• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.548-566
• /
• 2013

The availability of technology and the abundance of experts in universities create an ample opportunity to provide a venue that allows a knowledge seeker to easily connect with and request advice from university experts. On the other hand, outsourcing provides opportunities and remains one of the emerging trends in organizations, and can very clearly observed in the Philippines. This paper describes the development of a reliable web-based approach to Knowledge Product Outsourcing (KPO) services in the Silliman Online University Learning system. The system is called an "e-Knowledge Box."It integrates Web 2.0 technologies and mechanisms, such as instant messaging, private messaging, document forwarding, video conferencing, online payments, net meetings, and social collaboration together into one system. Among the tools used are WAMP Server 2.0, PHP, BlabIM, Wordpress 3.0, Video Whisper, Red5, Adobe Dreamweaver CS4, and Virtual Box. The proposed system is integrated with the search engine in URLs, Web feeds, email links, social bookmarking, search engine sitemaps, and Web Analytics Direct Visitor Reports. The site demonstrates great web usability and has an excellent rating in functionality, language and content, online help and user guides, system and user feedback, consistency, and architectural and visual clarity. Likewise, the site was was rated as being very good for the following items: navigation navigation, user control, and error prevention and correction.

• Electronics and Telecommunications Trends
• /
• v.27 no.4
• /
• pp.114-122
• /
• 2012

최근 CCTV(Closed Circuit Television)의 설치가 증가하면서 효율적인 모니터링을 위하여 지능형 영상분석 기술에 대한 관심이 높아지고 있다. 지능형 영상분석 기술은 영상의 정보를 분석하여 자동으로 이상 행위를 탐지하고 관리자에게 경보를 전송하는 기술로써, 사고를 사전에 예방하고 사고가 발생한 경우에는 신속하게 대응하여 피해를 줄일 수 있게 해준다. 본고에서는 지능형 영상분석 기술이 탐지할 수 있는 이상 행위, 즉 이벤트를 그 목적에 따라서 보안, 비즈니스 인텔리전스, 객체인식으로 구분하여 현재 기술 수준을 살펴볼 것이다. 그리고 앞으로 지능형 영상분석에서 이벤트 탐지 기술의 발전 방향을 사람의 행동인식, 행위 기반 이상 현상 탐지, 군중 환경에서 이벤트 탐지, 지능형 영상분석 구조의 변화 등의 관점으로 구분하여 살펴보고자 한다.

• Annual Conference of KIPS
• /
• 2014.04a
• /
• pp.939-940
• /
• 2014

본 논문에서는 CCTV설치 증가로 많은 양의 영상정보 데이터가 저장되고 있지만 활용되지 못하고 있는 문제를 해결하기 위해서 빅데이터 분석 동향과 기술을 조사 및 분석하였다. 이를 통해 영상정보 빅데이터 분석을 하고 소상공인 창업지원 서비스와 도시 인프라 개 보수 지원 서비스를 제공하는 도시고도화 지원 시스템을 설계하였다.

• Journal of Multimedia Information System
• /
• v.5 no.4
• /
• pp.257-264
• /
• 2018

Over the years application of computer vision techniques in sports videos for analysis have garnered interest among researchers. Videos of sports games like basketball, football are available in plenty due to heavy popularity and coverage. The goal of the researchers is to extract information from sports videos for analytics which requires the tracking of the players. In this paper, we explore use of deep learning networks for player spotting and propose an algorithm for tracking using Kalman filters. We also propose an algorithm for finding distance covered by players. Experiments on sports video datasets have shown promising results when compared with standard techniques like mean shift filters.

• Electronics and Telecommunications Trends
• /
• v.37 no.5
• /
• pp.22-32
• /
• 2022

Optical character recognition is a primary technology required in different fields, including digitizing archival documents, industrial automation, automatic driving, video analytics, medicine, and financial institution, among others. It was created in 1928 using pattern matching, but with the advent of artificial intelligence, it has since evolved into a high-performance character recognition technology. Recently, methods for detecting curved text and characters existing in a complicated background are being studied. Additionally, deep learning models are being developed in a way to recognize texts in various orientations and resolutions, perspective distortion, illumination reflection and partially occluded text, complex font characters, and special characters and artistic text among others. This report reviews the recent deep learning-based text detection and recognition methods and their various applications.

