• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.686-689
• /
• 1999

발전소 운전원 훈련용 시뮬레이터는 중앙제어실(MCR:Main Control Room) 운전원의 운전결과가 실시간 운영체계하에 발전소 프로세스 모델 및 컴퓨터 시스템과 통합되어 실제 발전소와 같은 반응을 운전원에게 제공하여야 한다. 따라서 시뮬레이터에는 프로세스의 동특성 이외에도 제어시스템의 모델링 및 운전원과 인터페이스되는 제어기들이 실제적으로 구성되어야하며, 이들 제어기와 컴퓨터시스템간 다양한 입력간의 통신 및 동기(Synchronization)가 중요하다. 본 논문에서는 원자력 발전소 시뮬레이터에서 쓰이는 지능형 계기(Intelligent Type Instrument)로 분류된 기기를 살펴보고 시뮬레이션을 위해 개발 구현된 방법들을 기술하고자한다.

• Journal of The Korean Association of Information Education
• /
• v.5 no.2
• /
• pp.268-278
• /
• 2001

This study is design and implementation of diagnosis module using item response theory to assess level of student's knowledge in web-based instruction systems. Item response theory uses responses to items on a test or survey questionnaire to simultaneously locate both the items on the latent trait defined by the set of items while simultaneously scaling each item on the very same dimension. Existing method of measurement in web-based instruction system provided dichromatic learning after to be assess just with the total scores of exam. This measurement has an error that do not consider the level of student's knowledge. Moreover, this method can't perform an exact diagnosis of student knowledge and make student modeling to construct intelligent tutoring system. In this study, we present that design and implement a diagnosis module using item response theory to assess level of student's knowledge in web-based instruction systems

• The Journal of the Korea Contents Association
• /
• v.21 no.5
• /
• pp.70-83
• /
• 2021

The issue of predicting the relationship between humans and AI robots is a 'strong AI' problem. Many experts predict the tragic ending which is a strong AI with superior thinking ability than humans will conquer humans. Due to the expectations of AI robots are projected onto media, the 'morally good AI' that meets human expectations is an important issue. However, the demand for good AI and the realization of perfect technology is not limited to machines. Rather, it appears as a result of putting all responsibility on humans, driving humans into immoral beings and turning them into human and human problems, which is resulting in more alienation and discrimination. As such, the result of technology interacts with the human being used and its properties are determined and developed according to the reaction. This again affects humans. Therefore, AI technology that considers human emotions in consideration of interaction is also important. Therefore, this study will clarify the process that the demand for 'Good AI' in the relationship of AI to humans with Randall Collins' Interaction Ritual Chain. Emotional energy in Interaction Ritual Chain has explained the formation of human bonds. Also, the methodology is a type of thinking experiment and explained through Janet and surrounding characters in the TV show .

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.325-328
• /
• 2005

기존의 다사용자 온라인 게임에서 구현되어 있는 MOB(Mobile Character)들은 '대기' 와 '공격' 의 2 가지 상태를 가지며 사용자의 '공격' 이라는 이벤트에만 반응하도록 설계되어 있는 수동적인 에이전트들이다. 본 논문에서는 기존의 '대기' 와 '공격' 상태에 '회피' 상태를 추가하고 3 가지 각각의 행동 전이에 따른 행동 패턴을 행동 특성 곡선으로 표현하며 '공격' 과 '접근' 자극을 스트레스 모형에 적용하여 스트레스에 따른 MOB 에이전트의 행동 패턴 변화를 설명하고 주변의 다른 에이전트들과의 협동을 도모할 수 있는 지능적인 NPC 에이전트를 설계한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.2 s.308
• /
• pp.40-51
• /
• 2006

As computer games become more complex and consumers demand more sophisticated computer controlled NPCs, developers are required to place a greater emphasis on the artificial intelligence aspects for their games. The platform for game NPC Intelligence Development should support real-time, independence, flexibility, group behavior, and various A.I to NPC that are reactive, realistic and easy to develop. This paper presents an architecture to satisfy these criteria for the platform of game NPC intelligence development. The proposed platform shows the higher performance than existing platform through the load sharing, and it also has some advantages which are supporting the various AI techniques, efficient group behavior, and independence to develop NPC intelligence.

