• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.31-38
• /
• 2024

In this paper, we propose an ASAP(AI-driven Service for Advertisement Production) application that provides a generative AI-based automatic advertising image production service. This application utilizes GPT-3.5 Turbo Instruct to generate suitable background mood and promotional copy based on user-entered keywords. It utilizes OpenAI's DALL·E 3 model and Stability AI's SDXL model to generate background images and text images based on these inputs. Furthermore, OCR technology is employed to improve the accuracy of text images, and all generated outputs are synthesized to create the final advertisement. Additionally, using the PILLOW and OpenCV libraries, text boxes are implemented to insert details such as phone numbers and business hours at the edges of promotional materials. This application offers small business owners who face difficulties in advertising production a simple and cost-effective solution.

• Journal of Information Technology Services
• /
• v.7 no.1
• /
• pp.131-149
• /
• 2008

Bandwidth Trading(BT) represents a potential market with over 1 trillion USD across the world and high growth potential. BT is also likely to accelerate globalization of the telecommunications industry and massive restructuring driven by unbundling rush. However, systematic researches on BT remain at an infant stage. This study starts with structure analysis of the Internet industry, and discusses significance of Internet interconnection with respect to BT Issues. We also describe the bandwidth commoditization trends and review technical requirements for effective Internet interconnection with BT capability. Taking a step further, this study explores the possibility of improving efficiency of network providers and increasing user convenience by developing an architectural prototype of Hub-&-Spoke interconnection model required to facilitate BT. The BT market provides an Innovative base to ease rigidity of two-party contract and Increase service efficiency. However, as fair, efficient operation by third party is required, this research finally proposes an exchanging hub named NIBX(New Internet Business eXchange).

• Journal of Service Research and Studies
• /
• v.4 no.1
• /
• pp.49-59
• /
• 2014

Context-aware computing is an emerging paradigm to achieve ubiquitous computing environments by enabling computer systems to understand their situational contexts. A context-aware system uses context to provide relevant information and services to the user depending on the user's task. In this paper, we propose an ontology-based context-aware modeling methodology that transmits low-level contexts acquired by directly accessing various sensors in the physical environments to high-level contexts. With these high-level contexts, context-aware application can provides proactive and intelligent services using ECA (Event-Condition-Action) rules. We implemented a home robot service in smart office environment.

• Journal of Computing Science and Engineering
• /
• v.6 no.1
• /
• pp.60-66
• /
• 2012

It has been proved that information and communication technology (ICT) solutions for personalized health (PHealth) and ambient assisted living (AAL) can support people in their daily life activities. Several solutions have been demonstrated to empower different levels of services through seamless data acquisition and specific users' interaction modalities. Usually services usability and accessibility are handled in the design process and are validated with small users' groups. Moreover, while service design and systems development have been extensively described in literature, service deployment methodologies are not properly addressed and documented. Proper reference guidelines are also missing. The most common methodologies like unified process (UP) or ICONX can cover only the design and the development of PHealth services without a clear description on the following phases such as deployment, service provision and maintenance. These phases present several risks to be taken into account right from the beginning of the implementation of PHealth or AAL services. This paper focuses on the description of a structured methodology to deploy PHealth services and how this process can be supported by integrated software routines and adapting the UP framework in particular the "Transition phase."

• Journal of Smart Tourism
• /
• v.3 no.1
• /
• pp.41-47
• /
• 2023

Tourism and hospitality have encountered significant changes in recent years as a result of the rapid development of information technology (IT). Customers now expect more expedient services and customized travel experiences, which has intensified competition among service providers. To meet these demands, businesses have adopted sophisticated IT applications such as ChatGPT, which enables real-time interaction with consumers and provides recommendations based on their preferences. This paper focuses on the AI support-prompt middleware system, which functions as a mediator between generative AI and human users, and discusses two operational rules associated with it. The first rule is the Information Processing Rule, which requires the middleware system to determine appropriate responses based on the context of the conversation using techniques for natural language processing. The second rule is the Information Presentation Rule, which requires the middleware system to choose an appropriate language style and conversational attitude based on the gravity of the topic or the conversational context. These rules are essential for guaranteeing that the middleware system can fathom user intent and respond appropriately in various conversational contexts. This study contributes to the planning and analysis of service design by deriving design rules for middleware systems to incorporate artificial intelligence into tourism services. By comprehending the operation of AI support-prompt middleware systems, service providers can design more effective and efficient AI-driven tourism services, thereby improving the customer experience and obtaining a market advantage.

