• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.88-90
• /
• 2022

Semi Supervised Learning 은 일부의 data 에는 labeling 을 하고 나머지 data 에는 labeling 을 안한채로 학습을 진행하는 방법이다. Object Detection 은 이미지에서 여러개의 객체들의 대한 위치를 여러개의 바운딩 박스로 지정해서 찾는 Computer Vision task 이다. 당연하게도, model training 단계에서 사용되는 data set 의 크기가 크고 객체가 많을 수록 일반적으로 model 의 성능이 좋아 질 것이다. 하지만 실험 환경에 따라 data set 을 잘 확보하지 못하던가, 실험 장치가 데이터 셋을 감당하지 못하는 등의 문제가 발생 할 수 있다. 그렇기에 본 논문에서는 semi supervised learning based object detection model 을 알아보고 data set 의 크기를 조절해가며 modle 을 training 시킨 뒤 data set 의 크기에 따라 성능이 어떻게 변화하는 지를 알아 볼 것이다.

• Journal of Educational Research in Mathematics
• /
• v.8 no.2
• /
• pp.605-620
• /
• 1998

This paper suggested a geometry learning model which relates an exploratory learning model with GSP applications, Such a model adopts GSP's capability of visualizing dynamic geometric figures and exploratory learning method's advantages of discovering properties and relations of geometric problem proving and concepts associated with geometric inferencing of students. The research was conducted for 3 middle school students by applying the proposed model for 6times at computer laboratory. The overall procedure was videotaped so that the collected data was later analyzed by qualitative methodology. The analysis indicated that the students with less than van Hiele 4 level took advantages of adoption our proposed model to gain concrete understandings of geometric principles and concepts with GSP. One of the lessons learned from this study suggested that the roles of students and a teacher who want to employ the proposed model need to change their roles respectively.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.367-372
• /
• 2021

The purpose of this study is to suggest that the movement expression activity of intellectually disabled people is effective in the learning process of LMA motion recognition based on Kinect sensor. We performed an ICT motion recognition games for intellectually disabled based on movement learning of LMA. The characteristics of the movement through Laban's LMA include the change of time in which movement occurs through the human body that recognizes space and the tension or relaxation of emotion expression. The design and implementation of the motion recognition model will be described, and the possibility of using the proposed motion recognition model is verified through a simple experiment. As a result of the experiment, 24 movement expression activities conducted through 10 learning sessions of 5 participants showed a concordance rate of 53.4% or more of the total average. Learning motion games that appear in response to changes in motion had a good effect on positive learning emotions. As a result of study, learning motion games that appear in response to changes in motion had a good effect on positive learning emotions

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.269-282
• /
• 2023

The purpose of this study was to construct land cover maps using a deep learning model and to select the optimal deep learning model for land cover classification by adjusting the dataset such as input image size and Stride application. Two types of deep learning models, the U-net model and the DeeplabV3+ model with an Encoder-Decoder network, were utilized. Also, the combination of the two deep learning models, which is an Ensemble model, was used in this study. The dataset utilized RapidEye satellite images as input images and the label images used Raster images based on the six categories of the land use of Intergovernmental Panel on Climate Change as true value. This study focused on the problem of the quality improvement of the dataset to enhance the accuracy of deep learning model and constructed twelve land cover maps using the combination of three deep learning models (U-net, DeeplabV3+, and Ensemble), two input image sizes (64 × 64 pixel and 256 × 256 pixel), and two Stride application rates (50% and 100%). The evaluation of the accuracy of the label images and the deep learning-based land cover maps showed that the U-net and DeeplabV3+ models had high accuracy, with overall accuracy values of approximately 87.9% and 89.8%, and kappa coefficients of over 72%. In addition, applying the Ensemble and Stride to the deep learning models resulted in a maximum increase of approximately 3% in accuracy and an improvement in the issue of boundary inconsistency, which is a problem associated with Semantic Segmentation based deep learning models.

• The Journal of Society for e-Business Studies
• /
• v.24 no.3
• /
• pp.99-110
• /
• 2019

As the 4th industrial revolution progressing, manufacturers are trying to apply intelligent information technologies such as IoT(internet of things) and machine learning. In the semiconductor/LCD/tire manufacturing process, schedule plan that minimizes setup change and due date violation is very important in order to ensure efficient production. Therefore, in this paper, we suggest the deep learning based scheduling generation model minimizes setup change and due date violation in parallel machines. The proposed model learns patterns of minimizing setup change and due date violation depending on considered order using the amount of historical data. Therefore, the experiment results using three dataset depending on levels of the order list, the proposed model outperforms compared to priority rules.

