• Electronics and Telecommunications Trends
• /
• v.35 no.6
• /
• pp.137-149
• /
• 2020

Several multi-agent reinforcement learning (MARL) algorithms have achieved overwhelming results in recent years. They have demonstrated their potential in solving complex problems in the field of real-time strategy online games, robotics, and autonomous vehicles. However these algorithms face many challenges when dealing with massive problem spaces in sparse reward environments. Based on the centralized training and decentralized execution (CTDE) architecture, the MARL algorithms discussed in the literature aim to solve the current challenges by formulating novel concepts of inter-agent modeling, credit assignment, multiagent communication, and the exploration-exploitation dilemma. The fundamental objective of this paper is to deliver a comprehensive survey of existing MARL algorithms based on the problem statements rather than on the technologies. We also discuss several experimental frameworks to provide insight into the use of these algorithms and to motivate some promising directions for future research.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.24 no.6
• /
• pp.396-405
• /
• 2019

Single-phase full-bridge inverters have shoot-through problems. Dead time is an essential way of solving these issues, but it distorts the output voltage and current. Dual-buck inverters are designed to eliminate the abovementioned problems. However, these inverters result in switching power loss and electromagnetic interference due to the diode reverse-recovery problem. Previous studies have suggested reducing the switching power loss from diode reverse-recovery, but their proposed methods have complex circuit configurations and high system costs. To alleviate the switching power loss from diode reverse-recovery, the current work proposes a dual-buck inverter with a coupled inductor. In the structure of the proposed inverter, the current flowing into the original diode is divided into a new diode. Therefore, the switching power loss is reduced, and the efficiency of the proposed inverter is improved. Simulation waveforms and experimental results for a 1.0 kW prototype inverter are discussed to verify the performance of the proposed inverter.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.9 no.2
• /
• pp.175-185
• /
• 2003

The purpose: This study was to describe the spiritual nursing care experiences of nursing students who were in a university, Seoul, Korea. Method: This study is based on descriptive analysis of case studies that were submitted by nursing students. Nursing students were 64 person who were sophomores in a university of the year 2000, 2001. Results: 1. The problems that students report for their subjects were: Loss of self-confidence, body image complex, health status problems, maladaptability, economic problems of home, guilty feeling, problems with dating, loneliness, uncertainty of their future, faith problem, accountability, stress and apart from intimate friends. 2. The methods which students use to solve the subjects's problems were: prayer with subjects, use the Scripture, conversation, meet frequently, listening, frequent phone call, explore problem solving methods together, write letters or E-mails, present with books or music CD etc. 3. After the students have experienced spiritual nursing care they feel that: satisfaction, lack of knowledge of spiritual care, understanding the importance of spiritual nursing care make a new resolution for others, understanding the importance of listening, understanding the power of prayer, the need of Bible study. Conclusion: Maintaining spiritual wellness is a important as maintaining physical fitness and essential for optimal well being. Therefore educating nursing students in developing and maintaining spiritual wellness is essential for the patient to achieve holism.

• Asia pacific journal of information systems
• /
• v.16 no.1
• /
• pp.71-84
• /
• 2006

Case-based reasoning (CBR) is a reasoning technique that reuses past cases to find a solution to the new problem. It often shows significant promise for improving effectiveness of complex and unstructured decision making. It has been applied to various problem-solving areas including manufacturing, finance and marketing for the reason. However, the design of appropriate case indexing and retrieval mechanisms to improve the performance of CBR is still a challenging issue. Most of the previous studies on CBR have focused on the similarity function or optimization of case features and their weights. According to some of the prior research, however, finding the optimal k parameter for the k-nearest neighbor (k-NN) is also crucial for improving the performance of the CBR system. In spite of the fact, there have been few attempts to optimize the number of neighbors, especially using artificial intelligence (AI) techniques. In this study, we introduce a genetic algorithm (GA) to optimize the number of neighbors to combine. This study applies the novel approach to Korean stock market. Experimental results show that the GA-optimized k-NN approach outperforms other AI techniques for stock market prediction.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.11a
• /
• pp.155-160
• /
• 2001

Actual engineering structure is frequently very complex, and parts of structure are designed independently by different engineers. Also each structure contains so many degree of freedom. For these reason, methods have been developed which permits the structure to be divided into components or substructures, with analysis being done on a small substructure in order to obtain a full structural system. In such case, because of different mesh size among finite element model (FEM) or different matching points among FEM models and experimentally obtained models, their interfacing points may be non-matching. Solving this non-matching problem is useful to other application such as structural dynamic modification or model updating. In this work, virtual node concept is introduced. Lagrange multipliers are used to enforce the interface compatibility constraint, and interface displacement is approximated by polynomial presentation. The governing equation of whole structure is derived using hybrid variational principle. The eigenvalue of whole structure are calculated using the determinant search method. The number of degree of freedom in the eigenvalue problem can be drastically reduced to just the number of interface degree of freedom. Some numerical simulation is performed to show usefulness of synthesis method.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.119-120
• /
• 2006

Prioritizing the design specifications among many alternatives is necessary at the stage of concept design. Design specifications have trade-offs between cost and performance, and the relationships among them, in the standpoint of various functional requirements, are complex. AHP(Analytic Hierarchy Process) method is one of the most popular ways of solving the priority setting problem. However, it is impossible to monitor the interim findings in the middle of the process, it is hard to predict the difference when changing pairwise comparison conditions, and the operation done by one person makes it hard to share the process simultaneously. This paper shows a new method of priority setting in this kind of decision making problem. This method is designed to support the realtime priority setting among many design specifications with regards to many functional requirements. A new algorithm and visualization methods are introduced, and the usability is verified in an exemplary concept design stage.

