• Journal of Intelligence and Information Systems
• /
• v.11 no.2
• /
• pp.1-15
• /
• 2005

The explosive growth of the Internet leads to various on-line shopping malls and active E-Commerce. however, as the internet has experienced continuous growth, users have to face a variety and a huge amount of items, and often waste a lot of time on purchasing items that are relevant to their interests. To overcome this problem the comparison shopping systems, which can help to compare items' information with those other shopping malls, have been issued as a solution. However, when users do not have much knowledge what they want to find, a keyword-based searching in the existing comparison shopping systems lead users to waste time for searching information. Thereby, the performance is fell down. To solve this problem in this research, we suggest the Comparison Shopping System using Image Retrieval based on Semantic Web. The proposed system can assist users who don't know items' information that they want to find and serve users for quickly comparing information among the items. In the proposed system we use semantic web technology. We insert the Semantic Annotation based on Ontology into items' image of each shopping mall. Consequently, we employ those images for searching the items instead of using a complex keyword. In order to evaluate performance of the proposed system we compare our experimental results with those of Keyword-based Comparison Shopping System and simple Semantic Web-based Comparison Shopping System. Our result shows that the proposed system has improved performance in comparison with the other systems.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06a
• /
• pp.169-174
• /
• 1996

객체 인식은 대용량의 영상 데이터를 분석, 탐색하고 재구성하기 위한 내용기반 영상 검색의 매우 중요한 분야이며, 특히 인간의 얼굴은 검색 영상 내에서 대부분 주요한 장면에 위치하고 있기 때문에 그 비중이 매우 크다. 본 논문에서는 내용기반 영상 검색을 위한 실시간 얼굴 영역 추출 방법을 제안한다. 제안된 방법에서는 다층 피라미드 구조와 간단한 형태의 머리 형판을 사용하여 얼굴의 후보 영역을 추출한 후, 보다 정확한 얼굴 영역을 추출하기 위하여 후보 영역 내에서 눈의 위치를 탐색하고, 두 눈의 위치를 기준으로 최종적인 얼굴 영역을 추출하였다. 얼굴 후보 영역 추출 단계에서는 얼굴의 형태 정보를 포함하고 있는 모자이크 형판을 사용하여 머리와 턱을 포함한 얼굴 영역을 추출하였으며, 눈 위치 추출 단계에서는 눈의 위치 정보를 사용하여 눈의 탐색 영역을 결정하고, 탐색 영역 내에서 이진 영상 형판을 사용하여 눈의 위치를 추출한 후, 눈 영역의 무게 중심을 눈의 중심 위치로 설정하였다. 마지막 얼굴 영역 추출단계에서는 두 눈의 위치를 기준으로 사각형의 영역을 얼굴 영역으로 추출하였다. 제안된 방법의 성능을 검증하기 위하여 1700장의 다양한 영상에 대하여 실험하였으며, 실험 결과 한 장의 영상에서 얼굴 영역을 추출하는데 있어서, Pentium 166Mz의 PC상에서 평균 3.2초의 처리 속도와 91.7%의 추출률을 보임으로써, 실시간 얼굴 영역 추출에 매우 효과적임을 알 수 있었다.

• Smart Structures and Systems
• /
• v.30 no.2
• /
• pp.145-157
• /
• 2022

The design of safe and economical structures depends on the reliable live load from load survey. Live load surveys are traditionally conducted by randomly selecting rooms and weighing each item on-site, a method that has problems of low efficiency, high cost, and long cycle time. This paper proposes a deep learning-based method combined with Internet big data to perform live load surveys. The proposed survey method utilizes multi-source heterogeneous data, such as images, voice, and product identification, to obtain the live load without weighing each item through object detection, web crawler, and speech recognition. The indoor objects and face detection models are first developed based on fine-tuning the YOLOv3 algorithm to detect target objects and obtain the number of people in a room, respectively. Each detection model is evaluated using the independent testing set. Then web crawler frameworks with keyword and image retrieval are established to extract the weight information of detected objects from Internet big data. The live load in a room is derived by combining the weight and number of items and people. To verify the feasibility of the proposed survey method, a live load survey is carried out for a meeting room. The results show that, compared with the traditional method of sampling and weighing, the proposed method could perform efficient and convenient live load surveys and represents a new load research paradigm.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.182-192
• /
• 2022

All the aspects of human life have been affected by the novel coronavirus (Covid-19). It has rapidly spread in most countries including the Kingdom of Saudi Arabia. As a result, early precautionary actions aiming to minimise the virus effect are taken by the Saudi government. One of these actions is the sudden shift to online classes and suspending the attendees to all educational institutes. Such immediate change can have a significant effect on the educational process, especially for students. One can argue that students' information-seeking behaviour within the current situation can affect their learning quality and outcomes. Therefore, this paper examines the Saudi students' information-seeking behaviour by taking a sample of students from Umm Al-Qura University. A descriptive analysis is conducted with 193 students and two approaches are used to collect data, questionnaire and semi-structured interview. The results showed that the majority of students face difficulties when searching and retrieving e-resources from the university library website. The problems range from mainly poor User Experience (UX), network connection, multiple errors and lack of subscription with academic publishers.

