• Journal of Platform Technology
• /
• 제10권3호
• /
• pp.51-59
• /
• 2022

최근 혁신적으로 발전하고 있는 기계학습은 다양한 최적화 문제를 해결할 수 있는 중요한 기술이 되었다. 본 논문에서는 기계학습을 활용하여 이종망의 채널 공용화 문제를 해결하는 최신 연구 논문들을 소개하고 주된 기술의 특성을 분석하여 향후 연구 방향에 대해 가이드를 제시한다. 기존 연구들은 대체로 온라인 및 오프라인으로 빠른 학습이 가능한 Q-learning을 활용하는 경우가 많았다. 반면 다양한 공존 시나리오를 고려하지 않거나 망 성능에 큰 영향을 줄 수 있는 기계학습 컨트롤러의 위치에 대한 고려는 제한적이었다. 이런 단점을 극복할 수 있는 유력한 방안으로는 ITU에서 제안한 기계학습용 논리적 망구조를 기반으로 망 환경 변화에 따라 기계학습 알고리즘을 선택적으로 사용할 수 있는 방법이 있다.

• 한국초등과학교육학회지:초등과학교육
• /
• 제19권1호
• /
• pp.85-99
• /
• 2000

Researches have shown that learning science frequently requires the process of conceptual change. As a result, many of the constructivist teaching and loaming approaches focus on this kind of loaming. In approaches that focus on conceptual change, cognitive conflict strategies play a key role. Students, however, still have much difficulty in loaming science. Theoretically, it underlies Piaget's genetic epistemology in which disequilibration demands an interplay between assimilation and accommodation until equilibrium is restored. Also, radical constructivism has its roots in a variety of disciplines, but has been most profoundly influenced by the theories of lean Piaget as interpreted and extended by Glasersfeld. This study is intended to interpret the conceptual change from radical constructivist perspective and explain difficulties of conceptual change which students have in learning science.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
• /
• pp.75-77
• /
• 1998

Perhaps one of the most versatile approaches to learning in practical domains lies in case based reasoning. To date, however, most case based reasoning systems have tended to focus on relatively simple domains. The current study involves the development of a decision support system for a complex production process with a limited database. This paper presents a set of critical issues underlying CBR, then explores their consequences for a complex domain. Finally, the performance of the system is examined for resolving various types of quality control problems.

• 전자통신동향분석
• /
• 제35권4호
• /
• pp.81-90
• /
• 2020

The use of machine learning technologies such as deep and reinforcement learning has proliferated in various domains with the advancement of deep neural network studies. To make the learning successful, both big data acquisition and fast processing are required. However, for some physical world applications such as autonomous drone flight, it is difficult to achieve efficient learning because learning with a premature A.I. is dangerous, cost-ineffective, and time-consuming. To solve these problems, simulation-based approaches can be considered. In this study, we analyze recent trends in drone simulation technologies and compare their features. Subsequently, we introduce Octopus, which is a highly precise and scalable drone simulator being developed by ETRI.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1228-1248
• /
• 2020

Steganalysis & steganography have witnessed immense progress over the past few years by the advancement of deep convolutional neural networks (DCNN). In this paper, we analyzed current research states from the latest image steganography and steganalysis frameworks based on deep learning. Our objective is to provide for future researchers the work being done on deep learning-based image steganography & steganalysis and highlights the strengths and weakness of existing up-to-date techniques. The result of this study opens new approaches for upcoming research and may serve as source of hypothesis for further significant research on deep learning-based image steganography and steganalysis. Finally, technical challenges of current methods and several promising directions on deep learning steganography and steganalysis are suggested to illustrate how these challenges can be transferred into prolific future research avenues.

