• The Journal of Korean Association of Computer Education
• /
• v.11 no.4
• /
• pp.23-36
• /
• 2008

It's known by recent surveys that many students have difficulty in understanding the concepts of programming algorithms, and don't feel interested in learning them. Dynamic programming, one of the most important and widely-used algorithms in computer science, is especially feared by students and unlike other algorithms, it also requires understanding of the process of problem solving and storage space design as well as basic principles of the algorithm. And so it has not been properly covered in classes. In this paper, we developed a visual simulator to solve the above problems in learning dynamic programming. This learning simulator is designed for students to run the algorithms themselves and learn how it works by visualizing each step of dynamic programming and corresponding states of storage space.

• Communications for Statistical Applications and Methods
• /
• v.10 no.3
• /
• pp.845-857
• /
• 2003

We explore the use of genetic programming to evolve decision trees directly for classification problems with both discrete and continuous predictors. We demonstrate that the derived hypotheses of standard algorithms can substantially deviated from the optimum. This deviation is partly due to their top-down style procedures. The performance of the system is measured on a set of real and simulated data sets and compared with the performance of well-known algorithms like CHAID, CART, C5.0, and QUEST. Proposed algorithm seems to be effective in handling problems caused by top-down style procedures of existing algorithms.

• 전기의세계
• /
• v.30 no.6
• /
• pp.375-385
• /
• 1981

New algorithms are derived for nonlinear programming problems which are characterized by their large variables and equality and inequality constraints. The algorithms are based upon the introduction of the Dependent-Variable-Elimination method, Independent-Variable-Reduction method, Optimally-Ordered-Triangular-Factorization method, Equality-Inequality-Sequential-Satisfaction method, etc. For a case study problem relating to the optimal determination of load flow in a 10-bus, 13-line sample power system, several approaches are undertaken, such as SUMT, Lagrange's Multiplier method, sequential applications of linear and quadratic programming method. For applying the linear programming method, the conventional simplex algorithm is modified to the large-system-oriented one by the introduction of the Two-Phase method and Variable-Upper-Bounding method, thus resulting in remarkable savings in memory requirements and computing time. The case study shows the validity and effectivity of the algorithms presented herein.

• The Journal of Korean Association of Computer Education
• /
• v.18 no.6
• /
• pp.23-31
• /
• 2015

The main aim in software education is to improve problem-solving ability based on computational thinking with the healthy information ethics. For this purpose, many institutions have attempted various educational programs such as Educational Programming Language, Physical Computing, and Robot education. However, it is possible to obscure the essence of computer education for computational thinking if the computer education focuses on using certain special education programming language and products. Therefore, this paper suggests a method of algorithm education using RAPTOR which is a visual programming development environment and is based on flowcharts. In order to verify the effectiveness of the algorithms education using the RAPTOR, 16 high-school students were applied to an educational program for twelve hours on five steps and then we obtained positive results.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.420-426
• /
• 1998

Evolutionary algorithms are probabilistic optimization algorithms based on the model of natural evolution. Recently the efforts to improve the performance of evolutionary algorithms have been made extensively. In this paper, we introduce the research for improving the convergence rate and search faculty of evolution algorithms by using reinforcement learning. After providing an introduction to evolution algorithms and reinforcement learning, we present adaptive genetic algorithms, reinforcement genetic programming, and reinforcement evolution strategies which are combined with reinforcement learning. Adaptive genetic algorithms generate mutation probabilities of each locus by interacting with the environment according to reinforcement learning. Reinforcement genetic programming executes crossover and mutation operations based on reinforcement and inhibition mechanism of reinforcement learning. Reinforcement evolution strategies use the variances of fitness occurred by mutation to make the reinforcement signals which estimate and control the step length.

• The Journal of Korean Association of Computer Education
• /
• v.14 no.5
• /
• pp.1-8
• /
• 2011

The purpose of this study is to explore vocational high school students' understanding levels and misconceptions regarding the time-efficiency of algorithms. In this study, a questionnaire with nine questions was developed. The questionnaire is base on three misconceptions about the time-efficiency of algorithms that are examined through prior studies. The questionnaire was applied to 51 students who completed a programming course. The result shows that the students didn't sufficiently understand the concept of time-efficiency of algorithms and several common misconceptions appeared repeatedly. Finally, teaching strategies using simulation and assesment framework for algorithm's time-efficiency were presented and some recommendations were suggested for refining the curriculum relating computer programming and algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.292-297
• /
• 1999

Evolving in artificial agent is an extremely difficult problem, but on the other hand, a challenging task. At present the studies mainly centered on single agent learning problem. In our case, we use simulated soccer to investigate multi-agent cooperative learning. Consider the fundamental differences in learning mechanism, existing reinforcement learning algorithms can be roughly classified into two types-that based on evaluation functions and that of searching policy space directly. Genetic Programming developed from Genetic Algorithms is one of the most well known approaches belonging to the latter. In this paper, we give detailed algorithm description as well as data construction that are necessary for learning single agent strategies at first. In following step moreover, we will extend developed methods into multiple robot domains. game. We investigate and contrast two different methods-simple team learning and sub-group loaming and conclude the paper with some experimental results.

• The Journal of Korean Association of Computer Education
• /
• v.22 no.6
• /
• pp.11-18
• /
• 2019

Software education is required from elementary schools to prepare students for the fourth industrial revolution, which aims to improve algorithmic thinking. In general, teaching is divided into two stages: using a flowchart to design algorithms and implementing them through programming. However, converting a flowchart into code and checking the results in an educational programming tool is time consuming and requires additional programming activities. This study proposes a tangible coding tool that enables elementary students to convert algorithms designed at the unplugged activity into educational programming tool codes. This tool was developed in order for students to design algorithms at the level of assembling paper blocks and input them into a programming tool by taking a picture. Sixth graders were participated in this activity to evaluate its usability.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.400-404
• /
• 2004

There are many methods to find solutions for Integer Programming problems (IPs) such as the Branch-Bound philosophy or the Cutting Plane algorithm. However, most of them have a problem that is the explosion of sets in the computing process. In addition, GA is known as a heuristic search algorithm for solutions of optimization problems. It is started from a random initial guess solution and attempting to find one that is the best under some criteria and conditions. The paper will study an artificial intelligent method to solve IPs by using Genetic Algorithms (GAs). The original solution of this was presented in the papers of Fabricio Olivetti de Francaand and Kimmo Nieminen [2003]. However, both have several limitations which causes could be operations in GAs. The paper proposes a method to upgrade these operations and computational results are also shown to support these upgrades.

• Nuclear Engineering and Technology
• /
• v.48 no.2
• /
• pp.404-418
• /
• 2016

This paper presents a documentation and development method to facilitate the certification of scientific computing software used in the safety analysis of nuclear facilities. To study the problems faced during quality assurance and certification activities, a case study was performed on legacy software used for thermal analysis of a fuelpin in a nuclear reactor. Although no errors were uncovered in the code, 27 issues of incompleteness and inconsistency were found with the documentation. This work proposes that software documentation follow a rational process, which includes a software requirements specification following a template that is reusable, maintainable, and understandable. To develop the design and implementation, this paper suggests literate programming as an alternative to traditional structured programming. Literate programming allows for documenting of numerical algorithms and code together in what is termed the literate programmer's manual. This manual is developed with explicit traceability to the software requirements specification. The traceability between the theory, numerical algorithms, and implementation facilitates achieving completeness and consistency, as well as simplifies the process of verification and the associated certification.