• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.22-29
• /
• 2022

Recently, with the development of mobile computing power, mobile-based VR and AR services are being developed. Due to network performance and computing power constraints, VR and AR services using large-capacity 3D content have limitations. A study on an efficient 3D content load method for a mobile device is required. The conventional method downloads all 3D content used for AR services at the same time. In this paper, we propose an active 3D content load according to the user's track. The proposed method is a partitioned 3D object load. Edge servers were installed for each area and connected through the MESH network. Partitioned load the required 3D object in the area referring to the user's location. The location is identified through the edge server information of the connected AP. The performance of the proposed method and the conventional method was compared. As a result of the comparison, the proposed method showed a stable Mobile AR Service. The results of this study, it is expected to contribute to the activation of edge server-based AR mobile services.

• 한국인터넷방송통신학회논문지
• /
• 제22권4호
• /
• pp.171-176
• /
• 2022

CNN은 딥러닝의 한 종류로 이미지나 영상 데이터를 처리할 때 사용하는 신경망이다. 필터가 이미지를 순회하며 이미지의 특징을 추출하여 이미지를 구분한다. 딥러닝은 데이터가 많을수록 좋은 모델을 만들 수 있는 특징이 있고, CNN에서는 적은 데이터의 약점을 보완하기 위해 회전, 확대, 이동, 뒤집기 같은 방법의 데이터 증강이라는 기법으로 데이터의 양을 인위적으로 늘리는 방법을 사용한다. 외곽선 이미지 학습은 이미지 데이터에서 외곽선에 해당하는 영역을 추출하는 것이다. CNN 학습 시, 외곽선 이미지 학습이 기존의 데이터 증강기법과 비교하여 성능 향상의 도움이 되는지 확인하고자 한다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.182-187
• /
• 2022

This study aims to study non-rechargeable wrist-type smart bands for those vulnerable to the digital environment. The transition to the digital age means improving the efficiency of human life and the convenience of management. In the digital age, it can be a very convenient infrastructure for the digital generation, but otherwise, it can cause inconvenience. COVID-19 is spreading non-face-to-face culture. The reality is that the vulnerable are complaining of discomfort in non-face-to-face culture. The core of the digital environment is smartphones. Digital life is spreading around smartphones. Technology that drives the digital environment is the core technology of the Fourth Industrial Revolution. The technologies are lot, big data, Blockchain, Smart Mobility, and AI. Related technologies based on these technologies include digital ID cards, digital keys, and nfc technologies. Non-rechargeable wrist-type smart bands based on related technologies can be conceptualized. Through these technologies, blind people can easily access books and manage their ID cards conveniently and efficiently. In particular, access authentication is required wherever you go due to COVID-19, which can be used as a useful tool for the elderly who feel uncomfortable using smartphones. It can also eliminate the inconvenience of the elderly finding or losing their keys.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.292-298
• /
• 2022

Coding education and algorithm education are essential in the era of the fourth industrial revolution. Text-oriented algorithm textbooks are perceived as difficult by students who are new to coding and algorithms. There is a need to develop educational content so that students can easily understand the principles of complex algorithms. This paper has implemented basic sorting algorithms as augmented reality contents for students who are new to algorithm education. To make it easier to understand the concept and principles of sorting algorithms, sorting data was expressed as a 3D box and the comparison of values according to the algorithms and the movement of values were produced as augmented reality contents in the form of 3D animations. In order to help with the understanding of sorting algorithms in C language, the change of variable values and the exchange of data were shown as animations according to the execution order of the code and the flow of the loop. Students can conveniently use contents through a smart phone without special equipment by being produced in a marker-based manner. Interest and immersion, as well as understanding of classes of sorting algorithms can be increased through educational augmented reality-based educational contents.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.8-13
• /
• 2023

We propose a method for removing interference and noise to estimate target information. In wireless channels, information signals are subject to interference and noise, making it is difficult to accurately estimate the desired signal. To estimate the desired information signal, it is essential to remove the noise and interference from the received signal, extracting only the desired signal. If the received signal noise and interference are not removed, the estimated information signal will have a large error in distance and direction, and the exact location of the target cannot be estimated. This study aims to accurately estimate the desired target in space. The objective is to achieve more presice target estimation than existing methods and enhance target resolution.An estimation method is proposed to improve the accuracy of target estimation. The proposed target estimation method obtains optimal weights using linear constraints and the minimum variance method. Through simulation, the performance of the proposed method and the existing method is analyzed. The proposed method successfully estimated all four targets, while the existing method only estimated two targets. The results show that the proposed method has better resolutiopn and superior estimation capability than the existing method.