• Convergence Security Journal
• /
• v.5 no.2
• /
• pp.37-42
• /
• 2005

Development of Information Technology and knowledge information society transfer brought huge change of education training field. According as Ubiquitous society approaches, e-Learning will be evolving by u-Learning. This presages in other form with present that professor-learner environment may change. This study proposes and embodied administration method of various studying contents by development of Learning environment, And through operation platform analysis, proposed LMS that can do practical use of contents efficiently.

• Journal of the Korean earth science society
• /
• v.39 no.3
• /
• pp.260-274
• /
• 2018

The purpose of this study was to propose curriculum and teaching sequence for seasonal change by exploring a learning progression. For the purpose, 4 steps of construct modeling approach (specifying construct, item design, outcome space, and measurement model) proposed by Wilson (2005) was applied. In the stage of specifying construct, 'length of shadow according to seasons', 'position of constellation according to seasons', 'seasons of the southern hemisphere and northern hemisphere', 'cause and phenomenon of seasonal change' were selected as the subconstructs of seasonal changes, and constructed a construct map showing the level of development from level 1 to level 4 for each subconstruct based on the results of the previous research. In the item design stage, we developed five assessment items consisting of 3 items in the form of C-E (choose and explain) and two items in the form of CR (constructed response), applied it to 383 elementary, middle and high school students. In the outcome space stage, the students' responses to the assessment items were categorized based on the construct map. The categories were classified into 4 levels according to student ability and scores of 1-4 were given. In the measurement model stage, we applied the partial credit model of the Rasch model and compared whether the learning pathway created from the results of students' response coincides with the construct map. Based on the results of the research, we modified the construct map and finally created hypothetical learning progression on seasonal change. Finally, we proposed an orientation of curriculum amendment and effective teaching sequence for seasonal change.

• Research in Mathematical Education
• /
• v.13 no.2
• /
• pp.109-122
• /
• 2009

This study investigates the change in two theoretical constructs, attitudes toward mathematics and mathematics self-efficacy, among college students involved in a learning community model. The case of this study was a developmental mathematics class offered at a historically black college located in the southeastern United States. Subjects included 31 students enrolled in an introductory mathematics course, some of whom participated in a learning community (treatment group). The participants completed mathematics attitudes and mathematics efficacy instruments twice: at the beginning of the semester and again at the end. Data was analyzed using descriptive statistics and a non-parametric statistic. The results showed that students' attitudes toward mathematics and mathematics self-efficacy are strongly correlated; the mathematical problem-solving efficacy changed significantly over time and it is significantly higher in the treatment group than in the control group; and the treatment group produced better outcomes. These findings indicate that a learning community model can increase students' mathematics self-efficacy beliefs. It is recommended that mathematics self-efficacy and attitudes toward mathematics be measured over an extended period of time when a learning community is implemented.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.792-795
• /
• 2006

In this paper, we examined the influence for a new learning method using on-line e-learning education model in the field of music appreciation. We applied this loaming method to the field of motive induction, the expectation of learning effect and the increase learning will through mesuring the student's pulse change in the learning class. We analysed the influence of interesting rate and emotional stability in the field of music appreciation.

• International Journal of Highway Engineering
• /
• v.19 no.2
• /
• pp.35-44
• /
• 2017

PURPOSES: This study suggests a specific methodology for the prediction of road surface temperature using vehicular ambient temperature sensors. In addition, four kind of models is developed based on machine learning algorithms. METHODS : Thermal Mapping System is employed to collect road surface and vehicular ambient temperature data on the defined survey route in 2015 and 2016 year, respectively. For modelling, all types of collected temperature data should be classified into response and predictor before applying a machine learning tool such as MATLAB. In this study, collected road surface temperature are considered as response while vehicular ambient temperatures defied as predictor. Through data learning using machine learning tool, models were developed and finally compared predicted and actual temperature based on average absolute error. RESULTS : According to comparison results, model enables to estimate actual road surface temperature variation pattern along the roads very well. Model III is slightly better than the rest of models in terms of estimation performance. CONCLUSIONS : When correlation between response and predictor is high, when plenty of historical data exists, and when a lot of predictors are available, estimation performance of would be much better.