• Journal of Korea Multimedia Society
• /
• v.20 no.9
• /
• pp.1559-1566
• /
• 2017

Recently in the IoT(Internet of Things) environment, a data collection in real-time through device's sensor has increased with an emergence of various devices. Collected data from IoT environment shows a large scale, non-uniform generation cycle and atypical. For this reason, the distributed processing technique is required to analyze the IoT sensor data. However if you do not consider the optimal scheduling for data and the processor of IoT in a distributed processing environment complexity increase the amount in assigning a task, the user is difficult to guarantee the QoS(Quality of Service) for the sensor data. In this paper, we propose APQTA(Adaptive Priority Queue-driven Task Allocation method for sensor data processing) to efficiently process the sensor data generated by the IoT environment. APQTA is to separate the data into job and by applying the priority allocation scheduling based on the deadline to ensure that guarantee the QoS at the same time increasing the efficiency of the data processing.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.3
• /
• pp.95-100
• /
• 2011

Due to rapid growth and development of telecommunication information technology, interest has been amplified regarding ubiquitous network computing and user-oriented service. Also, the rapid development of related technologies has been a big spotlight. Smart phone, with features such as a PC with advanced features is a mobile phone. According to environment and infrastructure development, a variety of mobile-based application software to provide various kinds of information and services has been released. However, most of them are provider-driven information systems and aim to provide large amounts of information simply to an unspecified number of users. Therefore, customized or personalized provision of information and service explained earlier for individual users has been hardly come true. According to background and need, this study wants to design and implement recommendations system for personalization and customization in mobile environments. To acquire more accurate recommendation results, recommendation system shall be composed using the Hybrid Filtering. Effective information recommendation according to user's situation by using user's context-information of purpose and location that are available in mobile devices before running the filtering of the information to improve the quality of recommendations.

• Journal of the HCI Society of Korea
• /
• v.10 no.2
• /
• pp.35-43
• /
• 2015

As augmented reality (AR) technology has been utilized to enhance the user experience, several AR applications have been developed in the cultural heritage domain. Although there has been significant progress in this area, naive augmentation representation becomes an obstacle to provide an enhanced user experience and there has been little research on an effective AR experience methodology that reflects the characteristics of AR technology. Furthermore, the development of temporary content that comes from the absence of the authoring framework restrains the content ecosystem, which is an essential requisite for sustainable service. To resolve these issues, we propose a space-driven AR experience methodology, Spacetelling, to extend established object-oriented augmentation trends and Storyscape that generates spatio-temporal related contents for the spacetelling and supports sustainable service. Moreover, we present the wrap-up system framework covering both features mentioned above for the archeological site tour. Finally, we present our work-in-progress project, K-Culture Time Machine Project, to investigate the practical feasibility of our proposals. Through these proposals, we expect that sustainable AR applications with improved user experience will be possible in the cultural heritage domain.

• KIISE Transactions on Computing Practices
• /
• v.21 no.9
• /
• pp.587-595
• /
• 2015

Several fields of science have traditionally demanded large-scale workflow support, which requires thousands of central processing unit (CPU) cores. In order to support such large-scale scientific workflows, large-capacity cluster systems such as supercomputers are widely used. However, as users require a diversity of software packages and configurations, a system administrator has some trouble in making a service environment in real time. In this paper, we present a container-based cluster management platform and introduce an implementation case to minimize performance reduction and dynamically provide a distributed computing environment desired by users. This paper offers the following contributions. First, a container-based virtualization technology is assimilated with a resource and job management system to expand applicability to support large-scale scientific workflows. Second, an implementation case in which docker and HTCondor are interlocked is introduced. Lastly, docker and native performance comparison results using two widely known benchmark tools and Monte-Carlo simulation implemented using various programming languages are presented.

• The Journal of Society for e-Business Studies
• /
• v.14 no.4
• /
• pp.149-166
• /
• 2009

With the rapid development of Web Service technology, the number of Web Service providers which provide same Web Services are increasing. As a result, the QoS elements become more and more important factors for Web Service matchmaking. But, most of previous research efforts do not consider various QoS elements including Service-specific QoS elements during the matchmaking process. In this paper, we propose a Web Service matchmaking scheme which allow dynamic QoS adaptation using the RSS technique. We first classify various QoS elements and describe an extensible QoS model. We then explain a matchmaking scheme, which can utilize the proposed QoS elements. We also show how to dynamically add user-specific QoS elements using the RSS mechanism, thus improving the correctness of web service matchmaking process. Finally, we implemented the proposed schemes and showed the usefulness of our methods through some experiments.