• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.679-680
• /
• 2008

When we apply the neural networks to applications, we need to select proper architecture of the network and the activation function of the network is one of most important characteristics. In this research, we propose a method to make a network using multiple activation functions. The performance of the proposed method is investigated through the computer simulations on various regression problems.

• 정보교육학회논문지
• /
• 제14권2호
• /
• pp.189-197
• /
• 2010

본 논문에서는 초등정보교육과정의 "문제해결방법과 절차" 영역에 필요한 알고리즘적 사고 문제 모델을 활용하고, 초등 로봇 프로그래밍 내용 요소를 적용하여 초등 로봇프로그래밍 알고리즘적 사고 문제를 제안하였다. 그리고 개발된 초등 로봇프로그래밍 알고리즘적 사고 문제들에 대해 실험 수업을 실시하여 알고리즘적 사고에 따른 답안들의 다양성과 효율성 및 개발된 문제들의 난이도 적절성에 대한 분석을 통해, 본 논문에서 제안된 문제들이 여러 형태의 답안이 도출될 수 있는 알고리즘적 사고의 다양성을 갖으며, 초등 단계에서 문제를 해결하는데 큰 어려움을 느끼지 않는 적절한 난이도를 나타내고 있음을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.129-134
• /
• 2022

The primary goal of any classroom is effective teaching and student learning, with an emphasis on changing negative students' behaviors into positive ones. This change can occur when students' behavior is always at the forefront of teachers' educational goals. The current study aimed to reveal the experiences of special education teachers in dealing with the behavioral problems that students with disabilities show by identifying behavioral problems among students with disabilities and investigating the efficacy of the application of behavior modification plans and strategies designed to address the behavioral problems presented by students with disabilities. The researcher used a qualitative phenomenological approach, and the study tool consisted of semi-structured interviews that consisted of (13) questions directed to (10) special education male and female teachers who work in special education centres and institutes. The data were analyzed using the thematic analysis method. The findings of the study showed that the most undesirable behaviors prevalent among students with disabilities in the classroom were aggression, bullying and ADHD. The actions taken by teachers in confronting these behaviors were not systematic and were carried out randomly, as no behavior modification plans were applied. The most important strategies used by teachers in facing behavioral problems were applied behavioral analysis (ABA) strategies such as reinforcement, punishment and ignoring. The results have many important implications for future practice, including the need to conduct practical training courses for special education teachers to implement behavior modification plans and develop methods of measuring inappropriate behavior.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1765-1794
• /
• 2019

Genetic Programming (GP) is an intelligence technique whereby computer programs are encoded as a set of genes which are evolved utilizing a Genetic Algorithm (GA). In other words, the GP employs novel optimization techniques to modify computer programs; imitating the way humans develop programs by progressively re-writing them for solving problems automatically. Trial programs are frequently altered in the search for obtaining superior solutions due to the base is GA. These are evolutionary search techniques inspired by biological evolution such as mutation, reproduction, natural selection, recombination, and survival of the fittest. The power of GAs is being represented by an advancing range of applications; vector processing, quantum computing, VLSI circuit layout, and so on. But one of the most significant uses of GAs is the automatic generation of programs. Technically, the GP solves problems automatically without having to tell the computer specifically how to process it. To meet this requirement, the GP utilizes GAs to a "population" of trial programs, traditionally encoded in memory as tree-structures. Trial programs are estimated using a "fitness function" and the suited solutions picked for re-evaluation and modification such that this sequence is replicated until a "correct" program is generated. GP has represented its power by modifying a simple program for categorizing news stories, executing optical character recognition, medical signal filters, and for target identification, etc. This paper reviews existing literature regarding the GPs and their applications in different scientific fields and aims to provide an easy understanding of various types of GPs for beginners.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권4호
• /
• pp.1481-1498
• /
• 2014

Automated activity monitoring has become important in many applications. In particular, automated monitoring is an important issue in large-scale management of group-housed livestock because it can save a significant part of farm workers' time or minimize the damage caused by livestock problems. In this paper, we propose an automated solution for measuring the daily-life activities of pigs by using video data in order to manage the group-housed pigs. Especially, we focus on the circadian rhythm of group-housed pigs under windowless and 24-hour light-on conditions. Also, we derive a cost-effective solution within the acceptable range of quality for the activity monitoring application. From the experimental results with the video monitoring data obtained from two pig farms, we believe our method based on circadian rhythm can be applied for detecting management problems of group-housed pigs in a cost-effective way.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.136-142
• /
• 2024

Haze is a very common phenomenon that degrades or reduces the visibility. It causes various problems where high quality images are required such as traffic and security monitoring. So haze removal from images receives great attention for clear vision. Due to its huge impact, significant advances have been achieved but the task yet remains a challenging one. Recently, different types of deep generative adversarial networks (GAN) are applied to suppress the noise and improve the dehazing performance. But it is unclear how these algorithms would perform on hazy images acquired "in the wild" and how we could gauge the progress in the field. This paper aims to bridge this gap. We present a comprehensive study and experimental evaluation on diverse GAN models in single image dehazing through benchmark datasets.

• East Asian mathematical journal
• /
• 제29권1호
• /
• pp.13-22
• /
• 2013

As a fuzzy counterpart of stochastic calculus, fuzzy calculus including Liu integral and Liu formula were introduced. In order to deal with the problems with several fuzzy dynamic factors, Liu process, Liu integral and Liu formula are extended to the case of multi-dimensional in this paper.

• Journal of the Korean Statistical Society
• /
• 제11권1호
• /
• pp.12-24
• /
• 1982

Selection procedures are proposed for selecting the 'best' industrial process with the smallest fraction defective. For normally distributed industrial processes, this is equivalent to selecting in terms of coefficients of variation. For the case of known vairances, selection procedures by Bechhofer (1954), and Bechhofer and Turnball (1978) are appropriate. We treat this problem for the case of uknown variances with or without reference to a standard. The large sample solutions of design constants are tabulated and the performance of these approximate solutions are investigated.

• 한국경영과학회지
• /
• 제22권2호
• /
• pp.67-78
• /
• 1997

In general, two types fuzziness of human judgements should be incorporated in multiobjective programming problems. One is the expert's ambigjous understanding of the nature of the parameters in the problem formulation process and the other is the fuzzy goals of the decision maker for each of the objective functions. In this paper, we present a new interactive fuzzy approach for obtaining the satisficing solution which efficiently reflect both types of fuzziness. An illustrative numerical example nonlinear programming problems with fuzzy parameters is demonstrated along with the corresponding computer outputs.

• 공학교육연구
• /
• 제19권1호
• /
• pp.61-66
• /
• 2016

To enhance the university-industry collaboration, a novel program named as Internship & Capstone Design Integrated program (ICIP) is developed by Dongguk University. Senior students must take one Capstone design class for graduation. By participating in summer Internship and one-year Capstone Design work, practical problems given by businesses are solved. The ICIP is a Project and Internship-based course. By participating in summer internship and one-year Capstone Design work, practical problems given by businesses are solved. The internship course requires students to work in teams under mentors who work in the partner company proposed project themes. Students apply their academic experiences in constructing real projects at work under the supervision of their site mentors and academic advisor. In this regard, this study attempts to present a case study on the assessment of program outcomes using the Internship.