• Convergence Security Journal
• /
• v.22 no.3
• /
• pp.25-32
• /
• 2022

Recently, the image processing industry has been activated as deep learning-based technology is introduced in the image recognition and detection field. With the development of deep learning technology, learning model vulnerabilities for adversarial attacks continue to be reported. However, studies on countermeasures against poisoning attacks that inject malicious data during learning are insufficient. The conventional countermeasure against poisoning attacks has a limitation in that it is necessary to perform a separate detection and removal operation by examining the training data each time. Therefore, in this paper, we propose a technique for reducing the attack success rate by applying modifications to the training data and inference data without a separate detection and removal process for the poison data. The One-shot kill poison attack, a clean label poison attack proposed in previous studies, was used as an attack model. The attack performance was confirmed by dividing it into a general attacker and an intelligent attacker according to the attacker's attack strategy. According to the experimental results, when the proposed defense mechanism is applied, the attack success rate can be reduced by up to 65% compared to the conventional method.

• Journal of the Korea Knowledge Information Technology Society
• /
• v.13 no.3
• /
• pp.305-317
• /
• 2018

This study is about the elderly people's use and experience of Virtual Reality (VR) in order to enhance their quality of life. Leisure is main activity of the elderly. As a result, the quality and diversity of leisure affects the quality of the elderly people's life. VR services including video contents could provide them with advanced and interesting experiences. Across the world, population aging becomes one of the most important problems in each society. The social and economic burden of aging is serious challenge to sustainability welfare of the world, including S. Korea. The authors used virtual reality devices to conduct experiments on 99 aged 50 to 90 (men's average age : 75 and women's average age : 70.8). Through the survey, major variants were measured such as system quality, present sense, enjoyment, intent to reuse, and awareness of advanced technology. Multiple regression analyses with the presence as a dependent variable resulted in a sense of closeness (t = 5.381, p <. 01) and a sense of clarity (t = 4.494, p <. 01). The presence of an independent variant had significant effects on pleasure (t = 4.312, p <. 01) and significant effects on the intent to reuse (t = 3.323,).Therefore, it can be interpreted that the higher the sense of existence, the more pleasure and the intent to reuse it. As a result, the possibility of using VR devices and content to enjoy leisure activities can be found in this study even if the elderly group is unfamiliar with IT devices.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.4
• /
• pp.333-351
• /
• 2023

This study investigates user behavior in library spaces through the lens of AI camera analytics. By leveraging the face recognition and tracking capabilities of AI cameras, we accurately identified the gender and age of visitors and meticulously collected video data to track their movements. Our findings revealed that female users slightly outnumbered male users and the dominant age group was individuals in their 30s. User visits peaked between Tuesday to Friday, with the highest footfall recorded between 14:00 and 15:00 pm, while visits decreased over the weekend. Most visitors utilized one or two specific spaces, frequently consulting the information desk for inquiries, checking out/returning items, or using the rest area for relaxation. The library stacks were used approximately twice as much as they were avoided. The most frequented subject areas were Philosophy(100), Religion(200), Social Sciences(300), Science(400), Technology(500), and Literature(800), with Literature(800) and Religion(200) displaying the most intersections with other areas. By categorizing users into five clusters based on space utilization patterns, we discerned varying objectives and subject interests, providing insights for future library service enhancements. Moreover, the study underscores the need to address the associated costs and privacy concerns when considering the broader application of AI camera analytics in library settings.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.73-80
• /
• 2023

The recent steep increase in the minimum hourly wage has increased the burden of labor costs, and the share of unmanned stores is increasing in the aftermath of COVID-19. As a result, theft crimes targeting unmanned stores are also increasing, and the "Just Walk Out" system is introduced to prevent such thefts, and LiDAR sensors, weight sensors, etc. are used or manually checked through continuous CCTV monitoring. However, the more expensive sensors are used, the higher the initial cost of operating the store and the higher the cost in many ways, and CCTV verification is difficult for managers to monitor around the clock and is limited in use. In this paper, we would like to propose an AI image processing fusion algorithm that can solve these sensors or human-dependent parts and detect customers who perform abnormal behaviors such as theft at low costs that can be used in unmanned stores and provide cloud-based notifications. In addition, this paper verifies the accuracy of each algorithm based on behavior pattern data collected from unmanned stores through motion capture using mediapipe, object detection using YOLO, and fusion algorithm and proves the performance of the convergence algorithm through various scenario designs.

• Communications of Mathematical Education
• /
• v.38 no.1
• /
• pp.1-26
• /
• 2024

As the limitations of professional development programs and individual attempts to improve teaching expertise have been reported, mathematics teachers have operated various types of teacher learning communities as alternative teacher professional programs. A teacher learning community can be considered a Community of Practice(CoP) in that it satisfies three factors of Cop, which are common purpose, mutual participation, and shared repertoire, so the 'learning' of a teacher community can be interpreted based on the theory of CoP. The purpose of this study is to investigate the process of identity development of five mathematics teachers who have been continuously involved in teacher communities. For this, the researcher collected data on the entire process of community activities through participant observation and conducted individual follow-up interviews to explore mathematics teachers' narratives and personal experiences. Results indicated that mathematics teachers experienced the development of practical knowledge related to mathematics teaching and learning, improvement of teaching practice through continuous reflection and introspection, and recognization the shared value of togethering through community immersion. Based on these experiences, implications for the effective operation of learning communities such as national support of teacher learning communities and horizontal and cooperative teacher norms were discussed, and follow-up research was proposed.

