• 한국정보시스템학회:학술대회논문집
• /
• 한국정보시스템학회 1996년도 추계학술발표회 발표논문집
• /
• pp.217-227
• /
• 1996

The new field of learning control develops controllers that learn to improve their performance at executing a given task, based on experience performin this specific task. In a previous work［6］, the authors presented a theory of indirect learning control based on use of indirect adaptive control concepts employing simultaneous identification ad control. This paper develops improved indirect learning control algorithms, and studies the use of such controllers in decentralized systems. The original motivation of the learning control field was learning in robots doing repetitive tasks such as on an assembly line. This paper starts with decentralized discrete time systems, and progresses to the robot application, modeling the robot as a time varying linear system in the neighborhood of the nominal trajectory, and using the usual robot controllers that are decentralized, treating each link as if it is independent of any coupling with other links. The basic result of the paper is to show that stability of the indirect learning controllers for all subsystems when the coupling between subsystems is turned off, assures convergence to zero tracking error of the decentralized indirect learning control of the coupled system, provided that the sample time in the digital learning controller is sufficiently short.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 1996년도 추계 학술 발표회 발표논문집
• /
• pp.217-227
• /
• 1996

The new filed of learning control develops controllers that learn to improve their performance at executing a given task , based on experience performing this specific task. In a previous work[6], authors presented a theory of indirect learning control based on use of indirect adaptive control concepts employing simultaneous identification and control. This paper develops improved indirect learning control algorithms, and studies the use of such controller indecentralized systems. The original motivation of the learning control field was learning in robots doing repetitive tasks such as on an asssembly line. This paper starts with decentralized discrete time systems. and progresses to the robot application, modeling the robot as a time varying linear system in the neighborhood of the nominal trajectory, and using the usual robot controllers that are decentralized, treating each link as if it is independent of any coupling with other links. The resultof the paper is to show that stability of the indirect learning controllers for all subsystems when the coupling between subsystems is turned off, assures convergence to zero tracking error of the decentralized indirect learning control of the coupled system, provided that the sample tie in the digital learning controller is sufficiently short.

• 대한수학교육학회지:수학교육학연구
• /
• 제16권1호
• /
• pp.59-78
• /
• 2006

본 연구에서는 먼저, 미적분에서 수학과 물리를 연결한 학습-지도의 필요성을 논의하고, 이를 위한 교수-학습 자료를 개발하여 제시한다. 그 후, 교수-학습 자료 중 하나를 활용하여 질적 사례연구를 하여 등가속도 운동을 탐구하는 활동에서 평균속도와 순간속도 개념이 발달되는 과정을 분석하였다. 연구대상자들은 등가속도 운동을 탐구하는 물리적 실험 상황에서 평균속도, 순간속도, 가속도 개념을 배웠다. 이 과정에서 학생들은 순간속도가 시간과 이동거리의 이차함수 그래프 위의 한 점에서 접선의 기울기를 의미한다는 점과 시간과 속도의 관계그래프 아래의 넓이 변화율이 이동거리의 변화율을 의미한다는 점을 이해할 수 있었다.

• 공학교육연구
• /
• 제17권4호
• /
• pp.21-24
• /
• 2014

The purpose of this study is to develop the engineering students leadership program and evaluate the pilot test. To this end, literature reviews covering various leadership programs were studied and a needs analysis survey was conducted. The needs analysis survey found that student subjects believe leadership to be an important quality, but that the current availability of leadership training programs is lacking. Furthermore, results of the study are as follows, with respective results listed in descending order. The majority of students selected on-line learning as their preferred training method, followed by blended learning and in-person learning. Students also indicated their preferred instructional method to be through on-line courses. Based on these results, a preliminary pilot program was experimentally launched for only 1 class's use. This process of the development for the Engineering Leadership Program consists of 4 stages. The first stage is a needs analysis survey, followed by the design of the program based on results from the needs analysis survey. Afterwards comes the development stage, followed by the implementation stage, comprised of two parts; the pilot test and the distribution. The final stage is the overall evaluation step. We are currently in the first step of the third stage (the pilot test) and only the overall evaluation stage remains. After the distribution, a follow-up study will be conducted to analyze the effectiveness of the implemented program.

