• 수산해양교육연구
• /
• 제29권1호
• /
• pp.128-136
• /
• 2017

The purpose of this research is to analyze the effects of smart learning in both general education and fisheries & marine education through meta-analysis. To find the effects size, we had collected 112 studies from graduation theses and journal articles. Followings are the results of the research: (a) Smart learning turns out to be more statistically effective comparing to traditional education. The total effect size of smart learning is .768 and the value of U3 is 61.50%. (b) There is no significant difference between general education and fisheries & marine education in the view of effect size. (c) There is a significant difference in subjects, type of publication, and size of members in experimental group. High school student group has the most effect size of smart learning.

• 에너지공학
• /
• 제26권3호
• /
• pp.11-29
• /
• 2017

인공지능 특히 심층신경망기계학습기법(딥러닝)의 제조업분야에서의 이용이 효율적이며 실용적일 수 있다는 인식이 넓게 수용되고 있다 이 보고서는 최근의 신경망기계학습 개발환경을 개관하고 제조업분야에서 활용되고 있는 딥 러닝기술을 개관한다.

• 한국산업정보학회논문지
• /
• 제1권1호
• /
• pp.153-176
• /
• 1996

The new field of learning control devleops controllers that learn to improve their performance at executing a given task, based on experience performing this task. the simplest forms of learning control are based on the same concepts as integral control, but operating in the domain of the repetitions of the task. This paper studies the use of such controllers ina decentralized system, such as a robot with the controller for each link acting independently. The basic result of the paper is to show that stability of the learning controllers for all subsystems when the coupling between subsystems is turned off, assures stability of the decentralized learning in the coupled system, provided that the sample time in the digital learning controller is sufficiently short.

• International journal of advanced smart convergence
• /
• 제5권4호
• /
• pp.32-39
• /
• 2016

Machine learning is a field of artificial intelligence (AI), and a technology that collects, forecasts, and analyzes securities data is developed upon machine learning. The difference between using machine learning and not using machine learning is that machine learning-seems similar to big data-studies and collects data by itself which big data cannot do. Machine learning can be utilized, for example, to recognize a certain pattern of an object and find a criminal or a vehicle used in a crime. To achieve similar intelligent tasks, data must be more effectively collected than before. In this paper, we propose a method of effectively collecting data.

• 경영과정보연구
• /
• 제14권
• /
• pp.79-99
• /
• 2004

Cyber education system service is in the field of software service which is highlighted after the latter half of 1990'. But the progress of this service is impeded by the lack of back office which contributes to the evaluation of learning achievement and the management of learning progress. This article points out the problem of current back office which is the most important in the cyber education system, and focuses on the new intelligent learning achievement evaluation module. First, we define the cause and effect between the learning stages using by fuzzy implication which is the important part of fuzzy theory. Next, we suggest the model which generates the results of the learning achievement evaluation. This model, suggested by this article, may contribute to the development of the cyber education system by improving the current on-line education service.

• 한국공간구조학회논문집
• /
• 제19권1호
• /
• pp.93-100
• /
• 2019

There has been considerable recent interest in deep learning techniques for structural analysis and design. However, despite newer algorithms and more precise methods have been developed in the field of computer science, the recent effective deep learning techniques have not been applied to the damage detection topics. In this study, we have explored the structural damage detection method of truss structures using the state-of-the-art deep learning techniques. The deep neural networks are used to train knowledge of the patterns in the response of the undamaged and the damaged structures. A 31-bar planar truss are considered to show the capabilities of the deep learning techniques for identifying the single or multiple-structural damage. The frequency responses and the elasticity moduli of individual elements are used as input and output datasets, respectively. In all considered cases, the neural network can assess damage conditions with very good accuracy.

• 전자통신동향분석
• /
• 제36권5호
• /
• pp.82-91
• /
• 2021

This study reviews application of data-driven anomaly detection techniques to the aviation domain. Recent advances in deep learning have inspired significant anomaly detection research, and numerous methods have been proposed. However, some of these advances have not yet been explored in aviation systems. After briefly introducing aviation safety issues, data-driven anomaly detection models are introduced. Along with traditional statistical and well-established machine learning models, the state-of-the-art deep learning models for anomaly detection are reviewed. In particular, the pros and cons of hybrid techniques that incorporate an existing model and a deep model are reviewed. The characteristics and applications of deep learning models are described, and the possibility of applying deep learning methods in the aviation field is discussed.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.370-373
• /
• 2022

최근 Tensorflow나 Pytorch, Keras 같은 여러가지의 딥러닝 프레임워크 모델들이 나왔다. 또한 이미지 인식에 Tensorflow, Pytorch, Keras 같은 프레임 워크를 이용하여 CNN(Convolutional Neural Network)을 적용시켜 이미지 분류에서의 최적화 모델을 주로 이용한다. 본 논문에서는 딥러닝 이미지 인식분야에서 가장 많이 사용하고 있는 파이토치와 텐서플로우의 프레임 워크를 CNN모델에 학습을 시킨 결과를 토대로 두 프레임 워크를 비교 분석하여 이미지 분석할 때 최적화 된 프레임워크를 도출하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.9-11
• /
• 2022

Applying Reinforcement Learning in everyday applications and varied environments has proved the potential of the of the field and revealed pitfalls along the way. In robotics, a learning agent takes over gradually the control of a robot by abstracting the navigation model of the robot with its inputs and outputs, thus reducing the human intervention. The challenge for the agent is how to implement a feedback function that facilitates the learning process of an MDP problem in an environment while reducing the time of convergence for the method. In this paper we will implement a reward shaping system avoiding sparse rewards which gives fewer data for the learning agent in a ROS environment. Reward shaping prioritizes behaviours that brings the robot closer to the goal by giving intermediate rewards and helps the algorithm converge quickly. We will use a pseudocode implementation as an illustration of the method.

• Educational Technology International
• /
• 제9권2호
• /
• pp.1-15
• /
• 2008

One of the challenges that online learners face is feeling of isolation and diminishing desire of maintaining active participation during e-learning. Social presence, that is considered to be a vital factor in e-learning, is recently started to receive a support from the field. Although research indicated a significant role of social presence in both learning process and learning outcome, there is no widely accepted measurement scale of social presence. This study, therefore, developed a new scale to measure social presence based on the existing theories and validated it against 723 participants. Nineteen self-report items with three dimensions, co-presence, influence, and cohesiveness, were identified and validated using Exploratory Factor Analysis (EFA) in a preliminary and a follow-up study.