• Title/Summary/Keyword: Model based reinforcement learning

Search Result 158, Processing Time 0.02 seconds

A Qualitative Research of Children's Mental Model on Media Environment and the Use (미디어 환경과 사용에 관한 아동의 심성모형 질적 연구)

  • Lee, Ran;Hyun, Eunja
    • The Journal of the Korea Contents Association
    • /
    • v.16 no.6
    • /
    • pp.601-613
    • /
    • 2016
  • The purpose of this study is to present the mental model of young adolescents' media environment and the use and to provide several educational suggestions drawing on the revealed model. For this, the data were collected through 4 activities such as interview, picture drawings, word association experiment, and sentence completion task with ten 4-5th graders in elementary schools; they were qualitatively analyzed by 2 researchers. First, the meaning components driven by sentence completion task, word association experiment were totally 6 components: media device, connection(alienation), competence(provision), entertainment, adverse effects, ambilaterality. Second, the components of media mental model driven by pictures were 4 components: functions/competence, entertainment, conflict with paper books/sharing, harmfulness/ambilaterality. Third, the components from interview consisted of conflict between paper books and electronic media, communication-centeredness, fear(addiction) and users' qualification. Based on those results, careful examination in cyber talk, necessity of addiction prevention, active development of learning media and their balanced utilization with books, and healthful media literacy education and reinforcement of critical thinking were suggested.

Strategy to coordinate actions through a plant parameter prediction model during startup operation of a nuclear power plant

  • Jae Min Kim;Junyong Bae;Seung Jun Lee
    • Nuclear Engineering and Technology
    • /
    • v.55 no.3
    • /
    • pp.839-849
    • /
    • 2023
  • The development of automation technology to reduce human error by minimizing human intervention is accelerating with artificial intelligence and big data processing technology, even in the nuclear field. Among nuclear power plant operation modes, the startup and shutdown operations are still performed manually and thus have the potential for human error. As part of the development of an autonomous operation system for startup operation, this paper proposes an action coordinating strategy to obtain the optimal actions. The lower level of the system consists of operating blocks that are created by analyzing the operation tasks to achieve local goals through soft actor-critic algorithms. However, when multiple agents try to perform conflicting actions, a method is needed to coordinate them, and for this, an action coordination strategy was developed in this work as the upper level of the system. Three quantification methods were compared and evaluated based on the future plant state predicted by plant parameter prediction models using long short-term memory networks. Results confirmed that the optimal action to satisfy the limiting conditions for operation can be selected by coordinating the action sets. It is expected that this methodology can be generalized through future research.

BERT-based Document Summarization model using Copying-Mechanism and Reinforcement Learning (복사 메커니즘과 강화 학습을 적용한 BERT 기반의 문서 요약 모델)

  • Hwang, Hyunsun;Lee, Changki;Go, Woo-Young;Yoon, Han-Jun
    • Annual Conference on Human and Language Technology
    • /
    • 2020.10a
    • /
    • pp.167-171
    • /
    • 2020
  • 문서 요약은 길이가 긴 원본 문서에서 의미를 유지한 채 짧은 문서나 문장을 얻어내는 작업을 의미한다. 딥러닝을 이용한 자연어처리 기술들이 연구됨에 따라 end-to-end 방식의 자연어 생성 모델인 sequence-to-sequence 모델을 문서 요약 생성에 적용하는 방법들이 연구되었다. 본 논문에서는 여러 자연어처리 분야에서 높은 성능을 보이고 있는 BERT 모델을 이용한 자연어 생성 모델에 복사 메커니즘과 강화 학습을 추가한 문서 요약 모델을 제안한다. 복사 메커니즘은 입력 문장의 단어들을 출력 문장에 복사하는 기술로 학습데이터에서 학습되기 힘든 고유 명사 등의 단어들에 대한 성능을 높이는 방법이다. 강화 학습은 정답 단어의 확률을 높이기 위해 학습하는 지도 학습 방법과는 달리 연속적인 단어 생성으로 얻어진 전체 문장의 보상 점수를 높이는 방향으로 학습하여 생성되는 단어 자체보다는 최종 생성된 문장이 더 중요한 자연어 생성 문제에 효과적일 수 있다. 실험결과 기존의 BERT 생성 모델 보다 복사 메커니즘과 강화 학습을 적용한 모델의 Rouge score가 더 높음을 확인 하였다.

