• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.25-28
• /
• 2020

Automatic segmentation of brain tissues such as WM, GM, and CSF from brain MRI scans is helpful for the diagnosis of many neurological disorders. Accurate segmentation of these brain structures is a very challenging task due to low tissue contrast, bias filed, and partial volume effects. With the aim to improve brain MRI segmentation accuracy, we propose an end-to-end convolutional based U-SegNet architecture designed with multi-scale kernels, which includes cascaded dilated convolutions for the task of brain MRI segmentation. The multi-scale convolution kernels are designed to extract abundant semantic features and capture context information at different scales. Further, the cascaded dilated convolution scheme helps to alleviate the vanishing gradient problem in the proposed model. Experimental outcomes indicate that the proposed architecture is superior to the traditional deep-learning methods such as Segnet, U-net, and U-Segnet and achieves high performance with an average DSC of 93% and 86% of JI value for brain MRI segmentation.

• English Language & Literature Teaching
• /
• v.8 no.2
• /
• pp.151-176
• /
• 2003

Motivation and learning strategies, some of the important factors affecting language learning, have mostly been studied with reference to their relationship in terms of proficiency. This study investigated motivation and learning strategies and their relationship in order to find the inward predisposition of learners. Data was collected from 200 university students in Taejon and Chungnam province, Korea language learning strategies were measured by the Strategy Inventory for Language Learning(SILL), and motivation by the Attitude / Motivation Test Battery(AMTB), with adaptations for Koreans. The detailed analysis of the data Indicated that Korean university students were more motivated to learn English for a practical goal than a formal one. They had a strong willingness to learn but showed 'the tendency of the new generation' of choosing the easiest and most convenient ways in studying English in terms of motivational intensity and strategy use. Findings imply that there have to be some changes and improvements in the deep-rooted classroom teaching methods. A systematic device is needed to induce students to be autonomous learners, providing them with a variety of activities suitable for their purposes and levels, as in opportunities of contacting native speakers, multi-media language labs, the Internet etc.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.240-241
• /
• 2019

최근 객체 추적 분야에서의 딥러닝 활용도가 증가하고 있다. 대표적인 딥러닝 기반 객체 추적 시스템은 객체 검출 알고리즘과 추적 알고리즘의 연쇄된 형태로 구성된 형태이다. 따라서 추적 시스템의 성능은 객체 검출기의 성능에 매우 의전적이라는 한계점이 존재한다. 본 논문에서는 위와 같은 검출-추적의 직관적인 구조로 구성된 시스템에서 딥러닝 기반 검출기에 대한 의존성을 낮추고 또한 추적기의 동작 속도를 증가시키는 방법을 제안한다.

• The Journal of the Korea Contents Association
• /
• v.11 no.11
• /
• pp.514-520
• /
• 2011

Technological development, a diverse range of media adapting to new technology has been developing. Augmented Reality Technology provides realistic information through the stereoscopic 3D images and it has been riding a wave of learner interest as an educational media which can broaden their learning experience through direct operating activity. The biggest reason why the Augmented Reality has gained such attention is because of its unique way of suggesting learning information that unlike the existing educational media, the Augmented Reality provides additional digitalized information while its users are looking at the actual object. Based on the domestic and foreign cases of development for educational contents using the Augmented Reality Technology, this thesis suggests the utilization of Pop-up books and multi-augmented Digilog Books that are ways to maximize the educational effects of the Augmented Reality. Through the development of smartphone applications that are propagating lately at a rapid rate, users can now use the Augmented Reality educational contents in a way that is easier than ever.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.27-32
• /
• 2019

