• 제목/요약/키워드: Repeated Learning

검색결과 274건 처리시간 0.023초

Model predictive control combined with iterative learning control for nonlinear batch processes

  • Lee, Kwang-Soon;Kim, Won-Cheol;Lee, Jay H.
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
    • /
    • pp.299-302
    • /
    • 1996
  • A control algorithm is proposed for nonlinear multi-input multi-output(MIMO) batch processes by combining quadratic iterative learning control(Q-ILC) with model predictive control(MPC). Both controls are designed based on output feedback and Kalman filter is incorporated for state estimation. Novelty of the proposed algorithm lies in the facts that, unlike feedback-only control, unknown sustained disturbances which are repeated over batches can be completely rejected and asymptotically perfect tracking is possible for zero random disturbance case even with uncertain process model.

  • PDF

프랙탈 생산시스템에서의 강화학습을 통한 골 보정 방법 (Goal Regulation Mechanism through Reinforcement Learning in a Fractal Manufacturing System (FrMS))

  • 신문수;정무영
    • 한국경영과학회:학술대회논문집
    • /
    • 대한산업공학회/한국경영과학회 2006년도 춘계공동학술대회 논문집
    • /
    • pp.1235-1239
    • /
    • 2006
  • Fractal manufacturing system (FrMS) distinguishes itself from other manufacturing systems by the fact that there is a fractal repeated at every scale. A fractal is a volatile organization which consists of goal-oriented agents referred to as AIR-units (autonomous and intelligent resource units). AIR-units unrestrictedly reconfigure fractals in accordance with their own goals. Their goals can be dynamically changed along with the environmental status. Since goals of AIR-units are represented as fuzzy models, an AIR-unit itself is a fuzzy logic controller. This paper presents a goal regulation mechanism in the FrMS. In particular, a reinforcement learning method is adopted as a regulating mechanism of the fuzzy goal model, which uses only weak reinforcement signal. Goal regulation is achieved by building a feedforward neural network to estimate compatibility level of current goals, which can then adaptively improve compatibility by using the gradient descent method. Goal-oriented features of AIR-units are also presented.

  • PDF

물리치료 전공대학생들의 진로선호도와 학습동기에 관한 연구 (A study on Learning Motivation and Career Preference After Graduation of University Students Majoring in Physical Therapy)

  • 강준구;복원주;서유리;이도영;한동국;손경현;이경현
    • 대한물리치료과학회지
    • /
    • 제22권2호
    • /
    • pp.19-27
    • /
    • 2015
  • Purpose : This study is to investigate on career preference after graduation and learning motivation of students majoring in physical therapy. Methods : This survey implement with 400 students majoring in physical therapy from 3 college and university in korea, jeonnam 394 of 400 attended this survey. The measured date were analysed by using repeated anova, frequency analysis, $x^2$-test, t-test. Results : The results of this study were as follows: Career preference showed significant difference between male and female in department of orthopedic physical therapy and showed significant difference all by workplace(general hospital, special hospital). Career preference didn't show significant difference by schol system(college, university) and showed significant difference by work place. Learning motivation(inner motivation) showed significant difference in male by gender. Learning motivation didn't show significant difference by school system.

  • PDF

Why Learners Found Transfer Pricing Difficult? Implications for Directors

  • Abeysekera, Indra;Jebeile, Sam
    • The Journal of Asian Finance, Economics and Business
    • /
    • 제6권1호
    • /
    • pp.9-19
    • /
    • 2019
  • A recent survey of Australian directors conducted by the Financial Reporting Council found that directors require a detailed understanding of technical accounting issues. With the aim of understanding learner difficulties in learning and applying higher learning material relevant to directors, this study explores the transfer pricing topic taught as a case presentation in an undergraduate accounting program at an Australian university. Before intervention with improvements, this study invited 25 students to take part in the study after they had learned the topic and been given one week to understand it. By adopting a transfer pricing problem presented in their essential reading and interviewing those students to gain further insights, the study found that learners experienced conceptual difficulties at various stages in attempting to learn. Intervention to ease learning difficulties was addressed through instructor training. The intervention improvements included using guided workbooks to develop a better understanding of concepts among learners, and representing the problem at hand with diagrams. After intervention with improvements, this study repeated the same procedures with 25 students who had not taken part in the previous study and found that interventions increased the learning. Results have implications for most directors, who are novices to the detailed technical accounting issues of transfer pricing.

