• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.213-218
• /
• 2021

In this paper, we detect and track vehicles by type based on highway daytime driving videos taken with black boxes for vehicles. In addition, we design a real-time MR contents production method that can be newly created by placing substitute videos of each type of detected vehicles in the same location as the new background video. To detect and track vehicles by type, we use the YOLO algorithm. And we also use the mask technique based on RGB color for substitute videos of each type of vehicles detected. The size of the vehicle substitute videos to be used for MR content are substituted by the same size as the area size of the detected vehicles. In this paper, we confirm that real-time MR contents design is possible as a result of experiments and simulations and believe that It will be usefully utilized in the field of VR contents.

• Clinics in Shoulder and Elbow
• /
• v.25 no.3
• /
• pp.217-223
• /
• 2022

Background: YouTube has become a popular source of healthcare information in orthopedic surgery. Although quality-based studies of YouTube content have been performed for information concerning many orthopedic pathologies, the quality and accuracy of information on the rotator cuff have yet to be evaluated. The purpose of the current study was to evaluate the reliability and educational content of YouTube videos concerning the rotator cuff. Methods: YouTube was queried for the term "rotator cuff." The first 50 videos from this search were evaluated. Video reliability was assessed using the Journal of the American Medical Association (JAMA) benchmark criteria (range, 0-5). Educational content was assessed using the global quality score (GQS; range, 0-4) and the rotator cuff-specific score (RCSS; range, 0-22). Results: The mean number of views was 317,500.7±538,585.3. The mean JAMA, GQS, and RCSS scores were 2.7±2.0, 3.7±1.0, and 5.6±3.6, respectively. Non-surgical intervention content was independently associated with a lower GQS (β=-2.19, p=0.019). Disease-specific video content (β=4.01, p=0.045) was the only independent predictor of RCSS. Conclusions: The overall quality and educational content of YouTube videos concerned with the rotator cuff were low. Physicians should caution patients in using such videos as resources for decision-making and should counsel them appropriately.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.37-45
• /
• 2022

As of 2020, about 500 hours of videos are uploaded to YouTube, a representative online video platform, per minute. As the number of users acquiring information through various uploaded videos is increasing, online video platforms are making efforts to provide better recommendation services. The currently used recommendation service recommends videos to users based on the user's viewing history, which is not a good way to recommend videos that deal with specific purposes and interests, such as educational videos. The recent recommendation system utilizes not only the user's viewing history but also the content features of the item. In this paper, we extract the content features of educational video for educational video recommendation based on YouTube, design a recommendation system using it, and implement it as a web application. By examining the satisfaction of users, recommendataion performance and convenience performance are shown as 85.36% and 87.80%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.2
• /
• pp.29-35
• /
• 2023

This paper makes it possible to search videos based on sentence by improving the previous research which automatically generates rich metadata from videos and searches videos by key words. For search by sentence, morphemes are analyzed for each sentence, keywords are extracted, weights are assigned to each keyword, and some videos are recommended by applying a ranking algorithm developed in the previous research. In order to evaluate performance of video search in this paper, a sufficient amount of videos and sufficient number of user experiences are re required. However, in the current situation where these are insufficient, three indirect evaluation methods were used: evaluation of overall user satisfaction, comparison of recommendation scores and user satisfaction, and evaluation of user satisfaction by video categories. As a result of performance evaluation, it was shown that the rich metadata construction and video recommendation implementation in this paper give users high search satisfaction.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.107-115
• /
• 2023

This study analyzes the content of YouTube Vlog videos created by patients of Coronavirus disease 2019 ("COVID-19") in South Korea and viewer comments on those videos. As this new infectious disease started to sweep the world in late 2019 and early 2020, the public started facing fear and uncertainty stemming from the lack of sufficient and accurate information about the virus. At the same time, as COVID-19 patients in South Korea were treated in isolation to prevent the spread of the virus, the patients themselves were experiencing anxiety and exclusion from the society. During this period, there was an increase in YouTube Vlog videos created by the patients in which they shared their experiences going through the treatment and recovery processes. To understand how these YouTube Vlog videos were being used by the patients to connect with the society and seek support in a state of isolation and anxiety, this study conducted a qualitative multi-case analysis of three sample YouTube Vlog video channels to analyze their content, as well as a lexicon-based sentiment analysis of viewer comments to understand the experiences and reactions of viewers. The patients' YouTube Vlog videos showed that they shared similar stages of progress, despite each emphasizing a different main theme. Overall, the tone of the viewer comments became increasingly positive over time, although with some variance among different patient cases and stages. The results confirmed that Vlogs of patients played a significant role in reducing the uncertainty around COVID-19 and strengthening social support for the patients. The findings of this study can improve an understanding of the psychological and behavioral aspects of patient experience in isolated treatment and the impact of shared communication among members of society in times of crisis.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.209-211
• /
• 2022

YouTube, a video platform used by millions of people worldwide, provides a rapidly growing video service. This study aims to understand the characteristics and cultural differences of each country using the Kaggle dataset, one of the public datasets, and to show the usefulness of the public dataset. For this purpose, we analyze data from 11 countries, 15 categories, and about 1.1 million trending videos. This study adopts Python to obtain the number of videos by category for data analysis, the selection period of videos rapidly increasing in popularity, and the ratio of unique videos. In the future, based on machine learning, we plan to research to help diagnose individual videos and establish channel operation plans and strategies by predicting the selection possibility and selection period based on machine learning.