Research that implements the classification process through Deep Learning algorithm, one of the outstanding human abilities, includes a unimodal model, a multi-modal model, and a multi-modal method using music videos. In this study, the results were better by suggesting a system to analyze each song's spectrum into short samples and vote for the results. Among Deep Learning algorithms, CNN showed superior performance in the category of music genre compared to RNN, and improved performance when CNN and RNN were applied together. The system of voting for each CNN result by Deep Learning a short sample of music showed better results than the previous model and the model with Softmax layer added to the model performed best. The need for the explosive growth of digital media and the automatic classification of music genres in numerous streaming services is increasing. Future research will need to reduce the proportion of undifferentiated songs and develop algorithms for the last category classification of undivided songs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.6 no.6
• /
• pp.502-505
• /
• 2005

According to use of a multimedia content being increased in an e-learning, a size deviation of a content to provide in an e-teaming system is increased. It is becoming a factor to drop efficiency of education because this makes a deviation of response time on an e-learning user. Therefore, studies about a deviation improvement of user response speed is necessary in the e-learning system that used a multimedia content. In this study, we designe the hybrid e-teaming system that used multi-layed structire. A proposed system is based on a characteristics of media and size of a content that a multimedia data had. Also, it proved superiority of performance through experimentation.

• The Journal of Korean society of community based occupational therapy
• /
• v.8 no.2
• /
• pp.1-14
• /
• 2018

Objective : The purpose of this study was to investigate the change in self-efficacy and writing ability after applying a Task-Oriented Multi-Sensory Movement Program to children with ADHD tendency accompanied by learning delays. Methods : A Task-Oriented Multi-Sensory Movement Program was implemented to children with ADHD tendency accompanied by learning delays attending S elementary school. The research proceeded in the order of a pre-test, Task-Oriented Multi-Sensory Movement intervention, and a post-test. The first session involved a pre-test, in which the children's self-efficacy and writing ability were examined using self-efficacy test and type 'A' KNISE-BAAT writing test. The multisensory group activity program intervention was conducted for a total of 8 sessions. In the last session, a post-test was conducted using self-efficacy test and type 'B' KNISE-BAAT writing test. Data collected from the tests were analyzed using SPSS Statistics 18. Results : According to the tests taken before and after implementing the Task-Oriented Multi-Sensory Movement Program, there was a significant improvement in self-efficacy (school, society), writing ability(command of vocabulary and sentence). Conclusion : Task-Oriented Multi-Sensory Movement Program may be used as a beneficial measure to improve the self-efficacy and writing abilities of children with ADHD tendency accompanied by learning delays. It is necessary to design various intervention models by combining educational media based on a multisensory approach.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.758-765
• /
• 2021

Recently, various research on the application of deep learning to video encoding for enhancing coding efficiency are being actively studied. This paper proposes a deep learning based intra prediction which uses multiple models by extending Matrix-based Intra Prediction(MIP) that is a neural network-based technology adopted in VVC. It also presents an efficient learning method for the multi-model intra prediction. To evaluate the performance of the proposed method, we integrated the VVC MIP and the proposed fully connected layer based multi-model intra prediction into HEVC reference software, HM16.19 as an additional intra prediction mode. As a result of the experiments, the proposed method can obtain bit-saving coding gain up to 0.47% and 0.19% BD-rate, respectively, compared to HM16.19 and VVC MIP.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1141-1155
• /
• 2022

Multicultural education is not about learning about a specific ethnic group, but rather developing the ability to cross the border of one's own culture and have conversations with people of other cultures. I think the purpose is to promote empathy and consideration. This study emphasizes the importance of developing multi-dimensional educational programs for all members of society for multicultural social integration, and it is necessary to lead personal, social and civic action movements to create a fair society through media-based multicultural literacy education. said that In order to achieve harmony and integration in a multicultural society, it is the most important to acknowledge cultural diversity and to discard cultural prejudices and inequalities for symbiosis between the mainstream culture and the minority culture. In particular, the United States and Germany, which have successfully led multicultural social integration, are comprehensive in all areas, including interculturalism based on peaceful coexistence and respect, labor market issues, vocational education issues, housing and health issues, and communication issues through media literacy. He led a multicultural national integration system with approaches and methods. Therefore, our multicultural education policy should also pursue a new paradigm that presupposes a change in the public's awareness of a multicultural society.