• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.117-129
• /
• 2024

This paper introduces collective navigation through a narrow gap using a curriculum-based deep reinforcement learning algorithm for a swarm of unmanned aerial vehicles (UAVs). Collective navigation in complex environments is essential for various applications such as search and rescue, environment monitoring and military tasks operations. Conventional methods, which are easily interpretable from an engineering perspective, divide the navigation tasks into mapping, planning, and control; however, they struggle with increased latency and unmodeled environmental factors. Recently, learning-based methods have addressed these problems by employing the end-to-end framework with neural networks. Nonetheless, most existing learning-based approaches face challenges in complex scenarios particularly for navigating through a narrow gap or when a leader or informed UAV is unavailable. Our approach uses the information of a certain number of nearest neighboring UAVs and incorporates a task-specific curriculum to reduce learning time and train a robust model. The effectiveness of the proposed algorithm is verified through an ablation study and quantitative metrics. Simulation results demonstrate that our approach outperforms existing methods.

• Journal of Korean society of Dental Hygiene
• /
• v.15 no.2
• /
• pp.303-310
• /
• 2015

Objectives: The purpose of this study was to examine the influence of cooperative learning on the learning attitude and self-directed learning capability of learners. Methods: The subjects were 50 sophomores enrolled in cooperative learning for 12-week period from March to June, 2014. A self-reported questionnaire was completed by the subjects. The instruments were 16 questions of learning attitude, 32 questions of self-directed learning, academic achievement, and 12 questions of satisfaction with instruction by Likert 5 scale. Cronbach's alpha was 0.84 in the previous study and 0.78 in this study. Self-directed learning was modified by Yoo and Cheong. Cronbach's alpha of self-directed learning was 0.86 in this study. Academic achievement was assessed by before and after the cooperative learning class. Cronbach's alpha was 0.95 in this study. Their learning attitude and self-directed learning capability were evaluated before and after the cooperative learning, and their satisfaction with the instruction and academic achievement were assessed by the written examination. Results: The score of learning attitude increased from 2.89 in the pretest to 3.38 in the posttest. The self-directed learning of the students increased from 2.98 in the pretest to 3.48 in the posttest. The academic achievement of students also increased from 82.0 in the pretest to 85.2 in the posttest. The satisfaction with instruction was 4.24 of Likert 5 scale. There were significant differences in satisfaction with instruction, cooperative learning and academic achievement. Conclusions: It is important to develop the cooperative learning program linked to self-directed learning for the dental hygiene students continuously. This study will provide the basic data and information for the development of new teaching methods for the dental hygiene.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.05a
• /
• pp.39-42
• /
• 2006

I analyzed the results of the influences the community activities will have on students' participation and how much these influences will satisfy students in terms of learning in an e-learning-based environment. These results were based on former studies on this topic. I summarized the characteristics of community activities, the methods for motivating learning desire, and students' participation in the learning session. I found out that community activities can form intimacy, and that using cell phone text messages (SMS) and emails as learning methods can be a factor in students' participation.

• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.97-101
• /
• 2004

This paper is about the use of existing evaluation methods, which evaluate learning determined by the score of an exam, which is either a multiple-choice type or single choice type question. These scores don't show the objective evaluations that cause some negative opinions about the scores. In this paper, we propose that the evaluation of the methods of self-directed learning use the triangle-type function of the fuzzy theory so that the learner can objectively evaluate their own learning ability. The proposed method classifies the result of learning into three fuzzy grades to calculate membership, and evaluate the result of an exam according to the final fuzzy grade degree as applied to the fuzzy grade sheets.

• Educational Technology International
• /
• v.21 no.2
• /
• pp.155-191
• /
• 2020

The aim of this study was to examine the trends (e.g., the distribution of the studies by year, country, research methods, and participants' education level) and fundamental findings [e.g., interaction in Virtual Reality (VR) environments, educational content through VR and Augmented Reality (AR) technologies, learning environment in AR, etc.] regarding immersive learning technologies such as VR and AR in English Language Teaching (ELT) between 2010 and 2019. Employing a systematic review research methodology, data was gathered from 59 academic articles published in the following databases: EBSCOhost, ERIC, Web of Science, and Taylor & Francis. The studies were analyzed using a content analysis approach, and findings demonstrated that immersive learning technologies in ELT came to prominence in 2017. Mixed methods research was the most widely employed research method. The most studied language skill was vocabulary for AR and speaking for VR. The results also revealed advantages and challenges with regards to the use of immersive learning technologies in ELT. Further analysis illustrated the findings related to characteristics of immersive learning technologies in ELT. Based on this review, research and design implications for researchers and practitioners are presented.