• Journal of radiological science and technology
• /
• v.45 no.1
• /
• pp.31-39
• /
• 2022

This study aimed to analyze educational understanding and satisfaction by survey including for the online educational videos by used online platform (YouTube) which provide resolve patient's questions, require attention and treatment information for a patient with radiation therapy. Video viewing analysis was used by YouTube studio. The survey was analyzed general properties (age, academic ability, disease, and watched of no watched videos) and educational understanding and satisfaction for two groups as no watched and watched patients. The views number was 60% at the female higher than 40% at the male. Based on the standard viewing time (hours), the non-subscription rate was 86.7%. The device type mostly used the mobile phone (82.8%). The viewership of educational videos was lower as the age increased and the academic ability decreased in the survey. The educational understanding increased by 22% at watched group as 4.15 point from at no watched group as 3.4 point (p<0.001), and the educational satisfaction increased by 15.8% at watched group as 4.25 point from at no watched group as 3.67 point (p<0.01). The correlation of understanding (r=0.761) and satisfaction (r=0.767) was high for both no watched and watched groups (p<0.01). The online educational videos increased educational understanding and satisfaction for the patient with radiation therapy. Our study could be used references data for improving the quality of medical services.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.145-149
• /
• 2024

Recently, research on temporal action localization has been actively conducted. In this paper, unlike existing methods, we propose two approaches for learning bidirectional information by creating reverse playback videos for fully supervised temporal action localization. One approach involves creating training data by combining reverse playback videos and forward playback videos, while the other approach involves training separate models on videos with different playback directions. Experiments were conducted on the THUMOS-14 dataset using TALLFormer. When using both reverse and forward playback videos as training data, the performance was 5.1% lower than that of the existing method. On the other hand, using a model ensemble shows a 1.9% improvement in performance.

• Korean Journal of Community Nutrition
• /
• v.29 no.2
• /
• pp.156-170
• /
• 2024

Objectives: This study aimed to investigate the association between how often Korean adolescents watch Mukbang and Cookbang videos and their dietary habits. Methods: Data from the 18th Korea Youth Risk Behavior Survey conducted in 2022 was analyzed for this study. The study included 51,850 middle and high school students and assessed various aspects, including demographics, frequency of watching Mukbang and Cookbang videos per week, dietary habits, health behaviors, and mental health factors. Results: Nearly a third (29.3%) of Korean adolescents watched Mukbang and Cookbang videos one to four times a week, while 13.5% watched them more than five times weekly. Females, those with lower academic achievement, and those from lower socioeconomic backgrounds were significantly more likely to be frequent viewers (P < 0.001). Increased viewing frequency was associated with poorer dietary habits. Adolescents who watched more frequently were less likely to eat breakfast and consume fruits and milk, while their consumption of fast food, high-caffeine drinks, sugary drinks, and late-night snacks increased (P < 0.001). Higher viewing frequency correlated with increased feelings of stress, depression, and loneliness (P < 0.001). Logistic regression analysis confirmed these associations. More frequent viewers were significantly less likely to eat breakfast (odds ratio (OR), 0.63; 95% confidence interval (CI), 0.58-0.68), and more likely to consume fast food (OR, 1.85; 95% CI, 1.69-2.02), high-caffeine drinks (OR, 1.43; 95% CI, 1.30-1.56), sugary drinks (OR, 1.54; 95% CI, 1.41-1.67), and late-night snacks (OR, 1.37; 95% CI, 1.25-1.51). Conclusions: Our findings suggest that frequent exposure to Mukbang and Cookbang content is linked to unhealthy dietary habits in adolescents. Educational programs may be necessary to mitigate the potential for these videos to negatively influence dietary choices.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.289-298
• /
• 2024

As digital mobile technology has advanced, vertical videos have emerged as a prominent format in the contemporary media field, presenting a new visual language that challenges traditional horizontal-centric aesthetic norms. This study delves into the visual and structural parallels and distinctions between traditional East Asian Hanging scrolls and contemporary vertical videos by applying traditional spatial composition techniques such as the 'Three Distances', 'One River, Two Banks', 'Intended Blank', and 'Unity of Poetry, Calligraphy, and Painting' to the creation of modern vertical videos. Through this comparative analysis, the research examines how vertical layouts enhance depth and layering of the screen, deepen emotional expression, and offer creators new avenues for expression. By juxtaposing the spatial compositions of traditional East Asian Hanging scrolls with those prevalent in today's digital vertical videos, this study seeks to uncover new visual languages and aesthetic values within the evolving media field.