• The Journal of Information Systems
• /
• v.29 no.1
• /
• pp.113-136
• /
• 2020

Purpose In recent years, "Internet + " is a new social form. Has already brought the vitality of social and economic entities. The rapid development of Internet globalization, promote the development of an emerging network interaction, "Live broadcast". Viewers from all over the world can watch various types of live programs by connecting to the Internet. Viewers and live broadcasters can generate instant and efficient interactions. Design Many companies have taken advantage of the advantages of the live broadcast platform. Use live broadcasts for brand marketing activities. Branding compared to offline, online advertising is cheaper, Spread more quickly, get feedback from consumers more realistic. Merchants are also aware that this type of interaction creates a closer connection between consumers and businesses. This article will deduce a unique research model through lots of prior studies. Establish independent variables from two aspects of live software features and consumer features, and from the seven hypotheses derived, summarize how to make consumers more loyal to the same brand. The audience of Korean and Chinese live broadcast software is also growing. In order compare the differences between the consumer groups in Korea and China, this article uses the same research model, analysis of consumers in Korea and China. Findings Finally based on the results of the study. Proposal for rationalization of companies that use Korean-Chinese live broadcast platforms for brand marketing.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.75-86
• /
• 2022

The existing image quality assessment (IQA) datasets have a small number of samples. Some methods based on transfer learning or data augmentation cannot make good use of image quality-related features. A No Reference (NR)-IQA method based on multi-task training and quality awareness is proposed. First, single or multiple distortion types and levels are imposed on the original image, and different strategies are used to augment different types of distortion datasets. With the idea of weak supervision, we use the Full Reference (FR)-IQA methods to obtain the pseudo-score label of the generated image. Then, we combine the classification information of the distortion type, level, and the information of the image quality score. The ResNet50 network is trained in the pre-train stage on the augmented dataset to obtain more quality-aware pre-training weights. Finally, the fine-tuning stage training is performed on the target IQA dataset using the quality-aware weights to predicate the final prediction score. Various experiments designed on the synthetic distortions and authentic distortions datasets (LIVE, CSIQ, TID2013, LIVEC, KonIQ-10K) prove that the proposed method can utilize the image quality-related features better than the method using only single-task training. The extracted quality-aware features improve the accuracy of the model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2053-2067
• /
• 2023

This paper proposes two video quality assessment methods based on deep neural network. (i)The first method uses the IQF-CNN (convolution neural network based on image quality features) to build image quality assessment method. The LIVE image database is used to test this method, the experiment show that it is effective. Therefore, this method is extended to the video quality assessment. At first every image frame of video is predicted, next the relationship between different image frames are analyzed by the hysteresis function and different window function to improve the accuracy of video quality assessment. (ii)The second method proposes a video quality assessment method based on convolution neural network (CNN) and gated circular unit network (GRU). First, the spatial features of video frames are extracted using CNN network, next the temporal features of the video frame using GRU network. Finally the extracted temporal and spatial features are analyzed by full connection layer of CNN network to obtain the video quality assessment score. All the above proposed methods are verified on the video databases, and compared with other methods.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.149-159
• /
• 2023

The Republic of Korea (ROK) Army is developing the Army Synthetic Battlefield Training System and plans divisional-level Live, Virtual, and Constructive (LVC) integrated training. This study proposes a plan to apply VR/AR/MR (Virtual Reality/Augmented Reality/Mixed Reality) technology to LVC integrated training systems to enhance the efficiency and effectiveness of future LVC integrated training. The study investigated immersive military training systems in the ROK and advanced countries. As a result, we confirm that immersive technology can significantly improve the efficiency and effectiveness of military training. Accordingly, we review the key technologies required for building a defense training system with immersive features and propose training subjects that can be enhanced in effectiveness and efficiency when built with an immersive approach. We also propose a plan to apply immersive technology to the Live, Virtual, and Constructive systems for the development of future LVC integrated training system.

• Journal of KIISE:Software and Applications
• /
• v.30 no.10
• /
• pp.904-911
• /
• 2003

In this paper, we propose an effective method for the distinction between machine-printed and handwritten Korean address images. It is important to know whether an input image is handwritten or machine-printed, because methods for handwritten image are quite different from those of machine-printed image in such applications as address reading, form processing, FAX routing, and so on. Our method consists of three blocks: valid connected components grouping, feature extraction, and classification. Features related to width and position of groups of valid connected components are used for the classification based on a neural network. The experiment done with live Korean address images has demonstrated the superiority of the proposed method. The correct classification rate for 3,147 testing images was about 98.85%.

• Journal of Information Technology Services
• /
• v.11 no.3
• /
• pp.161-175
• /
• 2012

A novel concept of ICT based service, which is called N-device service, is proposed and implemented in the form of N-device smart education services. The N-device services are different from the existing N-screen services in terms of the number of devices a user is using for a specific service at the same time. A N-device service consists of several smart devices which are different in size, software and hardware platform, mobility, manufacturer and the like by fully utilizing the characteristic of each device. The major and unique features of N-device services are analyzed and depicted in a strict way. Those are shared role for each device, service by configurable device, one sensor multiple use, real-time data sharing, role shifting and new market creation. It is turned out that the N-device service is more human centric compared with existing ICT based services and can give richer digital experience to users because non-existent services become possible with the new concept. However, there exist several barriers to be implemented and commercialized in the real world. Those include high development cost and time, small market and different application platforms of devices. These barriers can be overcome by technical advances and cooperation between relevant parties. The smart education is very prominent area, in which the novel concept can be applied with high priority because Korean government announced its plan to boost up new educational services with big budget and these are acceptable by enthusiastic Korean parents and students. That's why the N-device service is implemented in the education area, which is called as "livessam(live teacher)," with four smart devices, IPTV, tablet PC, PC and smart phone. By providing both detailed service scenario and techniques, we shows that the novel education service is technically feasible and acceptable by teachers and students.

• Journal of Digital Convergence
• /
• v.9 no.5
• /
• pp.225-233
• /
• 2011

Internet telephony is an Internet service which supports voice telephone using VoIP technology on the IP-based Internet. It has some advantages in that voice telephone services can be accompanied with multimedia services such as video communication and messaging services. Recently, the introduction of smart phones has led to a growth in social networking services and thus, the research and development of Internet telephony has been actively progressed and has the potential to become a replacement for the telephone service that is currently being used. In this paper we designed and implemented a recording system which records voice data of SIP-based Internet telephone's voice calls. It is developed on the linux system and has some features such as audio mixing of two in/out voice channels, live packet sniffing, and the ability to transfer mixed audio files to the log file server. These functions are implemented using various open source softwares. Afterwards, this VoIP recording system will be applied as a base technology to advanced services like a VoIP-based call center system.