• 대한수학교육학회지:수학교육학연구
• /
• 제8권2호
• /
• pp.425-437
• /
• 1998

The difference between "open" mathematics education and education of "open mathematics" arises from the difference of tearcher's understanding on the meaning of "teaching and learning mathematics" in the paper. Discusses the agreements and the worries of the researchers, the teachers, the students in korea, about open educationism, firstly, Three practical cases in mathematics lesson in korea are reviewed and analyzed in the respect of learning principles, secondly. Thirdly, the paper examines how to be modified two main learning principles, individualised learning and self-regulation of learning by teachers in the process of instruction. Finally, open mathematics advocated by Fisher(1984) and closed mathematics are compared especially in the probability unit. It concludes that the open approaches in mathematics lessons in korea need to improve with respect to teacher's attitude for didactic contents or mathematical knowledge. It is argued that teacher's open or flexible understanding of mathematical knowledge is no less important than that of their pupils.ant than that of their pupils.

• 대한임베디드공학회논문지
• /
• 제16권5호
• /
• pp.215-223
• /
• 2021

3D data can be categorized into two parts : Euclidean data and non-Euclidean data. In general, 3D data exists in the form of non-Euclidean data. Due to irregularities in non-Euclidean data such as mesh and point cloud, early 3D deep learning studies transformed these data into regular forms of Euclidean data to utilize them. This approach, however, cannot use memory efficiently and causes loses of essential information on objects. Thus, various approaches that can directly apply deep learning architecture to non-Euclidean 3D data have emerged. In this survey, we introduce various deep learning methods for mesh and point cloud data. After analyzing the operating principles of these methods designed for irregular data, we compare the performance of existing methods for shape classification and segmentation tasks.

• Korean Journal of Radiology
• /
• 제21권10호
• /
• pp.1126-1137
• /
• 2020

Imaging plays a key role in the management of brain tumors, including the diagnosis, prognosis, and treatment response assessment. Radiomics and deep learning approaches, along with various advanced physiologic imaging parameters, hold great potential for aiding radiological assessments in neuro-oncology. The ongoing development of new technology needs to be validated in clinical trials and incorporated into the clinical workflow. However, none of the potential neuro-oncological applications for radiomics and deep learning has yet been realized in clinical practice. In this review, we summarize the current applications of radiomics and deep learning in neuro-oncology and discuss challenges in relation to evidence-based medicine and reporting guidelines, as well as potential applications in clinical workflows and routine clinical practice.

• 한국과학교육학회지
• /
• 제27권6호
• /
• pp.519-528
• /
• 2007

Although science continues to be a key subject in the education of the majority of young people throughout the world, it is becoming increasingly clear that school science is failing to win the hearts and minds of many of today's younger generation. Researchers have begun to look at ways in which the learning that takes place in museums, science centres and other informal settings can add value to science learning in schools. Four case studies are used to illustrate the potential afforded by informal contexts to research aspects of science learning. The case studies involve: the European Union PENCIL (Permanent European Resource Centre for Informal Learning) project (a network of 14 museums and science centres working with schools to enhance learning in maths and science); a large natural history museum in England; the Tate Modernart gallery in London, and the Outdoor Classroom Action Research Project which involved researchers working in school grounds, field centres and farms. The range of research questions that were asked are examined as are the methodological approaches taken and the methods used to collect and analyse data. Lessons learned from the studies about research in the informal contexts are discussed critically.

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.220-225
• /
• 2021

Human population growth rate is an important parameter for real-world planning. Common approaches rely upon fixed parameters like human population, mortality rate, fertility rate, which is collected historically to determine the region's population growth rate. Literature does not provide a solution for areas with no historical knowledge. In such areas, machine learning can solve the problem, but a multitude of machine learning algorithm makes it difficult to determine the best approach. Further, the missing feature is a common real-world problem. Thus, it is essential to compare and select the machine learning techniques which provide the best and most robust in the presence of missing features. This study compares 17 machine learning techniques (base learners and ensemble learners) performance in predicting the human population growth rate of the country. Among the 17 machine learning techniques, random forest outperformed all the other techniques both in predictive performance and robustness towards missing features. Thus, the study successfully demonstrates and compares machine learning techniques to predict the human population growth rate in settings where historical data and feature information is not available. Further, the study provides the best machine learning algorithm for performing population growth rate prediction.