• ETRI Journal
• /
• v.42 no.2
• /
• pp.230-238
• /
• 2020

Human-object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extractor followed by detection layers comprising small filters (eg, 1 × 1 or 3 × 3). Although small filters can capture local spatial features with a few parameters, they fail to capture larger context information relevant for recognizing interactions between humans and distant objects owing to their small receptive regions. Hence, we herein propose a three-stream HOI detection network that employs a context convolution module (CCM) in each stream branch. The CCM can capture larger contexts from input feature maps by adopting combinations of large separable convolution layers and residual-based convolution layers without increasing the number of parameters by using fewer large separable filters. We evaluate our HOI detection method using two benchmark datasets, V-COCO and HICO-DET, and demonstrate its state-of-the-art performance.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1115-1121
• /
• 2018

In this paper, we have studied a data analysis method by deep learning to predict learning achievements based on accumulated data in cyber university learning management system. By predicting learner's academic achievement, it can be used as a tool to enhance learner's learning and improve the quality of education. In order to improve the accuracy of prediction of learning achievements, the autoencoder based attendance prediction method is developed to improve the prediction performance and deep learning algorithm with ongoing evaluation metrics and predicted attendance are used to predict the final score. In order to verify the prediction results of the proposed method, the final grade was predicted by using the evaluation factor attendance data of the learning process. The experimental result showed that we can predict the learning achievements in the middle of semester.

• International Journal of Advanced Culture Technology
• /
• v.10 no.4
• /
• pp.536-546
• /
• 2022

A society will lose a lot of something in this field when the forest fire broke out. If a forest fire can be detected in advance, damage caused by the spread of forest fires can be prevented early. So, we studied how to detect forest fires using CCTV currently installed. In this paper, we present a deep learning-based model through efficient image data construction for monitoring forest fire smoke, which is unstructured data, based on the deep learning model YOLOv5. Through this study, we conducted a study to accurately detect forest fire smoke, one of the amorphous objects of various forms, in YOLOv5. In this paper, we introduce a method of self-learning by producing insufficient data on its own to increase accuracy for unstructured object recognition. The method presented in this paper constructs a dataset with a fixed labelling position for images containing objects that can be extracted from the original image, through the original image and a model that learned from it. In addition, by training the deep learning model, the performance(mAP) was improved, and the errors occurred by detecting objects other than the learning object were reduced, compared to the model in which only the original image was learned.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.6
• /
• pp.85-93
• /
• 2004

We investigated the proper display environment for japanese electronic character reading lessons through the experiment with a projection TV and a computer. For the purpose of finding out the effect of prior learning activities at the context of authentic Japanese text orthography, which includes dual notation, words spacing, etc., we also made an experiment on comprehending the web documents which are extracted from japanese web sites. From the experimental results, we acquired a conclusion that two approaches are needed to enhance the ability of comprehending Japanese web documents which is newly added to the 7th curriculum revision. For short-term approach, we need to utilize Japanese web documents as learning materials. For long-term approach, we have to reconsider whether the orthography of the current Japanese textbooks is suitable or not.

• Journal of The Korean Association of Information Education
• /
• v.25 no.2
• /
• pp.317-325
• /
• 2021

In this paper, the degree of reflection of SW·AI elements and CT elements was investigated and analyzed for a total of 44 textbooks of Korean, social, moral, mathematics and science textbooks based on the 2015 revised curriculum. As a result of the analysis, most of the activities of data collection, data analysis, and data presentation, which are ICT elements, were not reflected, and algorithm and programming elements were not reflected among SW·AI content elements, and there were no abstraction, automation, and generalization elements among CT elements. Therefore, in order to effectively implement SW·AI convergence education in elementary school subjects, we will expand ICT utilization activities to SW·AI utilization activities. Training on the understanding of SW·AI convergence education and improvement of teaching and learning methods using SW·AI is needed for teachers. In addition, it is necessary to establish an information curriculum and secure separate class hours for substantial SW·AI education.

• Journal of The Korean Association of Information Education
• /
• v.15 no.1
• /
• pp.93-100
• /
• 2011

Previous studies on educational programming language reported that programming education can help students develop their abilities in cognitive, logical and reflecting thinking for problem solving. In this study, we examined the effects of Scratch programming language education on self-directed learning ability through six-grade elementary school students. The study results are that the treatment group shows more improvement with statistical significance on the subscales of self-directed learning such as openness, internal motivation, and autonomy, than the control group. These effects are especially larger with the students with high ICT literacy, whose degree is higher than that as a result of using digital textbook, UCC, and cyber home education reported in previous studies.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.271-271
• /
• 2007