• 한국HCI학회:학술대회논문집
• /
• 2007.02b
• /
• pp.489-496
• /
• 2007

u-러닝(u-learning) 체제의 도입은, 다양한 형태의 원격교육을 지원하기 위한 교수-학습 시스템 및 모형을 요구하며, 이에 따라 유무선 인터넷을 이용한 u-러닝 시스템이 지속적으로 개발 적용되어 왔다. 하지만, 현재 운영되고 있는 대부분의 원격교육시스템은 교수자와 학습자간의 지속적인 쌍방향 상호작용 유지의 어려움, 시스템 구축을 위한 경제적 부담, 시스템 운영에 투입되는 교수자의 기술적 소양 부족 등의 문제점을 안고 있다. 이러한 문제점을 해결하기 위해서는 다음 항목에 대한 제고가 필요하다. 첫째, 효율적인 쌍방향 상호작용은 학습자 행동에 대한 지속적인 모니터링 및 피드백, 그리고 교수자의 상시 접속 상태 유지를 전제로 한다. 이는 사이버 교사(cyber tutor)를 이용하는 지능형 학습에 대한 논의로 이어진다. 둘째, 구현될 시스템은 경제성과 재사용성 측면이 고려되어야 하며, 이는 기존의 학교 현장의 인프라를 활용하는 u-러닝 개념의 학습 환경, 즉 이동성 네트워크 구조에 대한 설계가 요구된다. 셋째, 시스템의 직접적인 운영 주체인 일선 교사들의 기술적 소양을 고려할 때, 시스템 구축 및 사용상의 편리성, 학습 진행을 위한 보조적 지원 장치 등이 충분히 전제되어야 한다. 이에 본 연구에서는, 이동성과 내재성의 u-러닝 개념을 포함하고, 지능형 가상 교수자(cyber tutor)에 의한 블랜디드 학습(blended learning)을 도입하며, 사용자의 기술적, 경제적 부담의 제거가 가능한 지능형 u-러닝시스템을 개발하였다. 본 연구에 의해 개발된 시스템은 기존의 네트워크 인프라와 u-러닝의 개념을 통합하는 네트워크 구조, 원격학습을 지원하는 네트워크 화이트보드, 학습 과정의 저장과 해석을 지원하는 스크립트 인터프리터, 학습자 반응에 대한 피드백을 자동 제공할 수 있는 지능형 인터프리터로 구성되었다.

• Journal of The Korean Association of Information Education
• /
• v.23 no.6
• /
• pp.675-687
• /
• 2019

As interest in artificial intelligence increases, each university has been establishing a special graduate school with artificial intelligence major, and recently, the Korea government has established various support policies for artificial intelligence education. However, each university has a lot of difficulties because it has little experience in operating graduate education with the latest field of artificial intelligence and it is not easy to find experts. In this study, the response of graduate school students majoring in artificial intelligence was analyzed using IPA technique, and the direction of education of graduate school artificial intelligence major was searched. Among the 40 items surveyed by IPA, 12 items such as systematization of artificial intelligence curriculum, progress of class considering learning level, improvement of academic relations with guidance professors were extracted as items to be improved first. On the other hand, 8 items such as assistant capacity, and relationship with colleagues were overloaded, and twelve items such as instructor's lecture competency, appropriateness of educational contents, learner's artificial intelligence skills and knowledge, and attitude acquisition were to be maintained. In addition, eight items such as convergence education curriculum and diversity of education methods were all low in importance and performance. It is suggested that AI graduate school should be divided into two tracks(technical specialization, convergence expansion) by educational goal, and each track should be conducted by level-specific educational contents and methods suitable for student level. The curriculum should be elaborate and systematic to acquire AI knowledge, skills, and attitudes, and should have an individualized guidance system centered on excellent faculty members.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.61-71
• /
• 2021

In a situation where the online learning is expanding due to COVID-19, the current maker education has limitations in applying it to classes. This study is to design the class of online maker education using artificial intelligence tools in elementary school. Also, it is to identify the responses to it and to confirm whether it helps improve the learner's computational thinking and creative problem solving ability. The class was designed by the literature review and redesign of the curriculum. Using interveiw, the responses of instructor and learners were identified. Pre- and post-test using corresponding sample t-test was conducted. As a result, the class consisted of ten steps including empathizing, defining making problems, identifying the characteristics of material and tool, designing algorithms and coding using remixes, etc. For computing thinking and creative problem solving ability, statistically significant difference was found. This study has the significance that practical maker activities using educational artificial intelligence tools in the context of elementary education can be practically applied even in the online environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.682-687
• /
• 2005

Behavioral sequences of the medaka(Oryzias latipes) were investigated through an image system in response to medaka treated with the insecticide and medaka not treated with the insecticide, diazinon(0.1 mg/1). After much observation, behavioral patterns could be divided into 4 patterns: active smooth, active shaking, inactive smooth, and inactive shaking. These patterns were analyzed by 5 features: speed ratio, x and y axes projection, FFT to angle transition, fractal dimension, and center of mass. Each pattern was classified using decision tree. It provide a natural way to incorporate prior knowledge from human experts in fish behavior, The main focus of this study was to determine whether the decision tree could be useful in interpreting and classifying behavior patterns of the animal.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.121-127
• /
• 2023

The purpose of this pilot study is to examine the responses of middle school students to English learning after conducting English writing activities using DALL-E2, an image-generating artificial intelligence tool. To this end, an experimental class was conducted for 3 weeks for 15 middle school English learners, and the results are summarized as follows. First, as a result of a survey on English writing activities using DALL-E2, it was found that confidence, interest, and awareness of writing using artificial intelligence-based tools changed positively. In addition, it was confirmed that there was a statistically significant difference, which meant that learning using artificial intelligence had a positive effect on English writing and overall English learning. Second, as a result of analyzing the English writing activities using DALL-E2, core themes could be extracted into three (cognitive, affective, and psychodynamic characteristics), and the use and implementation of artificial intelligence-based DALL-E2 in English learning showed potential to increase learning interest, challenge, will, and desire in learning and ultimately contribute to enhancing productive skill.