• Research in Mathematical Education
• /
• v.25 no.1
• /
• pp.1-20
• /
• 2022

Collaborative learning has been highlighted as an effective method of teachers' professional development in various studies. To disclose teachers' discourse threads in the process of collaborative learning for developing their knowledge, this paper adopted two methods including "content analysis" and "time-sequential analysis" of learning analytics. Such analyses were implemented for mining teachers' updated knowledge and the discourse threads in the discussion during collaborative learning. The materials for analysis involved two aspects: one was from the video-taped lesson observation reports written by teachers before and after discussing, and the other was from their discourses during the discussion process. The results proved that teachers' knowledge for teaching the centroid of a triangle was updated in the collaborative learning period, and also revealed the discourse threads of teachers' collaboration contained "requesting information or opinions", "building on ideas", and "providing evidence or reasoning", with the emphasis on "challenging ideas or re-focusing talk"

• The Journal of the Korea Contents Association
• /
• v.20 no.9
• /
• pp.29-42
• /
• 2020

The purpose of this study is to present a qualitative research method for extracting and analyzing the comments written by YouTube video users. To do this, we used YouTube users' feedback to measure the hedonic, social, and utilitarian gratification of use and gratification theory(UGT) through by using analysis and topic modeling. The result of the measurement found that the first reason why users watch the trot singer, Cho Myung-sub's video in the KBS Korean broadcasting channel is to achieve hedonic gratification with high frequency. In word-document network analysis, the degree of centrality was high in words, such as 'cheering', 'thank you', 'fighting', and 'best'. Betweenness centrality is similar to the degree of centrality. Eigenvector centrality also shows that words such as 'love', 'heart', and 'thank you' are the most influential words of users' opinions. The results of the centrality analysis present that the majority of video users show their 'love', 'heart' and 'thank you' for the video. it indicates that the high words in centrality analysis is consistent with the high frequency words of hedonic and social gratification dimension of the UGT. The study has research methodological implication that shed light on the motivations for watching YouTube videos with UGT using text mining techniques that automate qualitative analysis, rather than following a survey-based structural equation model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.11
• /
• pp.3384-3389
• /
• 2009

There are two major problems with current National GAP system. One was false in traceability record because it was written or inputted by farmers or distributers and no other measures to check the accuracy was valid. The other was incapability of tracking back and recalling the contaminated agricultural products. For solving these matters, IT convergence model which combined information technology with agricultural experience is elaborated. In IT convergence model, video analytic system classifies every activity depending on the pre-programmed farming process and create the traceability data automatically. Also real time trace system based on USN would solve the problem of tracking back. This system transmits the present location and monitors data of agricultural products from farm to table at all times.

• Fashion & Textile Research Journal
• /
• v.26 no.1
• /
• pp.65-77
• /
• 2024

This study aimed to propose effective ways to integrate CLO into educational settings by conducting a comparative analysis of pattern functions in YUKA and CLO, specifically focusing on skirt prototypes and variations. CLO, being a 3D virtual sample CAD tool, is mainly used in education to facilitate the creation of 3D virtual clothing. In order to explore the applicability of CLO's pattern functions in pattern education, CAD education experts were asked to produce two types of skirt prototypes and two skirt variations. Subsequently, in-depth interviews were conducted. In addition, the skirt pattern creation process was recorded on video and used for comparative analysis of YUKA and CLO pattern functions. The comparison revealed that CLO provides the pattern tools necessary for drafting skirt prototypes. The learning curve for acquiring the skills necessary for drafting and transforming skirt prototypes was found to be relatively shorter for CLO compared to YUKA. In addition, due to CLO's surface-based pattern drawing method, it is difficult to move or copy only specific parts of the outline, and there are some limitations in drawing right angle lines. In the pattern transformation process, CLO's preview function proved to be advantageous, and it was highly rated on user convenience due to the intuitive UI. Thus, CLO shows promise for pattern drafting education and is deemed to have high scalability as it is directly linked to 3D virtual clothing.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.20 no.3
• /
• pp.13-23
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis Detecting and tracking objects in continuous video is essential in self-driving cars, security and surveillance systems, sports analytics, medical image processing, and more. Correlation tracking methods such as Normalized Cross Correlation(NCC) and Sum of Absolute Differences(SAD) are used as an effective way to measure the similarity between two images. NCC, a representative correlation tracking method, has been useful in real-time environments because it is relatively simple to compute and effective. However, correlation tracking methods are sensitive to rotation and size changes of objects, making them difficult to apply to real-time changing videos. To overcome these limitations, this paper proposes an object tracking method using the Histogram of Oriented Gradients(HOG) feature to effectively obtain object data and the Convolution Neural Network(CNN) algorithm. By using the two algorithms, the shape and structure of the object can be effectively represented and learned, resulting in more reliable and accurate object tracking. In this paper, the performance of the proposed method is verified through experiments and its superiority is demonstrated.