• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.253-258
• /
• 2008

Recently, game players want new game requiring more various tactics and strategies in the complex environment beyond simple and repetitive play. Various artificial intelligence techniques have been suggested to make the game characters learn within this environment, and the recent researches include the neural network and the genetic algorithm. The Genetic programming(GP) has been used in this study for learning strategy of the agent in the pursuit-evasion problem which is used widely in the game theories. The suggested GP algorithm is faster than the existing algorithm such as neural network, it can be understood instinctively, and it has high adaptability since the evolving chromosomes can be transformed to the reasoning rules.

• The KIPS Transactions:PartD
• /
• v.13D no.4 s.107
• /
• pp.603-612
• /
• 2006

Recently the web service area is rapidly growing as the next generation IT paradigm because of increase of concern about SOA(Services-Oriented Architecture) and growth of B2B market. Since a service discovery through UDDI(Universal Description, Discovery and Integration) is limited to a functional requirement, it is not considered an effect on frequency of service using and reliability of mutual relation. That is, a quality as nonfunctional aspect of web service is regarded as important factor for a success between consumer and provider. Therefore, the web service selection method with considering the quality is necessary. This paper suggests the agent-based quality broker architecture and selection process which helps to find a service providing the optimum quality that the consumer needs in a position of service consumer. A theory of agent is accepted widely and suitable for proposed system architecture in the circumstance of distributed and heterogeneous environment like web service. In this paper, we considered the QoS and CoS in the evaluation process to solve the problem of existing researches related to the web service selection and used PROMETHEE(Preference Ranking Organization MeTHod for Enrichment Evaluations) as an evaluation method which is most suitable for the web service selection among MCDM approaches. PROMETHEE has advantages that solve the problem that a pair-wise comparison should be performed again when comparative services are added or deleted. This paper suggested a case study with the service composition scenario in order to verify the selection process. In this case study, the decision making problem was described on the basis of evaluated values for qualities from a consumer's point of view and the defined service level.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.11
• /
• pp.1363-1372
• /
• 1999

에이전트 기반 이동 컴퓨팅 환경에서 전자 상거래를 구현하기 위해 가장 필요로 하는 것은 안전한 지불 구조를 제공하는 것이다. 본 연구에서는 불확정 전송 기법 1,2 을 사용한 비대화형 엔티티 인증 기법과 Horster 기법 4,5 을 기반으로 메시지 복원 기능을 제공하는 공정 은닉 서명 기법을 제시한다. 또한 이를 직접 Brands가 제시한 오프-라인 전자 지불 시스템 3,6 에 접목한다. 인증 단계가 비대화형으로 수행되므로 이동 엔티티 인증에 효율적이고, 메시지 복원 기능을 갖고 공개 검증 기능을 제공하는 은닉 서명을 적용하기 때문에 카운터 방식을 사용한 스마트 카드 기반 전자 지불 시스템 6 에 효과적으로 적용할 수 있었다. 전자 화폐에 대해서 신뢰 센터에 의한 공정성 검토 기능을 추가로 제공하므로 전자 지불 시스템의 신뢰성을 향상시킬 수 있다.Abstract The primary requirements for realizing the electronic commerce in agent based mobile computing environments are to implement the compatible secure payment framework. In this paper, we propose both the non-interactive entity authentication scheme that is combined with oblivious transfer protocol 1,2 and the message recovery fair blind signature based on Horster scheme 4,5 . And these techniques are directly applied to the Brand's off-line electronic payment system 3,6 . As the authentication processes are done by non-interactive manner, we can also get efficiency for mobile entity authentication. Additionally, as the used signature scheme provides a message recovery function with publicly verifiable properties, it is efficiently applicable to a counter based off-line electronic payment scheme 6 based on the additional device like smart card. Therefore, we can enhance the reliability of proposed electronic payment system based on the publicly verifiable fairness in its electronic cash by a trusted judge.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.9_10
• /
• pp.417-420
• /
• 2008

We consider the problem of optimizing the performance of a system shared by selfish non-cooperative users. In this problem, small jobs which the users request should be scheduled on a set of shared machines with their speed functions, each of which dependson the amount of jobs allocated on a machine. The performance of the system is measured by the maximum of the completion times when the machines complete the jobs allocated on them. The selfish users can choose a machine on which their jobs are executed, and they choose the fastest machine. But it typically results in suboptimal system performance. The Price of Anarchy(PoA) was introduced as a measure of the performance degradation due to the user's selfish behavior. The PoA is the worst-case ratio of the cost of a Nash equilibrium to the optimal cost. In this paper, we estimate the PoA for the above scheduling problem.

