• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.166-175
• /
• 2019

Grit, a concept conceived in 2007 by Duckworth and others in the United States, is based on positive psychology that focuses on growth and development through individual strengths. Recently, "Grit", which means patience and enthusiasm for long-term goals, has emerged as a key factor of personality strength. In Korea, Joo-hwan Kim (2013) was the first to conceptualize and study the subject of Grit. However, there have been no overview studies that systematically summarize the overall trends and flow in the research of Grit so far. There have been 147 research papers on Grit published so far in Korea. The purpose of this study was to conduct trend analysis on the subject of Grit by analyzing forty-three (43) master's and doctoral dissertations, thus presenting the direction of future research on Grit through careful analysis. In the studies conducted, it was found that Grit is a very significant variable linked to self-efficacy. It is also a subjective belief that can help an individual achieve his/her educational goals, and go through failure resynchronization. In addition, Grit is very significant as a practical core indicator of how fusion talent is fostered for the fourth industrial revolution. Therefore, there is a need for more in-depth research from the viewpoints of workplace learning, experiential learning, or informal learning, as well as research into Grit characteristics.

• Steel and Composite Structures
• /
• v.47 no.1
• /
• pp.103-117
• /
• 2023

This paper presents an investigation on the shear resistance of corrugated web steel beams (CWBs) with a circular web opening. A total of five specimens with different diameters of web openings were designed and tested with vertical load applied on the top flange at mid-span. The ultimate strengths, failure modes, and load versus middle displacement curves were obtained from the tests. Following the tests, numerical models of the CWBs were developed and validated against the test results. The influence of the web plate thickness, steel grade, opening diameter, and location on the shear strength of the CWBs was extensively investigated. An XGBoost machine learning model for shear resistance prediction was trained based on 256 CWB samples. The XGBoost model with optimal hyperparameters showed excellent accuracy and exceeded the accuracy of the available design equations. The effects of geometric parameters and material properties on the shear resistance were evaluated using the SHAP method.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.3
• /
• pp.18-30
• /
• 2022

Predicting remaining useful life (RUL) becomes significant to implement prognostics and health management of industrial systems. The relevant studies have contributed to creating RUL prediction models and validating their acceptable performance; however, they are confined to drive reasonable preventive maintenance strategies derived from and connected with such predictive models. This paper proposes a data-driven preventive maintenance method that predicts RUL of industrial systems and determines the optimal replacement time intervals to lead to cost minimization in preventive maintenance. The proposed method comprises: (1) generating RUL prediction models through learning historical process data by using machine learning techniques including random forest and extreme gradient boosting, and (2) applying the system failure time derived from the RUL prediction models to the Weibull distribution-based minimum-repair block replacement model for finding the cost-optimal block replacement time. The paper includes a case study to demonstrate the feasibility of the proposed method using an open dataset, wherein sensor data are generated and recorded from turbofan engine systems.

• Journal of Korea Foundry Society
• /
• v.42 no.6
• /
• pp.369-376
• /
• 2022

The die-casting process is an important process for various industries, but there are limitations in the profitability and productivity of related companies due to the high defect rate. In order to overcome this, this study has developed die-casting fault detection modules based on industrial AI technologies. The developed module is constructed from three-stage models depending on the characteristics of the dataset. The first-stage model conducts fault detection based on supervised learning from the dataset without labels. The second-stage model realizes one-class classification based on semi-supervised learning, where the dataset only has production success labels. The third-stage model corresponds to fault detection based on supervised learning, where the dataset includes a small amount of production failure cases. The developed fault detection module exhibited outstanding performance with roughly 96% accuracy for actual process data.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.367-374
• /
• 2022

The purpose of this study was to propose a deep learning algorithm that applies to the fault diagnosis of fuel pumps and purifiers of autonomous ships. A deep learning algorithm reflecting the time dependence of the measured signal was configured, and the failure pattern was trained using the vibration signal, measured in the equipment's regular operation and failure state. Considering the sequential time-dependence of deterioration implied in the vibration signal, this study adopts Conv1D with sliding window computation for fault detection. The time dependence was also reflected, by transferring the measured signal from two-dimensional to three-dimensional. Additionally, the optimal values of the hyper-parameters of the Conv1D model were determined, using the grid search technique. Finally, the results show that the proposed data preprocessing method as well as the Conv1D model, can reflect the sequential dependency between the fault and its effect on the measured signal, and appropriately perform anomaly as well as failure detection, of the equipment chosen for application.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.3
• /
• pp.183-192
• /
• 2021

