• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.207-212
• /
• 2024

The importance of hydrogen fuel cells continues to be emphasized, and there is a growing demand for education and training in this field. Among various educational environments, metaverse education is opening a new era of change in the global education industry, especially to adapt to remote learning. The most significant change that the metaverse has brought to education is the shift from one-way, instructor-centered, and static teaching approaches to multi-directional and dynamic ones. It is expected that the metaverse can be effectively utilized in hydrogen fuel cell engineer education, not only enhancing the effectiveness of education by enabling learning and training anytime, anywhere but also reducing costs associated with engineering education.In this research, inspired by these ideas, we are designing a fuel cell education platform. We have created a platform that combines theoretical and practical training using the metaverse. Key aspects of this research include the development of educational training content to increase learner engagement, the configuration of user interfaces for improved usability, the creation of environments for interacting with objects in the virtual world, and support for convergence services in the form of digital twins.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.69-75
• /
• 2024

This paper proposes an IoT-based indoor autonomous driving system that applies SLAM (Simultaneous Localization And Mapping) and Navigation techniques in a ROS (Robot Operating System) environment based on TurtleBot3. The proposed autonomous driving system can be applied to indoor autonomous wheelchairs and robots. In this study, the operation was verified by applying it to an indoor self-driving wheelchair. The proposed autonomous driving system provides two functions. First, indoor environment information is collected and stored, which allows the wheelchair to recognize obstacles. By performing navigation using the map created through this, the rider can move to the desired location through autonomous driving of the wheelchair. Second, it provides the ability to track and move a specific logo through image recognition using OpenCV. Through this, information services can be received from guides wearing uniforms with the organization's unique logo. The proposed system is expected to provide convenience to passengers by improving mobility, safety, and usability over existing wheelchairs.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.29-37
• /
• 2024

In this paper, we propose an efficient image processing system to detect and track the movement of specific objects such as patients. The proposed system extracts the outline area of an object from a binarized difference image by applying a thinning algorithm that enables more precise detection compared to previous algorithms and is advantageous for mixed-mode design. The binarization and thinning steps, which require a lot of computation, are designed based on RTL (Register Transfer Level) and replaced with optimized hardware blocks through logic circuit synthesis. The designed binarization and thinning block was synthesized into a logic circuit using the standard 180n CMOS library and its operation was verified through simulation. To compare software-based performance, performance analysis of binary and thinning operations was also performed by applying sample images with 640 × 360 resolution in a 32-bit FPGA embedded system environment. As a result of verification, it was confirmed that the mixed-mode design can improve the processing speed by 93.8% in the binary and thinning stages compared to the previous software-only processing speed. The proposed mixed-mode system for object recognition is expected to be able to efficiently monitor patient movements even in an edge computing environment where artificial intelligence networks are not applied.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.281-287
• /
• 2024

In general, design education related to transportation has been recognized as a department specialized in transportation design or as an area of detailed transportation majors within industrial design majors. However, as technological, social, and environmental factors change, the concept of mobility and the ecosystem related to the mobility industry are diversifying, and accordingly, the category of mobility-related design is expanding further. Based on this background, this study is not a mobility design major, but it aims to find implications by analyzing the trend and type of topic selection related to the mobility ecosystem among the last five years of graduation design topics conducted in the design engineering major. As a result of the study, of a total of 131 graduation design works conducted over the past five years, about 30 works were highly related to mobility, and their types were very diverse. In conclusion, it was confirmed that the change and expansion of the mobility ecosystem expanding from products to services and systems were also reflected in the selection of graduation works in that various topics approached from user-centered and user experience were proposed and made into works.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.539-549
• /
• 2024

This study employed text mining techniques like frequency analysis, word clouds, and LDA topic modeling to assess consumer satisfaction and dissatisfaction with Hyundai Motor Company in the Chinese market, compared to brands such as Toyota, Volkswagen, Buick, and Geely. Focusing on compact vehicles from these brands between 2021 and 2023, this study analyzed customer reviews. The results indicated Hyundai Avante's positive factors, including a long wheelbase. However, it also highlighted dissatisfaction aspects like Manipulate, engine performance, trunk space, chassis and suspension, safety features, quantity and brand of audio speakers, music membership service, separation band, screen reflection, CarLife, and map services. Addressing these issues could significantly enhance Hyundai's competitiveness in the Chinese market. Previous studies mainly focused on literature research and surveys, which only revealed consumer perceptions limited to the variables set by the researchers. This study, through text mining and comparing various car brands, aims to gain a deeper understanding of market trends and consumer preferences, providing useful information for marketing strategies of Hyundai and other brands in the Chinese market.