• Journal of Korea Game Society
• /
• v.3 no.1
• /
• pp.74-85
• /
• 2003

If the game characters in the cyber world speak the same dialogues as in the real world, it will give game players more fun and realism. And game players are more and more immersed into the cyber space. However, we observed that only simple and primitive dialogues are used at the market places in most MMORPGS. We introduce personality psychology theory for generating the personality of NPC in MMORPG. And we suggest how to make a conversation between PC (Playable Character) and NPC (Non - Playable Character) according to 'Extroversion - Introversion dimension' and 'Neuroticism dimension'. And we implement the personality dialogue generation program, which is composed of two parts. One is for generating personality, and the other for making dialogue. Personality generator can set a NPC's personality automatically, and Dialogue Maker can control the dialogue styles, quantities, and characteristics of NPC. Thus, the program implemented in this paper can help game designer and scenario writer to make game characters easily. The approach in this paper can be applied to generate various game characters and used to represent agents and avatars of real-time animation.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.5
• /
• pp.522-538
• /
• 2001

This paper presents a cal center which is a subsystem of a web-based real time monitoring system of intensive care units. Based on Computer-Telephony Integration (CTI) technology, the call center attempts to efficiently and automatically send messages to patients\` families, doctors, and other staffs in hospital via communication media suitable to the occasion. The problem of determining appropriate media can be very complicated by the urgency of a message, calling time, and communication media available to the target person. We use the Dempster-Shafer theory, one of the uncertainty handling methods, to determine the most suitable communication media that will transmit a message rapidly and safely. In addition, we use agent technology to perform the calling process without requiring the intervention of the user of the call center. this call center enables message transfer through various communication media in an integrated environment, and relieves medical staff from the calling process, which in turn will make a contribution toward enhancing medical service.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.328-333
• /
• 2003

NGE (Nested Generalized Exemplars) proposed by Salzberg improved the storage requirement and classification rate of the Memory Based Reasoning. It constructs hyperrectangles during training and performs classification tasks. It worked not bad in many area, however, the major drawback of NGE is constructing hyperrectangles because its hyperrectangle is extended so as to cover the error data and the way of maintaining the feature weight vector. We proposed the OH (Optimizing Hyperrectangle) algorithm which use the feature weight vectors and the ED(Exemplar Densimeter) to optimize resulting Hyperrectangles. The proposed algorithm, as well as the EACH, required only approximately 40% of memory space that is needed in k-NN classifier, and showed a superior classification performance to the EACH. Also, by reducing the number of stored patterns, it showed excellent results in terms of classification when we compare it to the k-NN and the EACH.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2001.12a
• /
• pp.413-426
• /
• 2001

본 연구는 첫째, 정보통신기술의 발달이 시각장애인 복지 증진에 미칠 수 있는 가능성에 대한 이론적인 부분을 고찰하였다. 둘째, 우리나라 시각장애인 정보화의 문제점과 해결책을 도출하였고 셋째, 시각장애 사용자를 위한 전자상거래 인터페이스 디자인의 분석 및 설계를 통해 전자상거래에서 시각장애 사용자들이 큰 제약없이 사용할 수 있는 방안을 제시하고자 한다. 현재 시각장애인들의 웹 사용을 보면 시각장애 전용 S/W의 보조 하에 사용을 하고 있다. 그러한 보조 도구의 실정에 맞도록 텍스트 버전 및 Non-Frame버전, Alt-Text 옵션, 캡션 등을 넣어 접근성을 확보하고 인터넷을 큰 제약을 받지않고 이용할 수 있도록 웹 페이지의 설계가 필요한 실정이다. 이를 위하여 먼저 시각장애에 대한 개념과 원인 및 종류 그리고 특성을 통해 시각장애인에 대한 이론적 배경을 파악하였다. 그리고 시각장애인의 정보화 환경과 이용 현황과 시각장애인의 정보 접근을 제도적, 기기 및 소프트웨어 개발 측면에서 분석을 하였고, 장애인을 위한 정보통신기술 중 대표적인 사례를 검토해 보았다. 다음으로 국내외의 대표적인 전자상거래 사이트에서의 인터페이스를 화면구성(Layout), 텍스트(Text), 그래픽(Graphic), 멀티미디어(MultiMedia) 측면에서 분석을 하였다. 분석한 내용을 바탕으로 시각장애 사용자의 입력(User Input) 부분을 고려한 인터페이스 방향을 제시하고 프로토타입을 개발하여 시험 대상 사이트와의 만족도를 시각장애 사용자를 통해 비교 ·분석하였다. 결론부분에서는 정보불평등을 해소하고, 정보통신기술이 장애인의 복지향상에 기여하도록 하기 위해 전자상거래 싸이트에서의 시각 장애인들을 위한 방향을 제시하고자 한다.박의 표현, 등록 및 색인방법 (c) 공급 선박의 분류와 표현 방법 (d) 에이전트의 정보 수집을 위한 메시지 표현 방법 (e) 수집된 선박정보의 데이터베이스 저장 표현방법 (f) 요구 선박을 찾아주는 정보제공 서비스가 요구된다.동을 보여 조사대상 5호분, 6호분, 7호분, 중 가장 심한 거동을 보이고 있다. 이는 고분 벽돌의 깨짐이 6호분이 가장 심하다는 사실과 무관하지 않은 것으로 판단된다. 봉분내부의 토양층구조에 대한 지오레이다 영상단면을 분석한 결과 무령왕릉 연도상부의 누수지방지층이 심하게 균열되어 있음을 발견하였다. 이 곳은 고분내부로 직접누수가 발생하는 곳이다. 직접누수와 지하수 형태로 유입된 침투수는 고분군 주위의 지반의 함수비를 증가시켜 지반의 지지력을 약화시키고 또한 고분내로 서서히 유입되어 고분내부의 습도를 100%로 유지시키는 주된 원인이다. 이러한 높은 습도는 고분내의 남조류의 번식을 가져왔으며 남조류의 번식은 현재 6호분이 가장 심각하고 7호분이 우려되는 수준이며 5호분은 문제가 없는 것으로 판단된다. 이와 같이 고분군의 발굴후 인위적인 환경변화와 지속적인 강우침투 및 배수 불량의 영향은 고분군의 안정성에 상당한 위험을 초래하였으며, 현 상태는 각 고분에 대한 보강이 불가피한 것으로 판단된다. 고분 벽돌의 깨짐, 고분 벽체의 거동, 조류의 서식등을 포함하여 송산리 고분군에서 발생되고 있는 보존상의 제반 문제점들을 일차적으로 누수 및 침투수에 의한 결과이다. 그러므로 무엇보다도 고분군 내부 및 고분 주변으로의 강우 및 지하수 침투를 막는 차수 대책이 시급한 것으로 판단된다. 또한 이미 발생한 변위가 더 이상 진행되지 않도록 하중을 경감하고 토압의 균형을 이루는 보강대책이 시급한 실정이다. 고분군