• 한국인터넷방송통신학회논문지
• /
• 제23권6호
• /
• pp.89-95
• /
• 2023

인간 행동 인식 (Human action recognition, HAR) 기술은 스포츠 분석, 인간과 로봇 간의 상호작용, 대형 사이니지 콘텐츠 등의 애플리케이션에 활용되는 핵심 기술 중 하나이다. 본 논문에서는 몰입형 대형 사이니지 콘텐츠를 위한 STAGCN (Spatial temporal attention graph convolutional network) 기반 인간 행동 인식 시스템을 제안한다. STAGCN은 attention mechanism을 통해 스켈레톤 시퀀스의 시공간적 특징에 서로 다른 가중치를 부과하여, 동작 인식에 중요한 관절 및 시점을 고려할 수 있다. NTU RGB+D 데이터셋을 사용한 실험 결과, 제안된 시스템은 기존 딥러닝 모델들에 비해 높은 분류 정확도를 달성한 것을 확인했다.

• 한국인터넷방송통신학회논문지
• /
• 제24권2호
• /
• pp.191-196
• /
• 2024

최근 여러 기업과 연구기관들이 IoT 장비에서 수집되는 다양한 데이터를 분석하고 실제 응용 서비스를 통해 제공하기 위한 지능형 IoT 기술에 관한 연구가 활발히 진행되고 있다. 하지만 IoT 기기에서 수집되는 데이터들을 연구 및 개발에 사용하기 위해 데이터를 송수신하는 과정에서 개인정보유출과 같은 보안상의 이슈가 발생할 수 있다. 그리고 여러 IoT 기기에서 수집되는 데이터가 증가할수록 데이터 관리에 어려움이 존재하며 데이터를 이동하는 데 큰 비용과 시간이 소요된다. 따라서 본 논문에서는 다양한 기기로 이루어진 연합학습 환경에서 보안상의 이슈와 비효율성을 개선하기 위해 신뢰성이 보장된 이더리움 네트워크 기반의 연합학습 시스템을 개발하고자 한다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권2호
• /
• pp.203-208
• /
• 2024

The convergence of deep learning and smart factory is drawing a lot of attentions from not only industrial but also academic circles. The objective of this article is to quantitatively review on deep learning and smart factory from 2010 to 2023. This research analyzed the 138 articles, extracted from the Core Collection of Web of Science, in terms of four dimensions such as the main trend in article publications, the main trend in article citations, the distribution of article publications by research area, and the keywords representing the main contents of published articles. The quantitative review results reveal the following four points: First, the article publications drastically grew from 2019 to 2022 in its annual trend. Second, the article citations have rapidly grown since 2018. Third, Engineering, Computer Science, and Telecommunications are the top 3 research areas composing the 138 articles. Fourth, it is the top 10 keywords such as 'deep', 'learning', 'smart', 'detection', factory', 'data', 'system', 'manufacturing', 'neural', and 'network' that represent the main contents of the 138 articles published from 2010 to 2023 in deep learning and smart factory. These findings revealed by this quantitative review will be significantly useful for deepening and widening relevant future research on deep learning and smart factory.

• International journal of advanced smart convergence
• /
• 제11권1호
• /
• pp.55-63
• /
• 2022

Although research on the leader's or speaker's voice has been continuously conducted, existing research has a single point of view. Sound analysis of voice characteristics has been studied from engineering perspectives, and leadership trait theory has been studied from a business perspective. Convergence studies on leader voice and member cognition are being attempted today. Convergence research on voice has a positive effect on refinement of voice analysis, diversification of voice use, and establishment of voice utilization strategy. This study explains the current flow of research on convergence between speaker's voice and listener's perception, and suggests a direction for the future development of voice fusion research. Furthermore, in connection with AI in the 4th industrial age, new attempts for voice research are sought. First, advances in AI focus on strategically generating the voices needed for individual situations. Second, the voice corrected in real time will support the leader and speaker to utilize the desired voice type. Third, voices through AI based on big data will affect the cognition, attitude and behavior of individual listeners who members, customers, and students in more diverse situations. The purpose and significance of this study is to suggest the way to research the leader's voice recognized by members, and to suggest a method that can be applied in various situations.

• International Journal of Contents
• /
• 제4권2호
• /
• pp.24-28
• /
• 2008

In this paper, we propose a new approach for content-based video retrieval using non-parametric based motion classification in the shot-based video indexing structure. Our system proposed in this paper has supported the real-time video retrieval using spatio-temporal feature comparison by measuring the similarity between visual features and between motion features, respectively, after extracting representative frame and non-parametric motion information from shot-based video clips segmented by scene change detection method. The extraction of non-parametric based motion features, after the normalized motion vectors are created from an MPEG-compressed stream, is effectively fulfilled by discretizing each normalized motion vector into various angle bins, and by considering the mean, variance, and direction of motion vectors in these bins. To obtain visual feature in representative frame, we use the edge-based spatial descriptor. Experimental results show that our approach is superior to conventional methods with regard to the performance for video indexing and retrieval.