• The Mathematical Education
• /
• v.54 no.3
• /
• pp.207-222
• /
• 2015

Mathematics preservice teachers' Mathematical Content Knowledge ("MCK") includes not only knowledge for mathematics, but also academic knowledge for school mathematics and mathematical process knowledge. We can consider the items in PISA 2012 as suitable tools to assess process knowledge as well as mathematical content knowledge because these items are developed by competent international educational experts. Therefore, the responses to items with the low percentage of correct answers in conjunction with the mathematical contents were analyzed with focus on FMC. The results showed the reasoning competency in responses using the conditions of the problem and of understanding the conditions after reading the complex problems within the context (i.e. the reasoning and argumentation competency, and communication competency) requires improvements. Furthermore the results indicated the errors due to a lack of ability of devising strategies for problem solving. Based on the foregoing results, the implications towards the directions of the education for the preservice mathematics teachers have been derived.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.1
• /
• pp.66-76
• /
• 2003

The arbitrary V-notched crack problem is considered. The general expressions for the stress components on this problem are obtained as explicit series forms composed of independent unknown coefficients which are denoted by coefficients of eigenvector. For this results eigenvalue equation is performed first through introducing complex stress functions and applying the traction free boundary conditions. Next solving this equation, eigenvalues and corresponding eigenvectors are obtained respectively, and finally inserting these results into stress components, the general equations are obtained. These results are also shown to be applicable to the symmetric V-notched crack or straight crack. It can be shown that this solutions are composed of the linear combination of Mode I and Mode II solutions which are obtained from different characteristic equations, respectively. Through performing asymptotic analysis for stresses, the stress intensity factor is given as a closed form equipped with the unknown coefficients of eigenvector. In order to calculate the unknown coefficients. based on these general explicit equations, numerical programming using the overdetermined boundary collocation method which is algorithmed originally by Carpenter is also worked out. As this programming requires the input data, the commercial FE analysis for stresses is performed. From this study, for some V-notched problems, unknown coefficients can be calculated numerically and also fracture parameters are determined.

• Industrial Engineering and Management Systems
• /
• v.11 no.4
• /
• pp.310-330
• /
• 2012

Scheduling is an important tool for a manufacturing system, where it can have a major impact on the productivity of a production process. In manufacturing systems, the purpose of scheduling is to minimize the production time and costs, by assigning a production facility when to make, with which staff, and on which equipment. Production scheduling aims to maximize the efficiency of the operation and reduce the costs. In order to find an optimal solution to manufacturing scheduling problems, it attempts to solve complex combinatorial optimization problems. Unfortunately, most of them fall into the class of NP-hard combinatorial problems. Genetic algorithm (GA) is one of the generic population-based metaheuristic optimization algorithms and the best one for finding a satisfactory solution in an acceptable time for the NP-hard scheduling problems. GA is the most popular type of evolutionary algorithm. In this survey paper, we address firstly multiobjective hybrid GA combined with adaptive fuzzy logic controller which gives fitness assignment mechanism and performance measures for solving multiple objective optimization problems, and four crucial issues in the manufacturing scheduling including a mathematical model, GA-based solution method and case study in flexible job-shop scheduling problem (fJSP), automatic guided vehicle (AGV) dispatching models in flexible manufacturing system (FMS) combined with priority-based GA, recent advanced planning and scheduling (APS) models and integrated systems for manufacturing.

• Journal of Intelligence and Information Systems
• /
• v.4 no.2
• /
• pp.23-34
• /
• 1998

Travel time forecasting, especially public bus travel time forecasting in urban areas, is a difficult and complex problem which requires a prohibitively large computation time and years of experience. As the network of target area grows with addition of streets and lanes, computational burden of the forecasting systems exponentially increases. Even though the travel time between two neighboring intersections is known a priori, it is still difficult, if not impossible, to compute the travel time between every two intersections. For the reason, previous approaches frequently have oversimplified the transportation network to show feasibilities of the problem solving algorithms. In this paper, forecasting of the travel time between every two intersections is attempted based on travel time data between two neighboring intersections. The time stamps data of public buses which recorded arrival time at predetermined bus stops was extensively collected and forecast. At first, the time stamp data was categorized to eliminate white noise, uncontrollable in forecasting, based on wavelet conversion. Then, the radial basis neural networks was applied to remaining data, which showed relatively accurate results. The success of the attempt was confirmed by the drastically reduced relative error when the nodes between the target intersections increases. In general, as the number of the nodes between target intersections increases, the relative error shows the tendency of sharp increase. The experimental results of the novel approaches, based on wavelet conversion and neural network teaming mechanism, showed the forecasting methodology is very promising.