In the manufacturing industry, dispatching systems play a crucial role in enhancing production efficiency and optimizing production volume. However, in dynamic production environments, conventional static dispatching methods struggle to adapt to various environmental conditions and constraints, leading to problems such as reduced production volume, delays, and resource wastage. Therefore, there is a need for dynamic dispatching methods that can quickly adapt to changes in the environment. In this study, we aim to develop an agent-based model that considers dynamic situations through interaction between agents. Additionally, we intend to utilize the Q-learning algorithm, which possesses the characteristics of temporal difference (TD) learning, to automatically update and adapt to dynamic situations. This means that Q-learning can effectively consider dynamic environments by sensitively responding to changes in the state space and selecting optimal dispatching rules accordingly. The state space includes information such as inventory and work-in-process levels, order fulfilment status, and machine status, which are used to select the optimal dispatching rules. Furthermore, we aim to minimize total tardiness and the number of setup changes using reinforcement learning. Finally, we will develop a dynamic dispatching system using Q-learning and compare its performance with conventional static dispatching methods.

A mid-story isolation system was proposed for seismic response reduction of high-rise buildings and presented good control performance. Control performance of a mid-story isolation system was enhanced by introducing semi-active control devices into isolation systems. Seismic response reduction capacity of a semi-active mid-story isolation system mainly depends on effect of control algorithm. AI(Artificial Intelligence)-based control algorithm was developed for control of a semi-active mid-story isolation system in this study. For this research, an practical structure of Shiodome Sumitomo building in Japan which has a mid-story isolation system was used as an example structure. An MR (magnetorheological) damper was used to make a semi-active mid-story isolation system in example model. In numerical simulation, seismic response prediction model was generated by one of supervised learning model, i.e. an RNN (Recurrent Neural Network). Deep Q-network (DQN) out of reinforcement learning algorithms was employed to develop control algorithm The numerical simulation results presented that the DQN algorithm can effectively control a semi-active mid-story isolation system resulting in successful reduction of seismic responses.

구조물에 장기적으로 발생하는 노후화를 정량적으로 파악하기 위해 상시진동 데이터를 활용한 일반화된 모니터링 시스템에 관한 연구가 세계적으로 활발히 수행중이다. 본 연구에서는 구조물에서 장기적으로 취득되는 동특성을 앙상블 학습에 활용하여 구조물의 이상을 감지하기 위한 보급형 엣지 컴퓨팅 시스템을 구축하였다. 시스템의 하드웨어는 라즈베리파이와 보급형 가속도계, 기울기센서, GPS RTK 모듈, 로라 모듈로 구성됐다. 실험실 규모의 구조물 모형 진동실험을 통해 동특성을 활용한 앙상블 학습의 구조물 이상 감지를 검증하였으며, 실험을 기반으로 한 실시간 동특성 추출 분산처리 알고리즘을 라즈베리파이에 탑재하였다. 구축된 시스템을 하우징하고 포항시 행정복지센터에 설치하여 데이터를 취득함으로써 개발된 시스템의 현장 적용성을 검증하였다.

Contemporary University students are considered the Z generation who were born after 1995. They are more tech savvy than millennials. To target the generation, traditional class management platforms have evolved to smart LMS that is more customized and accessible for smart devices. Global level information search and collaboration can also be implemented using such smart LMS. However, switching from one LMS to another LMS requires great effort from teachers and support from staffs. This study measured the learners’ perception of the system when they were exposed to a new smart-LMS. Blackboard Learn Ultra was used for 15 weeks and at the end of the semester, a questionnaire was administered to the students of these classes. Results indicated that experience with previous LMS discouraged students from adopting Blackboard Learn. Result of TAM modeling indicated that perceived usefulness, compared to perceived ease of use and attitude, was an effective aspect to bring positive acceptance of the system. A qualitative approach and network analysis were also conducted based on students’ responses. Both positive and negative responses were detected. Inconvenience due to mechanical aspects was mentioned. Dissatisfaction compared to previous local LMS use was also mentioned. Mobile application and communication effectiveness were positive aspects. Revised course development and promoting how useful the system may help enhance the acceptance of the new system.

이 연구의 목적은 초등학교 6학년 학생들의 달의 위상 변화에 대한 학습 발달과정을 천문학적 시스템 사고를 기반으로 탐색하는 것이다. 선행 연구 결과 분석을 통해 서답형 문항을 개발하고 가설적 학습 발달과정을 설정하였으며, 이를 토대로 문항 분석틀을 개발하였다. 달의 위상 변화에 대한 수업을 실시하기 전과 후에 서답형 문항을 이용한 검 사 자료를 수집하였으며, 평가 결과를 이용하여 가설적 학습 발달과정의 타당성을 검증하였다. 이를 통하여, 상향식으로 지구-달계에 대한 학습 발달과정을 탐색할 수 있었다. 연구 결과, 초등학생들은 지구 기반 관점과 우주 기반 관점 사 이의 사고 전환에 어려움을 겪는 것으로 보인다. 또한, 달의 위상 변화에 대한 초등학생들의 학습 발달과정을 근거로 할 때, 달의 위상 변화의 개념은 교육과정 상에서 초등학교의 학습 내용으로 다소 높은 수준인 것으로 판단된다.

This paper provides based on the research of previous researchers of the learning organization, this study selected the factors that would influence the introduction effect of the learning organization operation in the construction companies. The result of this study is that the learning organization operating system has the effect of job performance, job satisfaction, organizational commitment and ultimate The results of this study are as follows.

