• Journal of the Korea Safety Management & Science
• /
• v.25 no.4
• /
• pp.131-140
• /
• 2023

This paper proposes an algorithm for the Unrelated Parallel Machine Scheduling Problem(UPMSP) without setup times, aiming to minimize total tardiness. As an NP-hard problem, the UPMSP is hard to get an optimal solution. Consequently, practical scenarios are solved by relying on operator's experiences or simple heuristic approaches. The proposed algorithm has adapted two methods: a policy network method, based on Transformer to compute the correlation between individual jobs and machines, and another method to train the network with a reinforcement learning algorithm based on the REINFORCE with Baseline algorithm. The proposed algorithm was evaluated on randomly generated problems and the results were compared with those obtained using CPLEX, as well as three scheduling algorithms. This paper confirms that the proposed algorithm outperforms the comparison algorithms, as evidenced by the test results.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.107-113
• /
• 2024

Scheduling of semiconductor test facilities has been crucial since effective scheduling contributes to the profits of semiconductor enterprises and enhances the quality of semiconductor products. This study aims to solve the scheduling problems for the wafer burn-in test facilities of the semiconductor back-end process by utilizing simulation and deep reinforcement learning-based methods. To solve the scheduling problem considered in this study. we propose novel state, action, and reward designs based on the Markov decision process. Furthermore, a neural network is trained by employing the recent RL-based method, named proximal policy optimization. Experimental results showed that the proposed method outperformed traditional heuristic-based scheduling techniques, achieving a higher due date compliance rate of jobs in terms of total job completion time.

• Journal of Korean Society for Quality Management
• /
• v.51 no.4
• /
• pp.573-588
• /
• 2023

Purpose: This study presents a research approach that utilizes deep reinforcement learning to construct optimal portfolios based on the business cycle for stocks and other assets. The objective is to develop effective investment strategies that adapt to the varying returns of assets in accordance with the business cycle. Methods: In this study, a diverse set of time series data, including stocks, is collected and utilized to train a deep reinforcement learning model. The proposed approach optimizes asset allocation based on the business cycle, particularly by gathering data for different states such as prosperity, recession, depression, and recovery and constructing portfolios optimized for each phase. Results: Experimental results confirm the effectiveness of the proposed deep reinforcement learning-based approach in constructing optimal portfolios tailored to the business cycle. The utility of optimizing portfolio investment strategies for each phase of the business cycle is demonstrated. Conclusion: This paper contributes to the construction of optimal portfolios based on the business cycle using a deep reinforcement learning approach, providing investors with effective investment strategies that simultaneously seek stability and profitability. As a result, investors can adopt stable and profitable investment strategies that adapt to business cycle volatility.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.116-123
• /
• 2024

In the manufacturing industry, dispatching systems play a crucial role in enhancing production efficiency and optimizing production volume. However, in dynamic production environments, conventional static dispatching methods struggle to adapt to various environmental conditions and constraints, leading to problems such as reduced production volume, delays, and resource wastage. Therefore, there is a need for dynamic dispatching methods that can quickly adapt to changes in the environment. In this study, we aim to develop an agent-based model that considers dynamic situations through interaction between agents. Additionally, we intend to utilize the Q-learning algorithm, which possesses the characteristics of temporal difference (TD) learning, to automatically update and adapt to dynamic situations. This means that Q-learning can effectively consider dynamic environments by sensitively responding to changes in the state space and selecting optimal dispatching rules accordingly. The state space includes information such as inventory and work-in-process levels, order fulfilment status, and machine status, which are used to select the optimal dispatching rules. Furthermore, we aim to minimize total tardiness and the number of setup changes using reinforcement learning. Finally, we will develop a dynamic dispatching system using Q-learning and compare its performance with conventional static dispatching methods.

• Journal of the Korean Society of Visualization
• /
• v.22 no.2
• /
• pp.44-54
• /
• 2024

This study investigates the effectiveness of using a plasma actuator for active control of turbulent flow around a finite square cylinder. The primary objective is to analyze the impact of plasma actuators on flow separation and wake region characteristics, which are critical for reducing drag and suppressing vortex-induced vibrations. Direct Numerical Simulation (DNS) was employed to explore the flow dynamics at various operational parameters, including different actuation frequencies and voltages. The proposed methodology employs a neural network trained using the Proximal Policy Optimization (PPO) algorithm to determine optimal control policies for plasma actuators. This network is integrated with a computational fluid dynamics (CFD) solver for real-time control. Results indicate that this deep reinforcement learning (DRL)-based strategy outperforms existing methods in controlling flow, demonstrating robustness and adaptability across various flow conditions, which highlights its potential for practical applications.