강화학습과 감정모델 기반의 지능적인 가상 캐릭터의 구현 (Implementation of Intelligent Virtual Character Based on Reinforcement Learning and Emotion Model)

  • 우종하;박정은;오경환
    • 한국지능시스템학회논문지
    • /
    • 제16권3호
    • /
    • pp.259-265
    • /
    • 2006
  • 학습과 감정은 지능형 시스템을 구현하는데 있어 가장 중요한 요소이다. 본 논문에서는 강화학습을 이용하여 사용자와 상호작용을 하면서 학습을 수행하고 내부적인 감정모델을 가지고 있는 지능적인 가상 캐릭터를 구현하였다. 가상 캐릭터는 여러 가지 사물들로 이루어진 3D의 가상 환경 내에서 내부상태에 의해 자율적으로 동작하며, 또한 사용자는 가상 캐릭터에게 반복적인 명령을 통해 원하는 행동을 학습시킬 수 있다. 이러한 명령은 인공신경망을 사용하여 마우스의 제스처를 인식하여 수행할 수 있고 감정의 표현을 위해 Emotion-Mood-Personality 모델을 새로 제안하였다. 그리고 실험을 통해 사용자와 상호작용을 통한 감정의 변화를 살펴보았고 가상 캐릭터의 훈련에 따른 학습이 올바르게 수행되는 것을 확인하였다.

알레르기비염 환자를 위한 플립러닝을 적용한 건강 교육프로그램 개발 및 효과 (Development and Effects of Health Education Program using Flipped Learning for Allergic Rhinitis Patients)

  • 이영실;은영
    • 한국간호교육학회지
    • /
    • 제25권2호
    • /
    • pp.173-185
    • /
    • 2019
  • Purpose: This study was conducted to develop and test effects of flipped learning on a health education program for allergic rhinitis patients. Methods: The study was a nonequivalent control group pretest-posttest design, with 38 participants (experimental group: 19, control group: 19). The education program for allergic rhinitis patients with flipped learning developed for this study was conducted in pre-class, in-class, and post-class stages for a total of 12 weeks. For the in-class stage, a TREAT model suitable for patient education program was developed. Data were analyzed with an independent t-test and repeated measures ANOVA. Results: The experimental group showed significant improvement in knowledge (F=15.029, p<.001), self-efficacy (F=6.814, p<.001) and self-care behavior (F=41.761, p<.001). In addition, subjective symptoms (F=61.453, p<.001) and quality of life (F=52.413, p<.001) improved. Conclusion: The results of this study show that flipped learning in an education program is an effective method for those in their twenties persistent moderate-severe allergic rhinitis. Therefore, the education program for allergic rhinitis developed by this study is actively recommended for nurses or health managers at universities to educate subjects in their twenties with allergic rhinitis.

The Effects of Astragalus Membranaceus on Repeated Restraint Stress-induced Biochemical and Behavioral Responses

  • Park, Hyun-Jung;Kim, Hyun-Young;Yoon, Kun-Ho;Kim, Kyung-Soo;Shim, In-Sop
    • The Korean Journal of Physiology and Pharmacology
    • /
    • 제13권4호
    • /
    • pp.315-319
    • /
    • 2009
  • Astragalus Membranaceus (AM) is a useful Korean herb that has been clinically prescribed for stress-related illness. The objective of the present study was to examine the anti-stress effects of AM on repeated stress-induced alterations of anxiety, learning and memory in rats. Restraint stress was administered for 14 days (2h/day) and AM (400mg/kg) given by oral administration, in the AM group, for the same period. Starting on the eighth day, the rats were tested for spatial memory on the Morris water maze test (MW) and for anxiety on the elevated plus maze (EPM). Changes of expression on immunohistochemistry were studied for cholineacetyl transferase (ChAT) and tyrosine hydroxylase (TH) in the brain. The results showed that the rats treated with AM had significantly reduced stress-induced deficits on learning and memory on the spatial memory tasks. In addition, the ChAT immunoreactivities were increased. In the EPM, treatment with AM increased the time spent in the open arms (p<0.001) compared to the control group. In addition, AM treatment also normalized increases of TH expression in the LC (p<0.001). In conclusion, administration of AM improved spatial learning and memory and reduced stress-induced anxiety. Thus, the present results suggest that AM is able to recover behavioral and neurochemical impairments induced by stress.