본 내용은 첨단 정보통신 기술을 이용하여 강의자 중심의 단방향 교육(Teaching) 환경을 학생 중심의 양방향 교육(Learning) 환경으로 개선하여 보다 창의적인 인재를 양성할 수 있는 교육환경 구축에 관한 내용이다. 우리나라를 포함한 OECD 국가들은 ICT활용 수업에 대한 필요성을 공감하고 교단 선진화를 위한 연구 및 지원을 다양하게 진행하고 있다. 학생들에게 지급하는 교과서를 인쇄매체 대신에 메모리 스틱, CD-ROM 및 인터넷을 통한 전자 매체로 대체하는 방안 등이 그 예이다. 따라서 학생들이 강의실에서 멀티미디어를 이용해 강의를 듣고, 과제를 풀며 정리된 내용을 발표하고 토론할 수 있는 양방향 수업환경이 요구된다. 그러나 컴퓨터를 활용한 수업을 진행할 때의 문제점이 강의내용을 학생들에게 효율적으로 전달하기가 어렵고, 학생들의 컴퓨터를 통제할 수 없기 때문에 수업을 이탈하는 경우가 발생되는 등 교육에 역효과가 초래된다. 본 내용에서 소개하는 양방향 수업진행 장비(드림랩)는 강의자가 학생들의 컴퓨터 모니터, 키보드 및 마우스를 자유로이 통제할 수 있어서 강의자의 화면과 음성을 실시간으로 선명하게 학생들에게 전달하고, 학생들의 내용을 모니터하고 제어할 수 있으며, 개인지도 및 수준별 그룹지도가 가능하다. 또한 강의자에게 개인적으로 질문을 할 수 있고, 학생들의 내용을 자신의 자리에서 전체 학생들에게 발표할 수도 있다. 드림랩은 순수 하드웨어로 구성되어 컴퓨터 기종이나 운영체제에 영향을 받지 않으며, 컴퓨터 자원과 네트워크 자원을 사용하지 않기 때문에 컴퓨터나 네트워크의 성능을 저하시키지 않는다. 또한 사용법이 간단하고 유지관리가 쉬운 장점 등이 있다. 따라서 컴퓨터를 활용한 수업진행이 원활하여 다양한 과목에 활용 가능하고, 학생들의 자발적인 수업 참여로 강의 중심 교육에서 자기 주도적 수업환경(T2L, Teaching to Learning)으로 자연스럽게 전환되어 교육의 질적 향상과 함께 창의적인 인재를 양성할 수 있을 것으로 기대된다.

• The Journal of the Korea Contents Association
• /
• v.16 no.2
• /
• pp.546-557
• /
• 2016

Tooth carving practice is required for novice learners in dentistry to understand dental morphology and acquire clinically underlying skills. Tooth carving practice is more effective when sequential models can be observed. The purpose of this study is to suggest a tooth carving practice model and to develop a mobile practice supporting tool based on tutorial providing 3D modeling information about steps of tooth carving. As a result, tooth carving practice model consists of the class activity including tooth information lecture and practice and mobile seamless learning connecting learners' practice and regular learning with the mobile tutorial tool. The mobile tutorial tool is implemented with tooth morphology dictionary, tooth carving practice/training tutorial, and 3D tooth modeling. The experts' evaluation on the developed contents shows that the content and function are valid(content validity: 5.0, interface validity: 4.53). Therefore, the mobile tutorial tool is suitable for supporting mobile seamless learning for tooth carving practice. Further researches are expected to be conducted to develop instructional models utilizing ICT and mobile contents in dentistry.

• Journal of The Korean Association of Information Education
• /
• v.6 no.3
• /
• pp.317-327
• /
• 2002

The need to support the ICT-using teaching and learning at elementary and secondary schools has led to various digital content service systems. The systems are designed to target the teachers and the students as the major users. The problems involved in them is that they do not provide such services as the integrated search and the systematic use of interface in terms of actual users' use of teaching and learning digital content. It's because they have been created at demands at each time. In an attempt to solve this problem, this study set out to suggest the integrated meta-data items of a teaching and learning digital content, which reflects the Dublin Core Education, the international meta-data standard. It also aimed to design an entity-relationship model to realize the digital content. The results of the integrated meta-data and the entity-relationship model will be utilized as a basic research to help the users to search for various teaching and learning digital contents on an integrated basis and to realize a consistent user interface. Furthermore, they are expected to contribute to the development a service system the teachers and the students can make better use of.

• Journal of The Korean Association of Information Education
• /
• v.8 no.2
• /
• pp.167-176
• /
• 2004

Due to the development of information communication technology, educational environment has undergone much change and various types of teaching and learning methods based on information communication technology has been suggested. Recently, remote education using the internet are also spreading. However, in current classrooms, students are asked to do an teacher-centered assignment, which they are required to collect and report some information using the internet. This method does not help students use the advantages of learning using the internet, which stimulate students-students interaction and teacher-students interaction.Thus, this study focused on the problem-based learning system based on video communication technology. The researcher designed the problem-based learning system based on video communication technology and applied the system to classes at elementary school. The results were analyzed in terms of students-students interaction and teacher-students interaction in the internet. This research found that the problem-based learning system stimulates teacher and students communication and has positive effects on students' attitude and interest in learning. This research proposes that the traditional teacher-centered teaching method can be supplemented with cyber space learning, which has the merit of problem-based learning model.