본 연구는 CEO의 혁신성, 학습적 문화, 정보 시스템 활용 수준이 기업의 혁신성과에 미치는 영향 그리고 이러 한 혁신성과가 기업의 경제적 성과에 어떠한 영향을 미치는지 살펴보는데 주요 목적이 있다. 김해시에서 활동하 고 있는 중소제조기업 122개를 대상으로 설문조사를 실시하여 구조방정식을 통해 분석한 결과, CEO의 혁신성과 학습 문화는 각각 기업의 혁신 성과에 긍정적인 영향을 미치며 그리고 기업의 혁신 성과는 기업의 경제적 성과에 긍정적인 영향을 미치는 것으로 나타났다. 이러한 결과를 통해 본 연구는 혁신은 대기업의 전유물이 아니며 대기업에게만 효과가 있는 것이 아니라 자원 이 부족하지만 CEO의 경영 스타일과 학습적 문화와 같이 거대한 자본을 들이지 않는 혁신활동으로도 기업의 혁 신을 이끌 수 있다는 것을 제안한다. 또한, 중소기업에게 있어 혁신이 기업 성과를 결정하는 요인으로 밝혀졌기 에 중소기업의 CEO는 실무적으로 이를 활용할 수 있을 것이다. 그리고 마지막으로, 본 연구에서는 기존 문헌과 달리 혁신성과를 경제적 성과와 연결하여 살펴보았다는데 큰 의의가 있다.

In this paper, we propose a logical control-based actor-critic algorithm as an efficient approach for the approximation of the capacitated fab scheduling problem. We apply the average reward temporal-difference learning method for estimating the relative

Recently, the role of artificial intelligence techniques in games is becoming important. Game artificial intelligence technology in the past, the graphics and sound technology were more important. However, Artificial intelligent technology in current games is necessary technology to provide variety pleasure to users, and role of user's partner or helper. Learning ability of artificial intelligence technologies is attention getting technology. In this paper, we apply the learning system to the game agent to implement it, and a nalysis its performance.

The benefits of information technology cannot be obtained unless potential users utilize it for their work. This led to a lot of research works on computer system acceptance. But most of the works address the early stage of system introduction, leaving th

This research is to develop an expert system utilizing virtual reality and 3D image technologies for minimizing damages from natural disaster, especially storm and flood, which could be used as a training kid for people including the old. It also develops an expert system for storm and flood on very limited region, 3D animation application technology using optical motion capture techniques for heavy storm and flood, and 3D-based rendering technology using virtual reality techniques. This data based expert system should work exactly like real experts by adapting all expert knowledge and experience, so that users, especially the old and vulnerable residents not familiar with computer systems, could easily use the system by several button selections. The animated character based program will also be developed for the old and vulnerable residents to learn and understand what to do quite easily.

지금까지의 NPC 게임캐릭터는 단순한 대전 동작과 길 찾기 알고리즘 정도의 인공지능 정도로 게임 내에서 주인공캐릭터와 대적하는 기능을 가지고 있다. 게임을 플레이 하면서 유저들이 좀 더 재미있고 긴장감 넘치는 게임을 할 수 있도록 인간과 같은 사고와 능력 그리고 감정을 가진 NPC 캐릭터를 위한 인공지능 엔진이 연구되고 있다. 이 논문에 서는 다중지각 능력과 스스로 자율학습이 가능한 게임캐릭터가 상대방의 동작을 모방하는 학습을 통해 주인공과 같은 유연한 동작을 하게 되고 상대 캐릭터의 동작에 따라 반응하는 감정을 토대로 다른 장소에서 다른 캐릭터를 만났을 때 이전에 학습한 동작이나 감정을 합성한 알고리즘을 바탕으로 반응하게 한다. 특히 이 논문에서는 계속적인 온라인 게임 환경에서 인공지능 캐릭터의 학습을 효율적으로 할 수 있으며 온라인 게임에서의 방대한 인공지능 캐릭터의 데이터를 줄이기 위한 방법으로 학습 공유시스템을 제안한다. 본 논문에서 제시한 방법을 이용하여 같은 구조를 가진 여러 에이전트들이 동시에 학습을 진행하고 또한 그렇게 습득한 지식을 공유할 수 있다면 더욱 신속하고 정확한 에이전트 학습이 이루어 질 수 있다.

In this paper, we present a wireless RFID glove in emotional learning method The Proposed wireless RFID glove consists of three parts RF wireless module, RFID reader, and RFID tags Objects tagged with a small passive RFID tag, can be sensed at short range

  This study aims to design and implement a learning evaluation system using .NET which is developed by Microsoft. .NET technology supports higher processing speed than ASP technology. The learning evaluation system is based on the web, consists of admini

Over the fast few years, web-based e-Learning have made remarkable progress. According to advance of e-Learning, the evaluation of e-Learning effectiveness and success model become more important. This study had a focus on the effect of system characteristic of e-Learning systems and self-efficacy on learning performance. Data has been collected from 192 person experienced in e-Learning. The questionnaire method was adopted to collect the data for this study. The research was conducted by using SPSS 12.0 and AMOS 4.0. The research results and suggestions of the study are as follow. First of all, system quality and information quality of e-Learning system had positive relationship with perceived usefulness. Second, information quality was related positively to user satisfaction. Third, perceived usefulness was positively connected with user satisfaction. Fourth, user satisfaction and self-efficacy had relation to learning performance.