• 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.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.1
• /
• pp.82-89
• /
• 2024

Black ice is very difficult to recognize and reduces the friction of the road surface, causing automobile accidents. Since black ice is difficult to detect, there is a need for a system that identifies black ice in real time and warns the driver. Various studies have been conducted to prevent black ice on road surfaces, but there is a lack of research on systems that identify black ice in real time and warn drivers. In this paper, an real-time image-based analysis system was developed to identify the condition of asphalt road surface, which is widely used in Korea. For this purpose, a dataset was built for each asphalt road surface image, and then the road surface condition was identified as dry, wet, black ice, and snow using deep learning. In addition, temperature and humidity data measured on the actual road surface were used to finalize the road surface condition. When the road surface was determined to be black ice, the salt spray equipment installed on the road was automatically activated. The surface condition recognition system for the asphalt concrete pavement and black ice automatic prevention system developed in this study are expected to ensure safe driving and reduce the incidence of traffic accidents.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.111-121
• /
• 2024

Recently, thanks to the development of artificial intelligence technologies such as image recognition, research on unmanned aerial vehicles is being actively conducted. In particular, related research is increasing in the field of military drones, which costs a lot to foster professional pilot personnel, and one of them is the study of an intelligent framework for autonomous mission performance of reconnaissance drones. In this study, we tried to design an intelligent framework for unmanned aerial vehicles using the methodology of designing an intelligent framework for service robots. For the autonomous mission performance of unmanned aerial vehicles, the intelligent framework and unmanned aerial vehicle module must be smoothly linked. However, it was difficult to provide interworking for drones using periodic message protocols with model-based interfaces of intelligent frameworks for existing service robots. First, the message model lacked expressive power for periodic message protocols, followed by the problem that interoperability of asynchronous data exchange methods of periodic message protocols and intelligent frameworks was not provided. To solve this problem, this paper proposes a message model extension method for message periodic description to secure the model's expressive power for the periodic message model, and proposes periodic and asynchronous data exchange methods using the extended model to provide interoperability of different data exchange methods.

• Cartoon and Animation Studies
• /
• s.33
• /
• pp.31-53
• /
• 2013

In the early twentieth century, history of animation began by modern artists, they produced various experimental images with the newly invented film and cameras. Artists in the field of movie, photography, paintings and others manipulated images in motion. But as some animated movies won industrial success and popularity, they became the trend but experimental style of early animation preserved by so-called non-mainstreamers or experimental animators, counteracting commercialism. Disney animation also followed the trend by applying realistic Hollywood film style, the worse critics placed a low value on the animation and it tarnished the image, although it was profitable investment from a business standpoint. To make images realistic, they opened a drawing class that animators developed skills to imitate motions and forms from subjects in real life. Also some techniques and gizmos were used to mimic and simulate three dimensional objects and spaces, multiplane camera and compositing 3D CG images with 2D drawings. Moreover, they brought animation stories from fairly tales or folk tales, and Walt's personal interest in live-action movies, they applied Hollywood-film-like narratives and realistic visual, and harsh criticism ensued. On the surface early disney animations' potential seems to be weakened, but in reality it still exists by simplifying and exaggerating forms and color as modern arts. Disney animation employs concepts of the modernism paintings such as simplified shapes and colors to a character design, when their characters are placed together in a scene, that visual elements cause mental reaction. This modification gives a new internal experience to audiences. As conceptual colors in abstract paintings make images appeared to be flat, coloring characters with no shading make them look flat and comparing to them, background images are also appeared to be flat. On top of that, multi-perspective at background images recalls modernist paintings. This essay goes in details with the animation pioneers' works and how Disney animation developed its techniques to emulate real life and analyses color schemes, forms, and spaces in Disney animation compared with modern artists' works, in that the visual language of Disney animation reminds of impression from abstract paintings in the beginning of the twentieth centuries.

• Journal of Korean Home Economics Education Association
• /
• v.21 no.3
• /
• pp.45-64
• /
• 2009

The purpose of this study was to develope issue-centered teaching learning process plan for environment-friendly housing education and to apply it to the housing section of Technology Home Economics in a middle school. PRO-CON cooperative group model was used for the teaching learning process plans of 2-session lessons according to the ADDIE model. In the development stage, 7 activity materials and 20 teaching learning materials (4 reading texts, 12 pictures and photos, & 5 moving pictures) were developed for 2-session lessons. The plans applied to the 7 classes, 222 students, in the third grade of the G middle school in Gyeonggi-do during July 10th-17th, 2008. The results showed that the final pro-con was influenced by the rationals of juries' pro-con of each team and the representative's discussion besides one's environmental perspective. The intention to implement environment-friendly housing activities was significantly increased between before and after the lessons. The contents, methods, goals, and process of the 2-session lessons were evaluated over medium to somewhat higher levels. Those evaluations except methods and general satisfaction with the lessons were differed by sex, students' and their families' interests in environments but not by the type of housing. These results might support that pro-con cooperative group model of controversial issues on parking lot would be appropriate to environment-friendly housing lessons and could apply to broad issues on housing and various schools in other areas.