• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.382-395
• /
• 2021

In this study, character recognition using deep learning is performed among the various defects in the PCB, the purpose of which is to check whether the printed characters are printed correctly on top of components, or the incorrect parts are attached. Generally, character recognition may be perceived as not a difficult problem when considering MNIST, but the printed letters on the PCB component data are difficult to collect, and have very high redundancy. So if a deep learning model is trained with original data without any preprocessing, it can lead to over fitting problems. Therefore, this study aims to reduce the redundancy to the smallest dataset that can represent large amounts of data collected in limited production sites, and to create datasets through data enhancement to train a flexible deep learning model can be used in various production sites. Moreover, ResNet model verifies to determine which combination of datasets is the most effective. This study discusses how to reduce and augment data that is constantly occurring in real PCB production lines, and discusses how to select coresets to learn and apply deep learning models in real sites.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1000-1011
• /
• 2021

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

• Journal of Korean Home Economics Education Association
• /
• v.15 no.3
• /
• pp.59-73
• /
• 2003

This study aims to review and analyze the contents related to environment among curriculum of Technology$.$Home Economics subject; to produce multimedia learning materials and web-based materials for effective environmental education: and to find the way to effectively utilize them in schools. The data were analyzed by t-test with SPSS Win 10.0 program. The results of this study are as follows; First, the textbook carries a lot of contents concerning the environment. Second, the multimedia materials help students to understand environmental issues and strengthen their attitudes of environmental problems very effectively. Third, after using the instructional multimedia materials, the students showed significantly different results.

• Journal of Korea Multimedia Society
• /
• v.12 no.5
• /
• pp.757-766
• /
• 2009

This study presents an adaptive hypermedia learning system which can provide individual learning environment using a learner behavioral model. This system proposes a LBML which can manage learners' learning behavioral information by tracking down such information real-time. The system consists of a collecting system of learning behavioral information and an adaptive learning support system. The collecting system of learning behavioral information uses Web 2.0 technologies and collects learners' learning behavioral information real-time based on a SCORM CMI data model. The collected information is stored as LBML instances of individual learners based on a LBML schema. With the adaptive learning support system, a rule-based learning supporting module and an interactive learning supporting module are developed by analysing LBML instances.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1221-1224
• /
• 2005

In this paper, by using MPEC-4 systems, it is easy to create MPEC-4 file and to design multimedia which it understands. Also, by using a MPEG-Pro it is proposed that the user understood the data transfer and expression etc. easily and it added the focus processing function it will be able to design and to be possible individual learning which is easy with the CD and web program. The effectiveness of this new multimedia courseware using MPEG-4 have been proven by experiments in practical teaching-learning method of courseware

• The Journal of the Korea Contents Association
• /
• v.2 no.4
• /
• pp.9-16
• /
• 2002

A multimedia figure learning system has been designed and implemented by using TOOBOOK. Also, the developed system has been analyzed after use it in classrooms. The analysis result shows that the multimedia system is better for understanding the concepts of revolving entity and cross section than the traditional teaching methods.

• Journal of information and communication convergence engineering
• /
• v.8 no.4
• /
• pp.383-386
• /
• 2010

Pattern classification is one of the most important topics for machine learning research fields. However incomplete data appear frequently in real world problems and also show low learning rate in classification models. There have been many researches for handling such incomplete data, but most of the researches are focusing on training stages. In this paper, we proposed two classification methods for incomplete data using triangular shaped fuzzy membership functions. In the proposed methods, missing data in incomplete feature vectors are inferred, learned and applied to the proposed classifier using triangular shaped fuzzy membership functions. In the experiment, we verified that the proposed methods show higher classification rate than a conventional method.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.1
• /
• pp.135-141
• /
• 2017

This thesis progressed research on the improvements of NCS multimedia utilization for preliminary teachers. A national module has not been developed yet in terms of child education, so this thesis suggests a curriculum according to the courses taught for freshmen and sophomores of K University Child Education majors. To lessen the burden of tremendous work and classes, provide motivation and interest in learning and maximize the effect, this thesis provides NCS based curriculum. It expects to improve task performance of teachers and help them with better skills to make class materials using up-to-date multimedia, regardless of the computer literacy of preliminary teachers. This thesis does prior research on the abilities to make use of computers and understand the level of computer literacy. Then it suggests NCS based curriculum goals and its performance standards to utilize task-suitable software. It aims to enable efficient multimedia usage, and optimize the learning efficiency of education linked to Nuri precesses.

• Educational Technology International
• /
• v.12 no.1
• /
• pp.1-20
• /
• 2011

The study described in this paper examined the effectiveness of a multimedia case-based learning environment to teach technology integration to Korean pre-service teachers. The structure and philosophy behind the use of embedded video in an online, multimedia system and the data collected from 103 pre-service teachers are presented and discussed. The overall finding shows that there was no significant difference from pre- to posttest among the lecture, the case-based, and the mixed environment groups. However, low prior knowledge students improved more when they learned about technology integration with the mixed method than with the case-based method alone. Discussion about this result and its educational implications conclude the paper.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2007.11a
• /
• pp.123-123
• /
• 2007