• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2020-2037
• /
• 2017

In order to improve the energy efficiency of n-Epidemic routing protocol in opportunistic networks, in which a stable end-to-end forwarding path usually does not exist, a novel adjustment strategy for parameter n is proposed using learning atuomata principle. First, nodes dynamically update the average energy level of current environment while moving around. Second, nodes with lower energy level relative to their neighbors take larger n avoiding energy consumption during message replications and vice versa. Third, nodes will only replicate messages to their neighbors when the number of neighbors reaches or exceeds the threshold n. Thus the number of message transmissions is reduced and energy is conserved accordingly. The simulation results show that, n-Epidemic routing protocol with the proposed adjustment method can efficiently reduce and balance energy consumption. Furthermore, the key metric of delivery ratio is improved compared with the original n-Epidemic routing protocol. Obviously the proposed scheme prolongs the network life time because of the equilibrium of energy consumption among nodes.

• 한국산학기술학회논문지
• /
• 제9권6호
• /
• pp.1574-1580
• /
• 2008

본 논문에서는 외란이나 시스템의 파라미터 변동 및 불확실성 등이 존재하는 자동화 설비시스템을 강인하고 정밀하게 제어할 수 있도록 하기 위해 동적 신경망 처리기(DNP)인 신경망 제어기를 설계하였다. 자동화 설비시스템에서 부품의 조립, 가공 등 복잡하고 정교한 임무를 수행시키기 위해서는 end-effector의 이동경로 궤적에 대한 추적제어 뿐만 아니라 목표물에 대하여 접촉하는 힘의 궤적에 대한 추적 제어가 필수적이다. 또한 자동화 설비시스템에서 플랜트의 역기구학적인 좌표변환을 계산하기 위한 학습구조를 개발하였으며, DNP가 이용될 수 있는 예를 설명하였다. 제안된 동적 신경망인 DNP의 구조와 학습 알고리즘을 제시하고 컴퓨터 모의실험을 통해 학습 성능을 증명하였다.

• 한국음향학회지
• /
• 제42권6호
• /
• pp.536-543
• /
• 2023

다수의 화자가 존재하는 음성에서 "누가 언제 발화했는가?"에 대해 레이블링하는 화자 분할은 발화 중첩 구간에 대한 레이블링과 화자 분할 모델의 최적화를 위해 심층 신경망 기반의 종단 간 방법에 대해 연구되었다. 대부분 심층 신경망 기반의 종단 간 화자 분할 시스템은 음성의 각 프레임에서 발화한 모든 화자의 레이블들을 추정하는 다중 레이블 분류 문제로 분할을 수행한다. 다중 레이블 기반의 화자 분할 시스템은 임계값을 어떤 값으로 설정하는지에 따라 모델의 성능이 많이 달라진다. 본 논문에서는 임계값 없이 화자 분할을 수행할 수 있도록 단일 레이블 분류를 이용한 화자 분할 시스템에 대해 연구하였다. 제안하는 화자 분할 시스템은 기존의 화자 레이블을 단일 레이블 형태로 변환하여 모델의 출력으로부터 레이블을 바로 추정한다. 훈련에서는 화자 레이블 순열을 고려하기 위해 Permutation Invariant Training(PIT) 손실함수와 교차 엔트로피 손실함수를 조합하여 사용하였다. 또한 심층 구조를 갖는 모델의 효과적인 학습을 위해 화자 분할 모델에 잔차 연결 구조를 추가하였다. 실험은 Librispeech 데이터베이스를 이용해 화자 2명에 대한 시뮬레이션 잡음 데이터를 생성하여 사용하였다. Diarization Error Rate(DER) 성능 평가 지수를 이용해 제안한 방법과 베이스라인 모델을 비교 평가했을 때, 제안한 방법이 임계값 없이 분할이 가능하며, 약 20.7 %만큼 향상된 성능을 보였다.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.140-146
• /
• 2020

This study aimed to provide basic data for enhancing the structural relationship among learning motivation, learning confidence, critical thinking skill and problem-solving ability in junior high school students and factors influencing problem-solving ability, by closely examining them. To this end, it investigated the causality among variables, for 390 junior high school students in Gangwondo, based on the outcomes of a questionnaire survey conducted to verify the effectiveness of digital textbooks. Although learning motivation did not have a significant effect on critical thinking skill, learning confidence had a direct effect on it. In addition, learning motivation, learning confidence and critical thinking skill had direct effects on problem-solving ability. In order to enhance problem-solving ability, therefore, We may be necessary to make efforts to support learning capabilities and provide opportunities for them to experience rich learning and resources.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2018년도 추계 학술논문 발표대회
• /
• pp.69-70
• /
• 2018

With increased interest in the Fourth Industrial Revolution, there is also a growing interest in the innovation of college education. In this regard, this study aims to develop a learning model for building construction to nurture architectural engineers needed in the era of the Fourth Industrial Revolution. To this end, it analyzed the previous studies on the recent innovations in engineering education. Among the educational innovation methods presented in the previous research, a new learning model was derived by using the most suitable method for the building construction eduction. The derived learning model is a building construction learning model applying team-based learning and flipped learning. The learning model proposed in this study was developed as a learning method to nurture engineers needed in the future. Therefore, it is expected that this model can be utilized in the eduction of architectural engineering at universities in Korea.