This study was purposed to explore the learning culture through the related literature and research review in Jewish Havruta which has interaction, critical reflection, and the driving force creating a better world. The prior researches on Havruta mainly tend to as ways to increase learners' interest in learning and studies as curriculum or teaching methods such as creativity, understanding, and problem-solving skills. However, Havruta is not just method to study subjects, but rather a process of developing thinking through dialogue and discussion. Therefore, Havruta's essential meaning as a lifelong learning should be explored. Studies showed that Jews embody the thinking process from interpreting, analyzing, setting up logic, questioning, discussing, and debating Talmud with others anytime, anywhere, and anyone throughout their learning culture. It develops basic skills for life, forms an integrated personality in relationships with others, and continuously conducts lifelong learning to shape one's own beings. Therefore, lifelong learning culture would be sharing information that one has in the process of discussion through dialogue between two or more people, and supporting and encouraging the other's failure or fear rather than attacking them. The embodiment of thinking process in which people teach and learn eachother, accept the difference, and expand thought would be significant foundation to create lifelong learning culture.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.5
• /
• pp.496-502
• /
• 2016

In this study, we investigated the comparative NHPP software model based on learning techniques that operators in the process of software testing and development of software products that can be applied to software test tool. The life distribution was applied Makeham distribution based on finite fault NHPP. Software error detection techniques known in advance, but influencing factors for considering the errors found automatically and learning factors, by prior experience, to find precisely the error factor setting up the testing manager are presented comparing the problem. As a result, the learning factor is larger than automatic error that is usually well-organized model could be established. This paper, a trust characterization of applying using time among failures and parameter approximation using maximum likelihood estimation, after the effectiveness of the data through trend examination model selection were well-organized using the mean square error and $R^2$. From this paper, the software operators must be considered life distribution by the basic knowledge of the software to confirm failure modes which may be helped.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.10
• /
• pp.4543-4549
• /
• 2011

In this study, software products developed in the course of testing, software managers in the process of testing software test and test tools for effective learning effects perspective has been studied using the NHPP software. The Burr distribution applied to distribution was based on finite failure NHPP. Software error detection techniques known in advance, but influencing factors for considering the errors found automatically and learning factors, by prior experience, to find precisely the error factor setting up the testing manager are presented comparing the problem. As a result, the learning factor is greater than automatic error that is generally efficient model could be confirmed. This paper, a numerical example of applying using time between failures and parameter estimation using maximum likelihood estimation method, after the efficiency of the data through trend analysis model selection were efficient using the mean square error and $R^2$.

• Convergence Security Journal
• /
• v.11 no.1
• /
• pp.25-32
• /
• 2011

In this study, software products developed in the course of testing, software managers in the process of testing software test and test tools for effective learning effects perspective has been studied using the NHPP software. The Weibull distribution applied to distribution was based on finite failure NHPP. Software error detection techniques known in advance, but influencing factors for considering the errors found automatically and learning factors, by prior experience, to find precisely the error factor setting up the testing manager are presented comparing the problem. As a result, the learning factor is greater than automatic error that is generally efficient model could be confirmed. This paper, a numerical example of applying using time between failures and parameter estimation using maximum likelihood estimation method, after the efficiency of the data through trend analysis model selection were efficient using the mean square error and $R_{sq}$.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.3
• /
• pp.79-89
• /
• 1998

The Error Back-Propagation(EBP) algorithm is widely applied to train a multi-layer perceptron, which is a neural network model frequently used to solve complex problems such as pattern recognition, adaptive control, and global optimization. However, the EBP is basically a gradient descent method, which may get stuck in a local minimum, leading to failure in finding the globally optimal solution. Moreover, a multi-layer perceptron suffers from locking a systematic determination of the network structure appropriate for a given problem. It is usually the case to determine the number of hidden nodes by trial and error. In this paper, we propose a new algorithm to efficiently train a multi-layer perceptron. OUr algorithm uses stochastic perturbation in the weight space to effectively escape from local minima in multi-layer perceptron learning. Stochastic perturbation probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the EGP learning gets stuck to it. Addition of new hidden nodes also can be viewed asa special case of stochastic perturbation. Using stochastic perturbation we can solve the local minima problem and the network structure design in a unified way. The results of our experiments with several benchmark test problems including theparity problem, the two-spirals problem, andthe credit-screening data show that our algorithm is very efficient.