• The Journal of Korean Association of Computer Education
• /
• v.5 no.1
• /
• pp.85-98
• /
• 2002

In this study, We are developed learner traits analysis and profile management software modules to develop learnable courseware fits to learner's individual traits in cyber learning system. We specified learner's personal information, performance information, preference information and portfolio information as learner's traits variables in this study, these four types of information are managed in learner profile management DB based on elaborate analysis to learner's traits. And we consists of curriculum sequencing module using high and low level sequencing technology, these are used in organizing learning contents sequencing with learning topic and specific learning task. The advice algorithm module developed based on adaptive navigational support and rule based technology. This Result of Research are able to be used for develop learnable courseware fits to learner's individual traits in cyber learning systems.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.139-146
• /
• 2002

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless these algorithms can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL) as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. In this paper we use the AMMQL algorithn as a learning method for dynamic positioning of the robot soccer agent, and implement a robot soccer agent system called Cogitoniks.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.434-437
• /
• 1999

The primary aim of this paper is to introduce and illustrate a radial basis function (RBF) modeling approach fur software module characterization, as an alternative to current techniques. The RBF model has been known to provide a rich analytical framework fur a broad class of so-called pattern recognition problems. Especially, it features both nonlinearity and linearity which in general are treated separately by its learning algorithm, leading to offer conceptual and computational advantages. Furthermore, our new modeling methodology fer determining model parameters has a sound mathematical basis and showed very interesting results in terms of model consistency as well as performance.

• International journal of advanced smart convergence
• /
• v.8 no.4
• /
• pp.75-81
• /
• 2019

Though recent advancement of deep learning methods have provided satisfactory results from large data domain, somehow yield poor performance on few-shot classification tasks. In order to train a model with strong performance, i.e. deep convolutional neural network, it depends heavily on huge dataset and the labeled classes of the dataset can be extremely humongous. The cost of human annotation and scarcity of the data among the classes have drastically limited the capability of current image classification model. On the contrary, humans are excellent in terms of learning or recognizing new unseen classes with merely small set of labeled examples. Few-shot learning aims to train a classification model with limited labeled samples to recognize new classes that have neverseen during training process. In this paper, we increase the backbone depth of the embedding network in orderto learn the variation between the intra-class. By increasing the network depth of the embedding module, we are able to achieve competitive performance due to the minimized intra-class variation.

• Management & Information Systems Review
• /
• v.14
• /
• 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.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.32 no.1
• /
• pp.51-61
• /
• 2018

This study aims to evaluate the student's satisfaction of clinical performance examination(CPX) and self-assessment in Korean medical curriculum. A questionnaire was given to clinical clerkship students of Pusan National University School of Korean medicine in this study. The items in this questionnaire covered overall evaluation of guidelines, module & learning environment, standardized patients, and self-assessment in CPX. Most of all students recognized CPX as a more effective learning method than any other method. Most students were satisfied with the module & learning environment, standardized patients, and self-assessment except the satisfaction for guidelines relationally. The results of this study demonstrated that the students had a high level of satisfaction in CPX. This study shows that CPX has been implemented into the Korean medical curriculum.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.175-177
• /
• 2022

This paper introduces a system that assists the blind to move to their destination, and compares the performance of 3-types of deep learning network (DNN) used in the system. The system is made up with a smartphone application that finds route from current location to destination using GPS and navigation API and a bus station installation module that recognizes and informs the bus (type and number) being about the board at bus stop using 3-types of DNN and bus information API. To make the module recognize bus number to get on, We adopted faster-RCNN, YOLOv4, YOLOv5s and YOLOv5s showed best performance in accuracy and speed.

• Journal of Korean Clinical Health Science
• /
• v.5 no.2
• /
• pp.850-863
• /
• 2017

Purpose. The purpose of this study was to investigate effects of preclinical OSCE(Objective Structured Clinical Evaluation) on knowledge, confidence in their Core fundamental nursing skills and self-efficacy in nursing students. Method. The research design was a one group pretest-posttest design and it was done to assess changes in knowledge, confidence in core fundamental nursing skills and self-efficacy from pre to the post-test which was given after the OSCE. Data were collected from March 5 to April 7, 2016 from 37 nursing students who were taking the 15-hours using OSCE learning module at one Gyeongbuk-do, P-city. This practicum was composed of 4 core fundamental nursing skills and 5 other fundamental nursing skills. The knowledge consisted of a 10-item by researchers and the confidence of core fundamental nursing skills consisted of an 9-item NRS and the self-efficacy consisted of a 17-item 5-point scale and measured in both the pretest and posttest. The collected data were analyzed with SPSS IBM 20.0 program for the frequency, percentage, x2-test, and paired t-test. Rusult. The results showed that although scores of knowledge of OSCE learning module were significanlty increased from 5.22 to 7.03(t=5.30, p<.001). There were significantly increased in scores of confidence in core fundamental nursing skills from 5.13 to 7.27(t=10.01, p<.001), In the sub-scales of each core fundamental nursing skills was scored the highest. otherwise, there was no significant difference in self-efficacy(t=1.42, p=.161). Conclusions. Based on the results, this study suggests that OSCE module development activities for nursing students in nursing education-learning in order to improve nursing skills.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.6 no.2
• /
• pp.390-405
• /
• 2000

PBL is a process and an effective educational tool that empower the student to be an active participant and emphasize a clinical context for learning, developing skills in working with a group, and encouraging self-directed study. The purpose of this study was to develop the PBL module based on lung cancer case, and to evaluate after implementation. The data on lung cancer patients at C university hospital in K city were collected from interviews and nursing records in June, 1999. A PBL module was developed including situation scenarios, timetable and tutor guide. PBL course was conducted at C university for short term period (3 days) in August, 2000. Fourteen nursing students at C college were participated in this study and they were divided into two small groups. I explained them about the PBL course through a preparatory meeting. At a stage of implementation, two groups went through the same process consisting of seven steps with group meetings and self-directed study. Their performances of identifying, stating problems and presenting referred resources were evaluated and supervised by researcher. The PBL course was evaluated by them with questionnaire and essay. Most students responded positively about PBL course and preferred the tutors in a supportive attitude. However, 3 days for PBL course seemed not enough for maximal educational benefits, and many possible problems were discussed. It is necessary for nursing educators to accumulate lots of knowledge and skills regarding creating good working problems and implementing and evaluating diverse PBL tutorials to test the feasibility changing to PBL curriculum.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.2
• /
• pp.59-67
• /
• 2002

Major Characteristic of the 7th National Curriculum in science is to provide deep and supplementary learning, depending on the level of each learner. In the level-oriented curriculum, coursewares are used to present teaching materials to various levels. In most coursewares, however, they provide their contents at a uniform level and hence it is hard to expect level-oriented learning. This paper presents learner's modeling for developing student's level-oriented dynamic tutoring system for science class , Instructional module of this system made by component unit is able to be reconstructed dynamically. Learning module is constructed using a hybrid model mixed of Overlay and Bug model. Testing module interprets diagnostic errors to be established by given differentiated weight in accordance with item's difficulty and discrimination. Through ITS student modeling, this system presents various problem solving methods reconstructed by learner's level differentiated.