• The Journal of Korean Association of Computer Education
• /
• v.20 no.5
• /
• pp.15-33
• /
• 2017

The 2015 revised educational curricula focused on creative and convergent student education, so the importance of informatics education is arising along with emphases on its teaching and learning methods. This study has analyzed the research trend of teaching and learning methods and suggested their implications by selecting 179 studies of same keyword searching from 2000 to the present years and classifying them into 16 categories. This analysis showed that problem based learning was the most researched topic on these subjects, while unplugged learning, Creative Problem Solving model and peer teaching were among the actively studied topics. In the content domain of informatics curriculum, the problem solution and programming was most researched. This study is expected to suggest implications for not only studying informatics education research but also selecting teaching and learning methods in the field of class for teachers.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.388-394
• /
• 2001

Reinforcement learning is a kind of unsupervised learning methods that an agent control rules from experiences acquired by interactions with environment. The eligibility is used to resolve the credit-assignment problem which is one of important problems in reinforcement learning, Conventional eligibilities such as the accumulating eligibility and the replacing eligibility are ineffective in use of rewards acquired in learning process, since on1y one executed action for a visited state is learned. In this paper, we propose a new eligibility, called the distributed eligibility, with which not only an executed action but also neighboring actions in a visited state are to be learned. The fuzzy Q-learning algorithm using the proposed eligibility is applied to a cart-pole balancing problem, which shows the superiority of the proposed method to conventional methods in terms of learning speed.

• Journal of East-West Nursing Research
• /
• v.16 no.2
• /
• pp.96-104
• /
• 2010

Purpose: This research is a case study on a problem-based learning (PBL) model with blended learning in a nursing college. Methods: The target students were nursing sophomores in a nursing college who agreed to participate in a blended learning course and to be subjects in this study for 15 weeks. The questionnaires developed by Baek (2003) and Lee (2007) were modified and applied to collect data. Results: The students' satisfaction with the blending learning was the highest in the item "Online community activities were helpful in enhancing knowledge." The level of satisfaction with PBL was the highest in the item "It was helpful to listen my classmates' opinions rather than thinking all by myself." Conclusion: This study is suggestive that blended learning is effective to improve learning satisfaction by reinforcing practicality of face-to-face study to online learning. Various learning methods based on students' demands and preferences should be applied in nursing education.

• Journal of Distribution Science
• /
• v.15 no.8
• /
• pp.65-73
• /
• 2017

Purpose - Although e-learning has this advantage, currently many organizations have failed to recognize the necessity for basic e-learning educational training. It follows that practitioners working in the above organizations face the difficulty of having to find educational training processes of boosting their capabilities by themselves, rather than being able to utilize the educational training processes offered by e-learning. So of their own accord, learners have considered the necessity of information relating to being able to choose between high quality educational training processes. The purpose of this study is to propose opening e-learning content information for enabling an efficient choice of learning processes related to e-learning. Research design, data, and methodology - To pinpoint the items of e-learning content information, the study was initiated according to the following process. First, information relating to e-learning content (offered on e-learning websites) was researched. Second, based on the items of information which emerged from the research, selection and validity verification took place with 5 e-learning specialists as the subjects. Third, the opinions of adult learners at K University were collated relating to the items of information which emerged from the research. Results - The e-learning content information was comprised of 16 items in order to improve the choosing process for learner's e-learning contents. The analysis results showed that when learners were choosing e-learning processes, the most highly considered item was 'mobile support' (4.35). Following this (in order) were 'tuition fees' (4.30), 'certificate issuing' (4.23), and 'awareness of educational institution' (4.18). The least considered items were 'recruiting learners' (3.01) and 'tutor support' (3.18). Conclusions - The 16 items of e-learning content information in this study, were deemed to be helpful to learners in providing them with a choice of desirable e-learning process when this process was offered to them. Following this, there is a need for service institutions offering e-learning processes to make public the information suggested by this study. Research into educational methods additionally points to a necessity for not only e-learning forms, but also offline educational methods and a combination of blended learning to be offered and run parallel to e-learning.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.635-642
• /
• 2003

Reinforcement learning got successful results in a lot of applications such as control and scheduling. Various function approximation methods have been studied in order to improve the learning speed and to solve the shortage of storage in the standard reinforcement learning algorithm of Q-Learning. Most function approximation methods remove some special quality of reinforcement learning and need prior knowledge and preprocessing. Fuzzy Q-Learning needs preprocessing to define fuzzy variables and Local Weighted Regression uses training examples. In this paper, we propose a function approximation method, Fuzzy Q-Map that is based on on-line fuzzy clustering. Fuzzy Q-Map classifies a query state and predicts a suitable action according to the membership degree. We applied the Fuzzy Q-Map, CMAC and LWR to the mountain car problem. Fuzzy Q-Map reached the optimal prediction rate faster than CMAC and the lower prediction rate was seen than LWR that uses training example.