• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.23-29
• /
• 2019

In this paper, the mood of images was classified into eight categories through a deep convolutional neural network and video was automatically generated using proper background music. Based on the collected image data, the classification model is learned using a multilayer perceptron (MLP). Using the MLP, a video is generated by using multi-class classification to predict image mood to be used for video generation, and by matching pre-classified music. As a result of 10-fold cross-validation and result of experiments on actual images, each 72.4% of accuracy and 64% of confusion matrix accuracy was achieved. In the case of misclassification, by classifying video into a similar mood, it was confirmed that the music from the video had no great mismatch with images.

• The korean journal of orthodontics
• /
• v.24 no.3 s.46
• /
• pp.735-758
• /
• 1994

This study was designed to investigate the displacements and reaction forces of teeth caused by the application of the rectangular shape-memory arch wires with curve of Spee. Computer-aided three dimensional finite element method was adopted. This finite element model consists of brick element for teeth, beam element for the wire, and contact element for the periodontal ligament. And the application of the MEAW(Multiloop Edgewise Arch Wire) was also studied so that the results of the two methods can be compared each other. Total number of the nodes and elements were found to be 5925 and 4031, repectively. In addition, several types of elastics and corresponding displacements and reaction forces were examined. The findings of this study were as follows: 1. When the rectangular shape-memory arch wire with curve of Sun was used alone, the intrusion and labioversion was noticeable on the upper incisors, while the upper molars showed less intrusion. With MEAW, the intrusion and labioversion of the upper incisors were slightly larger than those when the shape-memory arch wire was used, but on the upper molars the opposite result was obtained with respect to the intrusion. 2. The shape-memory arch wire with the vertical elastics caused the larger downward displacement on the upper canine than that when the MEAW was used with the vertical elastics. However, the downward displacement of the upper incisors was larger in MEAW. The uprighting and buccoversion of the molars were observed in both cases. 3. The use of the Class II or III elastics showed the extrusion and changes in torque of the corresponding teeth. The downward displacement of the upper canine was increased when the Class II and vertical elastics were applied simultaneously, but it was decreased when both of the Class III and vertical elastics were used.

• Journal of The Korean Association of Information Education
• /
• v.6 no.2
• /
• pp.202-211
• /
• 2002

The purpose of this paper is to compare and analyze on the result of academic motivation and achievement between two groups in order to certify the application possibility of the cooperative learning method in computer education, and on these research results this paper is to propose the profitable learning and teaching method to the teachers in the class of the computer department and to contribute the improvement of the academic motivation and achievement in computer education of the vocational high school's students. As a result, the post-test average score of academic motivation and achievement in experimental group appeared to be significantly higher than that of the comparative group. And that result is accepted as statistical in significance level p<.001

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.174-178
• /
• 2008

P2P를 포함하는 인터넷 애플리케이션 트래픽의 보다 빠르고 정확한 분류는 최근 학계의 중요한 이슈 중 하나이다. 본 논문에서는 기존의 전통적인 분류방법으로 대표되는 port 번호 및 payload 정보를 이용하는 방법론의 구조적 한계점을 극복하는 새로운 대안으로써, 이진 분류기인 SVM과 단일클래스 SVM을 계층적으로 결합한 다중 클래스 SVM을 구축하여 인터넷 애플리케이션 트래픽 분류를 수행하였다. 제안된 시스템은 이진 분류기인 SVM으로 P2P 트래픽과 non-P2P 트래픽을 빠르게 분류하는 첫 번째 계층, 3개의 단일클래스 SVM을 기반으로 P2P 트래픽들을 파일공유, 메신저, TV로 분류하는 두 번째 계층, 그리고 전체 16가지의 애플리케이션 트래픽별로 세분화 분류하는 세 번째 계층으로 구성된다. 제안된 시스템은 flow 기반의 트래픽 정보를 수집하여 인터넷 애플리케이션 트래픽을 coarse 혹은 fine하게 분류함으로써 효율적인 시스템의 자원 관리, 안정적인 네트워크 환경의 지원, 원활한 bandwidth의 사용, 그리고 적절한 QoS를 보장하였다. 또한, 새로운 애플리케이션 트래픽이 추가되더라도 전체 시스템을 재학습 시킬 필요 없이 새로운 애플리케이션 트래픽만을 추가 학습함으로써 시스템의 점증적 갱신 및 확장성에도 기여하였다. 평가항목인 recall과 precision에서 만족스러운 수치 등을 실험을 통하여 확인함으로써 제안된 시스템의 성능을 검증하였다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.89-94
• /
• 2024