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.1-7
• /
• 2020

Deep neural networks(DNN), which are used as approximation functions in reinforcement learning (RN), theoretically can be attributed to realistic results. In empirical benchmark works, time difference learning (TD) shows better results than Monte-Carlo learning (MC). However, among some previous works show that MC is better than TD when the reward is very rare or delayed. Also, another recent research shows when the information observed by the agent from the environment is partial on complex control works, it indicates that the MC prediction is superior to the TD-based methods. Most of these environments can be regarded as 5-step Q-learning or 20-step Q-learning, where the experiment continues without long roll-outs for alleviating reduce performance degradation. In other words, for networks with a noise, a representative network that is regardless of the controlled roll-outs, it is better to learn MC, which is robust to noisy rewards than TD, or almost identical to MC. These studies provide a break with that TD is better than MC. These recent research results show that the way combining MC and TD is better than the theoretical one. Therefore, in this study, based on the results shown in previous studies, we attempt to exploit a random balance with a mixture of TD and MC in RL without any complicated formulas by rewards used in those studies do. Compared to the DQN using the MC and TD random mixture and the well-known DQN using only the TD-based learning, we demonstrate that a well-performed TD learning are also granted special favor of the mixture of TD and MC through an experiments in OpenAI Gym.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.21-41
• /
• 2024

This study explores the relationship between users' attachment styles and their interactions with ChatGPT (Chat Generative Pre-trained Transformer), an advanced language model developed by OpenAI. As artificial intelligence (AI) becomes increasingly integrated into everyday life, it is essential to understand how individuals with different attachment styles engage with AI chatbots in order to build a better user experience that meets specific user needs and interacts with users in the most ideal way. Grounded in attachment theory from psychology, we are exploring the influence of attachment style on users' interaction with ChatGPT, bridging a significant gap in understanding human-AI interaction. Contrary to expectations, attachment styles did not have a significant impact on ChatGPT usage or reasons for engagement. Regardless of their attachment styles, hesitated to fully trust ChatGPT with critical information, emphasizing the need to address trust issues in AI systems. Additionally, this study uncovers complex patterns of attachment styles, demonstrating their influence on interaction patterns between users and ChatGPT. By focusing on the distinctive dynamics between users and ChatGPT, our aim is to uncover how attachment styles influence these interactions, guiding the development of AI chatbots for personalized user experiences. The introduction of the Perceived Partner Responsiveness Scale serves as a valuable tool to evaluate users' perceptions of ChatGPT's role, shedding light on the anthropomorphism of AI. This study contributes to the wider discussion on human-AI relationships, emphasizing the significance of incorporating emotional intelligence into AI systems for a user-centered future.