• Journal of Gifted/Talented Education
• /
• v.23 no.2
• /
• pp.215-236
• /
• 2013

In this study, we seek to improve the quality of education at institutes for science gifted education in universities by analysing the curriculums. Annual reports were analyzed, directors, professors, and students participated in the survey, directors were interviewed. The number of students was three times more than enrichment step than mentorship step. In content items, four items among nine received scores was 4 on the 5 point Likert scale. In the teaching and learning process items, five items among ten received scores 4. Students' choice and experience received scores below 4. In the product and the learning environment items, all items lower than 4. The professors did not supply guidance according to the results of the assessment. The professors developed and revised the curriculum considering the students' interests. The directors, professors, and students wanted to increase the free inquiry time. Based on the findings, we suggested that free inquiry time, a variety of experience, product, and environment considering individual students' abilities and interests should be increased.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.1
• /
• pp.51-65
• /
• 2016

A syllabus can be considered to be a masterplan for good educational results. This study tries to diagnose the current status of landscape architectural design education and suggest improvement strategies for better landscape design courses through the analysis of the syllabi of mid-level landscape design studio classes collected from the four-year undergraduate programs. The findings and suggestions are as follows. First, it is necessary to take advantage of a syllabus as a contract as well as a plan and a learning tool. Second, it is crucial to make more detailed statement from the perspectives of learners. Third, more customized components for design courses should be developed; the syllabus should give the structure of a design class as an integration and synthesis of other courses. Fourth, it is necessary to increase the interrelationship and relevance among the components, especially between course objectives and evaluation criteria, and course activities and references. Fifth, a syllabus needs to function as a communication tool in a flexible manner. Sixth, a syllabus needs to give a comprehensive information about the site and the design project. Finally, instructors need to introduce a set of detailed evaluation rubrics or criteria acceptable to students in order to increase the fairness and transparency of the evaluation.

• Journal of The Korean Association of Information Education
• /
• v.21 no.4
• /
• pp.463-474
• /
• 2017

Software integration becomes very important in these days. Since the 4th industrial revolution has begun and influences its heavy effects on our daily life, software education has been introduced in the 2015 national revised curriculum. The purpose of this study is to verify the effects of a mobile web application for the elementary algorithm class based on STEAM on the problem solving process of elementary school students. To do so, in this study we constructed an algorithm learning contents based on STEAM for new software education and developed a mobile web application for flipped learning to improve their problem solving ability. Further, an experimental group and a controlled group are selected respectively from the 5th grade elementary school students. Then, a new flipped learning class using our mobile materials was applied to the experimental group while a traditional lecture class using the activity papers was applied to the controlled group. Finally the paired samples t-tests were carried out. As a result, we found that there was a statistically significant difference in problem solving process between the two groups. Based on our experimental research and the results of statistical analysis, the mobile web application class based on STEAM turned out to be effective in improving the problem solving ability of elementary school students.

• Journal of The Korean Association For Science Education
• /
• v.18 no.3
• /
• pp.443-450
• /
• 1998

This study was performed to find the environmental factors of inquiry instruction perceived by secondary school science teacher. The instrument consisted of three domains such as teaching conditions, viewpoints of secondary school science teachers of environmental factors for inquiry instruction, and barrier and improve! rent factors of inquiry instruction. Teaching conditions between middle school and high school science teachers were not different significantly. Environmental factors of inquiry instruction of secondary school science teacher included five factors such as 'facilities and encouragement', 'amount of works and materials', 'teacher education and textbook', 'practice and knowledge' and 'perception of necessity and satisfaction'. And all factors except 'perception of necessity and satisfaction' were very low state for inquiry instruction. In the disturbant and improving factors, the critical factors were 'over students per class', 'textbook' and 'learning materials' for middle school science teachers, and 'over students per class', and 'entrance examination' for high school science teachers. Thus the development and diffusion of adequate inquiry learning materials may be helpful to practicing inquiry instruction as decrease of works and psychological charges, and it is needed to reorganize systematically and intensify pre- and in-service teacher education to practice inquiry instruction.

• Journal of The Korean Association For Science Education
• /
• v.38 no.3
• /
• pp.331-341
• /
• 2018

The purpose of this study is to explore relationships among the structural elements of Science Classroom as Community of Practice (SCaCoP). For this, we investigated the case of small-group activities in practical work of elementary school science in a qualitative way based on the five structural elements of SCaCoP, such as responsibility for learning, common interest, open participation, mutual relationship, and practice. We observed and interviewed five small-groups during five lessons with video- and audio- recording to collect data. The results of analysis are as follows. First, 'mutual relationship' was a necessary-condition for 'open participation.' We also found that 'common interest' has two dimensions related to their interest and related to learning topic. The former interacted with 'open participation,' and the latter was influenced by 'responsibility for learning. Lastly, 'practice' enhanced the features of other elements with dynamic relationships. Based on these results, we suggested the relationships among the structural elements of SCaCoP and discussed implications related to the perspective that regards learning as participation.