• Child Health Nursing Research
• /
• v.20 no.1
• /
• pp.49-57
• /
• 2014

Purpose: The purpose of this qualitative study was to explore how adolescent survivors of childhood cancer grieve the death of cancer peers. Methods: Data were obtained from Korean adolescents with cancer between the ages of 13 and 18 (N=12) through semi-structured interviews (face-to-face, telephone, and Internet chatting), observations of the social dynamics of participants in self-help groups, and retrieval of personal Web journals. Based on the grounded theory methodology, data collection and analysis were conducted simultaneously, and constant comparative methods were used. Clarke's situational analysis was adopted, and this paper focused on presenting "how to" and "what we can learn" from this analytic strategy. Results: Mapping examples were visualized using of three modes of maps. Adolescent cancer survivors coped with reminders of the "darkness" that ultimately featured their overall grief. Additionally, adolescents' encounters and avoidance of grief were triggered by introspection and interactions with family and friends. Conclusion: Situational analysis provided an efficient way to analyze the experiences of adolescent survivors of childhood cancer by systematizing possible information within the relational social contexts of the research phenomenon.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.112-118
• /
• 2009

Skin color segmentation techniques have been widely utilized for face/hand detection and tracking in many applications such as a diagnosis system using facial information, human-robot interaction, an image retrieval system. In case of a video image, it is common that the skin color model for a target is updated every frame for the robust target tracking against illumination change. As for a single image, however, most of studies employ a fixed skin color model which may result in low detection rate or high false positive errors. In this paper, we propose a novel method for effective skin color segmentation in a single image, which modifies the conditions for skin color segmentation iteratively by the image feedback of segmented skin color region in a given image.

• Journal of Digital Convergence
• /
• v.10 no.8
• /
• pp.287-297
• /
• 2012

In order to prepare for the introduction of the E-Discovery system from the United States and to cope with some causable changes of legal systems, we propose a general E-Discovery process and essential tasks of the each phase. The proposed process model is designed by the analysis of well-known projects such as EDRM, The Sedona Conference, which are advanced research for the standardization of E-Discovery task procedures and for the supply of guidelines to hands-on workers. In addition, Machine Learning Algorithms, Open-source libraries for the Information Retrieval and Distributed Processing technologies based on the Hadoop for big data are introduced and its application methods on the E-Discovery work scenario are proposed. All this information will be useful to vendors or people willing to develop the E-Discovery service solution. Also, it is very helpful to company owners willing to rebuild their business process and it enables people who are about to face a major lawsuit to handle a situation effectively.

• Journal of The Korean Association of Information Education
• /
• v.1 no.1
• /
• pp.92-101
• /
• 1997

There has been increasing demand of hypermedia as computing and educational environment change. Most authoring tools developed recently have various built-in functions., but they are not enough to create hypermedia program or easy to learn. Even though teachers might try to develop hypermedia program with existing authoring tools, they usually come to face with the difficulties of creating new nodes, adding new data, or keeping user's activity records. Therefore, this study investigated to present a prototype of Educational Hypermedia Editor that can be conveniently used in hypermedia programs. According to the theories of courseware design, instructional design, learning theory, and hypertext and hyperemia, design strategies for the study were selected. Based on the analysis of the characteristics of domestic authoring tools as well as foreign authoring tools, the Educational Hypermedia Editor that has authoring and executing mode was designed and developed. Because the Educational Hypermedia Editor was designed for information retrieval CAI(Computer Assisted Instruction) materials, it is expected that the Educational Hypermedia Editor will be extensively used in the urea of social science classes, investigation studies, and information processing studies.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.21 no.4
• /
• pp.67-80
• /
• 2010

The output and usage rate of audio-visual materials have sharply increased as the information industry advances and diverse archives became available. However, the awareness of the audio-visual archives are more of a separate record with collateral value. The organizations that hold these materials have very weak system of the various areas such as the categories and archiving methods. Moreover, the management system varies among the organizations, so the users face difficulty retrieving and utilizing the audio-visual materials. Thus, this study examined the feasibility of the synchronized management of audio-visual archives by comparing the descriptive elements of the audio-visual archives in internal key agencies. The study thereby examines the feasibility of the metadata element of the organizations and that of synchronized management to propose the effect of the use of management, retrieval and service of efficient AV materials. The study also proposes the improvement of descriptive element of metadata.

• Journal of Korea Spatial Information System Society
• /
• v.6 no.2 s.12
• /
• pp.39-49
• /
• 2004

An increasing number of distributed applications will be achieved with mobile technology. These applications face temporary loss of network connectivity when they move. They need to discover other hosts in an ad-hoc manner, and they are likely to have scarce resources including CPU speed, memory and battery power. Software engineers building mobile applications need to use a suitable middleware that resolves these problems and offers appropriate support for developing mobile applications. In this paper, we describe the meta-server building for middleware that addresses reflective context awareness and present usability with demonstration. Metadata is consist of user configuration, device configuration, user context, device context and dynamic image metadata. When middleware send a saving or retrieval request to meta-server, it returns messages to middleware after the verification of the request. This meta-server has the application for multimedia stream services with context awareness.