Indian subcontinent is a birthplace of multilingual people where documents such as job application form, passport, number plate identification, and so forth is composed of text contents written in different languages/scripts. These scripts may be in the form of different indic numerals in a single document page. Due to this reason, building a generic recognizer that is capable of recognizing handwritten indic digits written by diverse writers is needed. Also, a lot of work has been done for various non-Indic numerals particularly, in case of Roman, but, in case of Indic digits, the research is limited. Moreover, most of the research focuses with only on MNIST datasets or with only single datasets, either because of time restraints or because the model is tailored to a specific task. In this work, a hybrid model is proposed to recognize all available indic handwritten digit images using the existing benchmark datasets. The proposed method bridges the automatically learnt features of Capsule Network with hand crafted Bag of Feature (BoF) extraction method. Along the way, we analyze (1) the successes (2) explore whether this method will perform well on more difficult conditions i.e. noise, color, affine transformations, intra-class variation, natural scenes. Experimental results show that the hybrid method gives better accuracy in comparison with Capsule Network.

• The Journal of Korean Association of Computer Education
• /
• v.23 no.2
• /
• pp.21-29
• /
• 2020

The purpose of this study is to develop the educational programs for cultivating balanced view of technical understanding and social impact on Artificial Intelligence (AI). To this end, an educational program based on a constructivist approach was developed. Through an experimental class for middle school students we analyzed the concept and perception of AI and the satisfaction of the class. The main results are as follows. First, students' understanding of the concept and the cases of AI in their daily lives has improved. Second, the recognition of the impact of AI on society has emerged and concern about social impact have been lowered. Third, in terms of program satisfaction, all the factors such as understanding of AI, interest in class, interest in AI were high. With these results, we discussed the implications for AI education in elementary and secondary school.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.4 no.2
• /
• pp.38-45
• /
• 2012

Building a game has been used as effective and attractive way of teaching computer science. Building a usable Multi-player Game is requires important aspects of technology, teamwork and software engineering principles. The whole class was structured in to several teams and students needed to join one or two teams. Each team presented their progress, discussed future milestones and troubleshoots, updated documents for clearer communication and utilized SVN(Subversion) throughout the semester. Unlike usual class setting, all students worked collaboratively together like one company to achieve the goal. In one semester, students started from concept design and completed a working Multiplayer Online Game called "deBugger" (Fall 2009), and "World of Balance" (Fall 2011), while learning game design, 3D graphics, Game Engine, Server-client architecture, Game Protocol, network programming, database, Software Engineering principles, and large application development as a team project.

• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.45-52
• /
• 2021

Although many studies have been conducted to identify unknown attacks in cyber security intrusion detection systems, studies based on outliers are attracting attention. Accordingly, we identify outliers by defining categories for unknown attacks. The unknown attacks were investigated in two categories: first, there are factors that generate variant attacks, and second, studies that classify them into new types. We have conducted outlier studies that can identify similar data, such as variants, in the category of studies that generate variant attacks. The big problem of identifying anomalies in the intrusion detection system is that normal and aggressive behavior share the same space. For this, we applied a technique that can be divided into clear types for normal and attack by discrete wavelet transformation and detected anomalies. As a result, we confirmed that the outliers can be identified through One-Class SVM in the data reconstructed by discrete wavelet transform.

• Journal of Practical Engineering Education
• /
• v.14 no.3
• /
• pp.499-504
• /
• 2022

Artificial intelligence is expanding its reach throughout our society, and education is no exception to its scope of application. In line with this trend, we conducted a computer programming class for teachers in graduate school. The final purpose of this class is to develop the programming skills of teachers who teach students to code artificial intelligence programs. This paper studies how the logical thinking and mental consistency of teachers, who are learners, are related to programming aptitude and describes education environmental factors of the class. It was confirmed that logical thinking and mental consistency were proportional to the programming score. This proportional relationship is expected to apply to students learning programming languages. When team formation is required in programming classes, it is expected that better learning effects will be achieved if students with excellent logical thinking and mental consistency are included in each team.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.71-76
• /
• 2003

The purpose of this study is the development, application and assessment of probability and artificial neural network methods for assessing landslide susceptibility in a chosen study area. As the basic analysis tool, a Geographic Information System (GIS) was used for spatial data management. A probability method was used for calculating the rating of the relative importance of each factor class to landslide occurrence, For calculating the weight of the relative importance of each factor to landslide occurrence, an artificial neural network method was developed. Using these methods, the landslide susceptibility index was calculated using the rating and weight, and a landslide susceptibility map was produced using the index. The results of the landslide susceptibility analysis, with and without weights, were confirmed from comparison with the landslide location data. The comparison result with weighting was better than the results without weighting. The calculated weight and rating can be used to landslide susceptibility mapping.