  • PDF

Study on 3D AR of Education Robot for NURI Process (누리과정에 적용할 교육로봇의 가상환경 3D AR 연구)

  • Park, Young-Suk;Park, Dea-Woo
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2013.05a
    • /
    • pp.209-212
    • /
    • 2013
  • The Nuri process of emphasis by the Ministry of Education to promote is standardized curriculum at the national level for the education and care. It is to improve the quality of pre-school education and Ensure a fair starting line early in life and It emphasizes character education in all areas of the window. Nuri the process of development of a the insect robot for the Creativity education Increased the interesting and educational effects. Assembly and the effect on learning of educational content using a VR educational robot using the existing floor assembly using the online website to help assemble and learning raised. Order to take advantage of information technology in the information-based society requires the active interest and motivation in learning, creative learning toddlers learning robot are also needed. A three-dimensional model of the robot, and augmented by linking through the marker, the target marker and the camera relative to the coordinate system of augmented reality, seeking to convert the marker to be used in augmented reality marker patterns within a pre-defined patternto be able to make a decision on what of. The fusion of a smart education through training and reinforcement the educational assembly of the robot in the real world window that is represented by a virtual environment in this paper to present a new form of state-of-the-art smart training, you will want to lay the foundation of the nation through the early national talent nurturing talent.

  • PDF

Development of a Robot Programming Instructional Model based on Cognitive Apprenticeship for the Enhancement of Metacognition (메타인지 발달을 위한 인지적 도제 기반의 로봇 프로그래밍 교수.학습 모형 개발)

  • Yeon, Hyejin;Jo, Miheon
    • Journal of The Korean Association of Information Education
    • /
    • v.18 no.2
    • /
    • pp.225-234
    • /
    • 2014
  • Robot programming allows students to plan an algorithm in order to solve a task, implement the algorithm, easily confirm the results of the implementation with a robot, and correct errors. Thus, robot programming is a problem solving process based on reflective thinking, and is closely related to students' metacognition. On this point, this research is conducted to develop a robot programming instructional model for tile enhancement of students' metacognition. The instructional processes of robot programming are divided into 5 stages (i.e., 'exploration of learning tasks', 'a teacher's modeling', 'preparation of a plan for task performance along with the visualization of the plan', 'task performance', and 'self-evaluation and self-reinforcement'), and core strategies of metacognition (i.e., planning, monitering, regulating, and evaluating) are suggested for students' activities in each stage. Also, in order to support students' programming activities and the use of metacognition, instructional strategies based on cognitive apprenticeship (i.e. modeling, coaching and scaffolding) are suggested in relation to the instructional model. In addition, in order to support students' metacognitive activities. the model is designed to use self-questioning, and questions that students can use at each stage of the model are presented.

A Preliminary Study for Curriculum Building in Nursing (교육과정개발을 위한 학생측면의 기초연구 - 간호학과 학생의 자아개념과 교육자의 인식을 중심으로 -)