• International Journal of Contents
• /
• 제15권4호
• /
• pp.59-64
• /
• 2019

In recent years, emotion recognition has been an interesting and challenging topic. Compared to facial expressions and speech modality, gesture-based emotion recognition has not received much attention with only a few efforts using traditional hand-crafted methods. These approaches require major computational costs and do not offer many opportunities for improvement as most of the science community is conducting their research based on the deep learning technique. In this paper, we propose an end-to-end deep learning approach for classifying emotions based on bodily gestures. In particular, the informative keyframes are first extracted from raw videos as input for the 3D-CNN deep network. The 3D-CNN exploits the short-term spatiotemporal information of gesture features from selected keyframes, and the convolutional LSTM networks learn the long-term feature from the features results of 3D-CNN. The experimental results on the FABO dataset exceed most of the traditional methods results and achieve state-of-the-art results for the deep learning-based technique for gesture-based emotion recognition.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권2호
• /
• pp.127-146
• /
• 2021

Research Purpose Advances in digital technology have facilitated the widespread adoption of online learning, which has become a substantial way of learning. Although digital immigrants have become a main group of users of learning online, there is a lack of understanding of their online learning. This study aims to explore digital immigrants' adoption of online learning from the goal-pursuit perspective to gain insight into how they use online learning. Research Method A laddering interview was conducted with 22 Korean adults to elicit their goals in online learning. Then, a means-end chain analysis was used to derive their hierarchical goal structure. Findings The results reveal digital immigrants' goal structure of online learning, consisting of four attributes of online learning (e.g., accessibility, diversity, up-to-dateness, and repeatability) and six goals (e.g., self-esteem, enjoyment, recognition, productivity, gaining insights, and positive relations). This study contributes to the literature by providing a rich picture of their use of online learning.

• East Asian mathematical journal
• /
• 제39권2호
• /
• pp.167-181
• /
• 2023

The purpose of this study is to confirm the possibility of whether learning using a math learning platform can be used to expand students' conceptual structure and to consider how to use it. To this end, first-year middle school students studied using a math learning platform. Then, the concept map created was compared and analyzed with the concept map created before learning to examine the change in the concept structure. The results of analyzing the concept map are as follows. First, the change in the hierarchical structure of the concept appeared as the division of the upper concept was subdivided. However, it has also been changed to comprehensively integrate and simplify higher concepts. The term-centered concept structure has changed to content-centered superordinate and subordinate concepts. In the concept structure, subordinate concepts linked to one higher concept were expanded and differentiated. Second, changes in the integrated structure did not form a linkage structure. The expansion of the integrated structure of concepts through learning using the learning platform was influenced by the composition of the learning contents designed in the learning platform.

• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제24권1호
• /
• pp.259-282
• /
• 2010

본 연구자들은 이 논문에서 다변수미적분학 수업에 적용한 변형 무어교수법(Modified Moore Method)을 소개하고, 이 교수법을 적용한 수업에서 학습에 대한 학생들의 인식변화와 학습 효과를 관찰하여 효과적인 교수 학습을 논의하였다. 본 연구는 3주 기간의 여름계절학기 강좌로 개설된 다변수미적분학 수업을 수강한 15명의 학생들을 대상으로 실시되었다. 학생들의 능동적 예습을 안내하기 위하여 주요 수학 개념에 관련된 단계별로 구조화된 발문 형식의 예습자료를 미리 제시하였다. 수업 중 학생들의 소그룹 협력학습 과정과 발표를 관찰하고, 매 수업 후반에 작성한 학생들의 강의일지와 학기말에 실시한 설문 조사를 분석한 결과에 의하면, 학생들은 스스로 탐구하여 발견하는 학습을 통하여 주제 개념에 대하여 보다 깊이 이해할 수 있음을 인식하게 되었고, 동료와의 토론 및 상호 가르침을 통하여 다양한 내용의 학습과 반성적 사고를 경험할 수 있었다.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.145-166
• /
• 2021

M-learning is one of the most important modern learning environments in developed countries, especially in the context of the COVID-19 pandemic. According to the Ministry of Education policies in Saudi Arabia, gender segregation in education reflects the country's religious values, which are a part of the national policy. Thus, it will help many in the target audience to accept online learning more easily in Saudi society. The literature review indicates the importance to use the UTAUT conceptual framework to study the level of acceptance through adding a new construct to the model which is Mobile Application Quality. The study focuses on the end user's requirements to use M-learning applications. It is conducted with a qualitative method to find out the students' and companies' opinions who working in the M-learning field to determine the requirements for the development of M-learning applications that are compatible with the aspirations of conservative societies.