performance for contract power. Even if the preprocessing method for missing values and outliers was changed, there was no significant difference in the prediction results through hyperparameters tuning.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.23 no.1
• /
• pp.67-95
• /
• 1998

This research addresses flow time prediction in the dynamic unbalanced job shop scheduling environment. The specific purpose of the research is to develop the job flow time prediction model in the dynamic unbalance djob shop. Such factors as job characteristics, job shop status, characteristics of the shop workload, shop dispatching rules, shop structure, etc, are considered in the prediction model. The regression prediction approach is analyzed within a dynamic, make-to-order job shop simulation model. Mean Absolute Lateness (MAL) and Mean Relative Error (MRE) are used to compare and evaluate alternative regression models devloped in this research.