  • Jung Moon-Hee;Lim Nan-Young;Choi Sun-Ha;Do Keong-Jin
    • Journal of Korean Public Health Nursing
    • /
    • v.4 no.2
    • /
    • pp.35-57
    • /
    • 1990
  • This study was conducted to provide information useful in developing a nursing curriculum. The sample consisted of 158 nursing students in Hanyang University and 34 faculty members who has taught them in their college & the practical area. Data were collected by using a structured questionnaire, which consisted of general characteristics of the students & their self-concept, teacher's perception of student's professional roles. The results are summarized as follows; 1. General characteristics of the students When the students applied for the university, they decided what they would specialized in. Because the motive of application for their major was simply based on their high school records, they were admitted to their university without previous knowledge of their major. The reason why they wanted to tranfer to another course after the admission was the same as above. The level of satisfaction of their major was the highest in Freshman, but in other grades the higher the;, grades were, the more they satisfied with their major and they had a better prospects about their speciality. 2. Self-concept in profermance for their major Self-concept in horne aspects was more positive perception than in social aspects & self control aspects. It resulted from tile fact that all students were females and the nursing uniqueness was based on the spirit of humanity & service. The students who had graduated from the high school in rural area wanted to tranfer to another course and taken counsel their personal problems with their parents had higher self-concept in horne aspects. As their grades were higher, the self-concept in social aspects bacame higher. The students who were satisfied with their major and took counsel their personal problems with their parents had more positive self - concept in social aspects. Self-concept in self control aspects was lower than other aspects. The students who didn't take counsel their problems with their parents, were burdened with their educational expenses and their curriculum had more negative self-concept in self control aspects. Therefore the university should be concerned about student's welfare and provide detailed orientation about their curriculum. 3. Teacher's perception about learner's professional role The role model of democratic group leader, role models for learners facilitator in a students' reach for knowledge and teaching based on soundly researched theory showed more positive perception than other factors. Their mean values were over 4. 32. The professionalism of allnurshing area, reinforcement with reinforcement for learning, nursing as part of the meaningful context of the whole showed nagative perception. Their mean values were below 3. 00. Therefore the nurse as a teacher should try to promote the locus of nursing profession and participate in their research actively.

  • PDF

Smartphone-User Interactive based Self Developing Place-Time-Activity Coupled Prediction Method for Daily Routine Planning System (일상생활 계획을 위한 스마트폰-사용자 상호작용 기반 지속 발전 가능한 사용자 맞춤 위치-시간-행동 추론 방법)

  • Lee, Beom-Jin;Kim, Jiseob;Ryu, Je-Hwan;Heo, Min-Oh;Kim, Joo-Seuk;Zhang, Byoung-Tak
    • KIISE Transactions on Computing Practices
    • /
    • v.21 no.2
    • /
    • pp.154-159
    • /
    • 2015
  • Over the past few years, user needs in the smartphone application market have been shifted from diversity toward intelligence. Here, we propose a novel cognitive agent that plans the daily routines of users using the lifelog data collected by the smart phones of individuals. The proposed method first employs DPGMM (Dirichlet Process Gaussian Mixture Model) to automatically extract the users' POI (Point of Interest) from the lifelog data. After extraction, the POI and other meaningful features such as GPS, the user's activity label extracted from the log data is then used to learn the patterns of the user's daily routine by POMDP (Partially Observable Markov Decision Process). To determine the significant patterns within the user's time dependent patterns, collaboration was made with the SNS application Foursquare to record the locations visited by the user and the activities that the user had performed. The method was evaluated by predicting the daily routine of seven users with 3300 feedback data. Experimental results showed that daily routine scheduling can be established after seven days of lifelogged data and feedback data have been collected, demonstrating the potential of the new method of place-time-activity coupled daily routine planning systems in the intelligence application market.

Energy Management and Performance Evaluation of Fuel Cell Battery Based Electric Vehicle

  • Khadhraoui, Ahmed;SELMI, Tarek;Cherif, Adnene
    • International Journal of Computer Science & Network Security
    • /
    • v.22 no.3
    • /
    • pp.37-44
    • /
    • 2022
  • Plug-in Hybrid electric vehicles (PHEV) show great potential to reduce gas emission, improve fuel efficiency and offer more driving range flexibility. Moreover, PHEV help to preserve the eco-system, climate changes and reduce the high demand for fossil fuels. To address this; some basic components and energy resources have been used, such as batteries and proton exchange membrane (PEM) fuel cells (FCs). However, the FC remains unsatisfactory in terms of power density and response. In light of the above, an electric storage system (ESS) seems to be a promising solution to resolve this issue, especially when it comes to the transient phase. In addition to the FC, a storage system made-up of an ultra-battery UB is proposed within this paper. The association of the FC and the UB lead to the so-called Fuel Cell Battery Electric Vehicle (FCBEV). The energy consumption model of a FCBEV has been built considering the power losses of the fuel cell, electric motor, the state of charge (SOC) of the battery, and brakes. To do so, the implementing a reinforcement-learning energy management strategy (EMS) has been carried out and the fuel cell efficiency has been optimized while minimizing the hydrogen fuel consummation per 100km. Within this paper the adopted approach over numerous driving cycles of the FCBEV has shown promising results.