Effects of Glycyrrhizae Radix on Repeated Restraint Stress-induced Neurochemical and Behavioral Responses

  • Park, Hyun-Jung;Shim, Hyun-Soo;Kim, Hyun-Young;Kim, Kyung-Soo;Lee, Hye-Jung;Hahm, Dae-Hyun;Shim, In-Sop
    • The Korean Journal of Physiology and Pharmacology
    • /
    • 제14권6호
    • /
    • pp.371-376
    • /
    • 2010
  • Glycyrrhizae radix (GR) is an herbal medicine that is commonly used in the East Asia for treating a variety of diseases, including stomach disorders. The objective of the present study was to examine the anti-stress effects of GR on repeated stress-induced alterations of anxiety, learning and memory in rats. Restraint stress was administered for 14 days (2 h/day) to the rats in the Control and GR groups (400 mg/kg/day, PO). Starting on the eighth day, the rats were tested for spatial memory on the Morris water maze test (MW) and for anxiety on the elevated plus maze (EPM). We studied the changes of the expressions of cholineacetyl transferase (ChAT) and tyrosine hydroxylase (TH) in the locus coerleus (LC) using immunohistochemistry. The results showed that the rats treated with GR had significantly reduced stress-induced deficits on their learning and memory on the spatial memory tasks. In addition, the ChAT immunoreactivities were increased. Gor the EPM, treatment with GR increased the time spent in the open arms (p<0.001) as compared to that of the control group. Moreover, GR treatment also normalized the increases of the TH expression in the LC (p<0.001). In conclusion, administration of GR improved spatial learning and memory and reduced stress-induced anxiety. Thus, the present results suggest that GR has the potential to attenuate the behavioral and neurochemical impairments caused by stress.

차량 검출용 CNN 분류기의 실시간 처리를 위한 하드웨어 설계 (A Real-Time Hardware Design of CNN for Vehicle Detection)

  • 방지원;정용진
    • 전기전자학회논문지
    • /
    • 제20권4호
    • /
    • pp.351-360
    • /
    • 2016
  • 최근 딥 러닝을 중심으로 빠르게 발전하고 있는 기계학습 분류 알고리즘은 기존의 방법들보다 뛰어난 성능으로 인하여 주목받고 있다. 딥 러닝 중에서도 Convolutional Neural Network(CNN)는 영상처리에 뛰어나 첨단 운전자 보조 시스템(Advanced Driver Assistance System : ADAS)에서 많이 사용되고 있는 추세이다. 하지만 차량용 임베디드 환경에서 CNN을 소프트웨어로 동작시켰을 때는 각 Layer마다 연산이 반복되는 알고리즘의 특성으로 인해 수행시간이 길어져 실시간 처리가 어렵다. 본 논문에서는 임베디드 환경에서 CNN의 실시간 처리를 위하여 Convolution 연산 및 기타 연산들을 병렬로 처리하여 CNN의 속도를 향상시키는 하드웨어 구조를 제안한다. 제안하는 하드웨어의 성능을 검증하기 위하여 Xilinx ZC706 FPGA 보드를 이용하였다. 입력 영상은 $36{\times}36$ 크기이며, 동작주파수 100MHz에서 하드웨어 수행시간은 약 2.812ms로 실시간 처리가 가능함을 확인했다.

예비학습자의 간호영어 팀 기반 학습방법의 학습경험과 효과에 관한 연구 (Team Based Learning Experience and Effect on Study of Preliminary Learners on Medical Terminology)

  • 유수옥
    • 한국콘텐츠학회논문지
    • /
    • 제17권7호
    • /
    • pp.101-112
    • /
    • 2017
  • 본 연구의 목적은 학습자 중심 팀 기반 학습방법(Team Based Learning 이하tbl)이 예비간호학습자의 간호영어교과에서 경험과 효과를 확인 하고자 한다. 예비간호학습자 12명 대상으로 학습 결과 기록지, 학습관찰, 학습만족도, 학습자가 보고서, 동료평가서를 내용 분석하여 학습경험의 의미를 기술하였고 개인별, 팀별 점수는 빈도분석, 대응표본 T 검정을 통해 분석하였다. 연구결과는 1차, 2차 모두 개인별 점수보다 팀별 점수가 높았다. 협동이 잘되는 팀별 순위로 문제를 해결하였고 팀별 점수도 높았다. tbl학습 경험으로는 동료와 친밀감을 형성하며, 학습동기가 되고, 자율학습을 형성하며 학습이 용이해지고, 반복학습을 통해 어렵게 느꼈던 의학용어가 쉽게 암기되었다. 또한 팀끼리 시험을 봄으로 긴장감과 승부욕이 생기게 되어 성적향상에 도움이 된다고 하였고, 즐거운 학습시간으로 기억되었다고 하였다. 본 연구결과 예비학습자들에게 어렵게 접하는 간호영어 과목을 tbl을 통하여 학습동기를 유발하고 자율 학습을 유도하고 성적향상 및 동료와 친밀감이 형성됨을 알 수 있었다.