• Journal of Digital Convergence
• /
• v.22 no.1
• /
• pp.33-38
• /
• 2024

In recent years, as more and more middle-aged people who worked at companies are retiring, they are becoming interested in starting their own businesses, and the rate of middle-aged people starting businesses is increasing. The purpose of this study was to analyze the quality and satisfaction of educational services and trust in educational institutions in providing entrepreneurship education to prospective entrepreneurs over the age of 40 who want to start a business, and to analyze the impact of entrepreneurship education on entrepreneurship in the future. Afterwards, the goal is to establish an education strategy to improve the quality of entrepreneurship education. To achieve the purpose of the study, a hypothesis was established and an empirical analysis was conducted on educated prospective entrepreneurs and retirees over 40 years of age. As a result of the analysis, it was confirmed that confidence and reliability ultimately influence the factors that increase satisfaction with entrepreneurship education for middle-aged and older people. Satisfaction was found to play a meaningful role in trust. The research points out that entrepreneurship education institutions should provide education centered on the trainees rather than entrepreneurship education centered on support organizations. Moreover, due to the diversity of education, not only the content and method of education but also the education of employees working in supporting organizations is important.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.891-899
• /
• 2024

The Fourth Industrial Revolution is centered on a personalized demand fulfillment economy and is all about transformation and flexible processing that can deliver what customers want in real time across space and time. This paper implements the construction and operation of a packaging platform that can instantly procure the required packaging products based on real-time orders and evaluates its performance. The components of customer satisfaction are flexible and dependent on the situation which requires efficient management of enterprise operational processes based on an e-SCM platform. An OMS optimized for these conditions plays an important role in maximizing and differentiating the efficiency of a company's operations and improving its cost advantage. OMS is a system of mass customization that provides efficient MOT(Moment of Truth) logistics services to meet the eco-friendly issues of many individual customers and achieve optimized logistics operation goals to enhance repurchase intentions and sustainable business. OMS precisely analyzes the collected data to support information and decision-making related to efficiency, productivity, cost and provide accurate reports. It uses data visualization tools to express data visually and suggests directions for improvement of the operational process through statistics and prediction analysis.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.809-818
• /
• 2024

This paper proposes an action plan for local governments to safely utilize artificial intelligence technology in various local government policies. The proposed method analyzes cases of application of artificial intelligence-related laws and policies in Gyeonggi Province, Seoul City, and New York City, and then presents matters that local governments should consider when utilizing AI technology in their policies. This paper applies the AILocalism-Korea analysis methodology, which is a modified version of the AILocalsm analysis methodology[1] presented by TheGovLab at New York University. AILocalism-Korea is an analysis methodology created to analyze the current activities of each local government in the fields of legal system, public procurement, mutual cooperation, and citizen participation, and to suggest practical alternatives in each area. In this paper, we use this analysis methodology to present 9 action plans that local governments should take based on safe and reliable use of artificial intelligence. By utilizing various AI technologies through the proposed plan in local government policies, it will be possible to realize reliable public services.

• Journal of Legislation Research
• /
• no.41
• /
• pp.401-434
• /
• 2011

The discussion on the adoption of the horizontal regulatory framework is underway to overcome the problems regarding the vertical regulatory framework resulting from a convergence of broadcasting and telecommunications services. Recently, however, the horizontal regulatory framework shows its limitation to regulate the ecosystem established mainly by Google and Apple. The existing horizontal regulatory framework does not fully reflect the characteristics of the two-sided market and the change in the competition structure in the broadcasting and telecommunications sector. What is important to note is that if the existing horizontal regulatory framework is simply applied to the ecosystem, a regulatory imbalance can be caused among ecosystems. The existing horizontal regulatory framework, which is subject to a value chain structure, categorizes business entities into either contents layer or transmission layer and applies the same regulation to all business entities in the same category. However, in the ecosystem, a keystone-player can be categorized into different layers depending on its strategy. Therefore, if the existing horizontal regulatory framework is applied as it is, the regulatory imbalance between keystone-players located in less regulated areas and keystone-players located in more regulated areas occurs resulting in a distortion of competition. There are two possible ways to establish a new regulatory framework to prevent the distortion of competition likely to be caused by the adoption of a horizontal regulatory system. First, a new ecosystem regulatory framework different from the existing one can be established. Second, the horizontal regulatory framework can be modified to reflect the ecosystem elements. The first approach is hard to adopt given the current situation as the approach requires the analysis of all broadcasting and telecommunications ecosystems including mobile and wired services; currently research and study on the competition conditions in the ecosystems is not enough. Therefore, this paper supports the second approach proposing a modified horizontal regulatory framework through the improvement of institutions and remedies suitable for accommodating the ecosystem elements. This paper intends to propose a way to regulate broadcasting and telecommunications ecosystems taking into consideration the ecosystem elements on top of the Telecommunications Business Act, Broadcasting Act, IPTV Act, the competition condition evaluation system of the Basic Act on Broadcasting and Telecommunications Development, and regulation on common carriers under the Telecommunications Business Act.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.