• 만화애니메이션 연구
• /
• 통권40호
• /
• pp.443-476
• /
• 2015

미술 디자인계열 학과를 개설한 대학의 이러닝 강의는 실습중심의 전공 교과목조차 대부분 이론중심 강의로 운영되고 있다. 심지어 완전 사이버교육을 제공하는 사이버대학교들 조차 실습과목에 대한 사이버학습 운영에 많은 어려움과 한계점을 토로하면서 이론위주로 운영하고 있는 상황이다. 많은 사이버대학교들이 이러한 실습교육의 한계를 극복하기 위해 특강형식으로 일정기간 오프라인에서의 실습교육을 진행하고 있어 결과적으로 학습에 있어서 시간적 공간적 제약을 갖게 되는 학생들의 중도탈락 비율이 점차 증가되고 있다. 본 연구는 대학의 이러닝 환경에서 실습이 필요한 과목의 효율적인 이러닝 실습환경을 제공하는 것에 목표를 두고 증강현실 기반의 실습교육이 기존 강의실 기반의 실습교육에 비해 어느 정도의 학업성취도를 이루어 내는지 알아보는 실험을 수행하였다. 연구대상은 2년제 일반대학교 디자인학부 1학년 84명을 선정하였으며, 3개 분반으로 나뉘어진 전공실습 수업 중 1개 분반에서 증강현실 기반 이러닝 수업을, 2개 분반에서는 강의실기반 실습수업을 각 7주간 처치하였다. 본 연구를 통하여 얻은 결과는 첫째, 이러닝 환경에서 증강현실 기반의 실습수업은 강의실 기반 실습수업보다 학업성취도 면에서 더 효과적이었다. 둘째, 학습 흥미도에 있어서는 증강현실기반의 실습이 수업자체에 대한 흥미를 유발하는 것으로 나타냈다. 셋째, 학습몰입에 있어서 증강현실기반의 실습수업 집단이 더 높은 수준의 몰입을 보였다. 본 연구가 실제 대학교육의 정규과정에서 수행되었다는 점을 고려해 볼 때, 이러한 연구결과는 증강현실기반의 전공 실습교육이 기존의 이론중심 이러닝 강의나 이러닝 환경이지만 별도로 강의실에서 실습을 진행했던 대학들의 수업방식을 보완할 수 있는 대안적 수업방법임을 시사한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.782-784
• /
• 1999

This paper deals with speed control of DC-servo motor using a Back-Propagation(BP) Learning Algorism and a PID controller Conventionally in the industrial control, PID controller has been used. But the PID controller produced suitable parameter of each system and also variable of PID controller should be changed enviroment, disturbance, load. So this paper revealed for experimental, a neural network and a PID controller combined system using developed speed characters of a Variable Load DC-servo motor. The parameters of the plant are determined by neural network perform on on-line system after training the neural network on off-line system.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.223-228
• /
• 2009

We propose an on-line machine learning approach for object recognition, where new images are continuously added and the recognition decision is made without delay. Random forest (RF) classifier has been extensively used as a generative model for classification and regression applications. We extend this technique for the task of building incremental component-based detector. First we employ object descriptor model based on bag of covariance matrices, to represent an object region then run our on-line RF learner to select object descriptors and to learn an object classifier. Experiments of the object recognition are provided to verify the effectiveness of the proposed approach. Results demonstrate that the propose model yields in object recognition performance comparable to the benchmark standard RF, AdaBoost, and SVM classifiers.

• 한국산업융합학회 논문집
• /
• 제25권4_1호
• /
• pp.521-531
• /
• 2022

This study proposed a new approach to intelligent control of a mobile robot system by back properpagation based on multi-layer neural network. A experiment result is given in which some artificial assumptions about the linear and the angluar velocities of mobile robots from recent literature are dropped. In this study, we proposed a new thinique to impliment the real time conrol of he position and velocity of mobile robots. With the proposed control techinique, mobile robots can now globally follow any path such as a straight line, a circle and the path approaching th toe origin using proposed controller. Computer simulations are presented, which confirm the effectiveness of the proposed control algorithm. Moreover, practical experimental results concerning the real time control are reported with several real line constraints for mobile robots with two wheel driving.

• Journal of Welding and Joining
• /
• 제25권6호
• /
• pp.64-70
• /
• 2007

Recently, several models to control weld quality, productivity and weld properties in arc welding process have been developed and applied. Also, the applied model to make effective use of the robotic GMA(Gas Metal Arc) welding process should be given a high degree of confidence in predicting the bead dimensions to accomplish the desired mechanical properties of the weldment. In this study, a development of the on-line learning neural network models that investigate interrelationships between welding parameters and bead width as well as apply for the on-line quality control system for the robotic GMA welding process has been carried out. The developed models showed an excellent predicted results comparing with the predicted ability using off-line learning neural network. Also, the system will extend to other welding process and the rule-based expert system which can be incorporated with integration of an optimized system for the robotic welding system.

• 한국학교수학회논문집
• /
• 제25권1호
• /
• pp.79-104
• /
• 2022

학생들이 수학 문제를 어느 정도 해결하는지 조사하여 학생들의 학습에 도움을 주는 일은 매우 중요하다. 이에 이 연구에서는 중학교 함수에 대한 개념 간의 연결성이 문제 풀이 결과에 어떠한 영향을 미치는지 분석하기 위한 4가지 방법(문제 유형별 정·오 분석, 도식화 분석, 영역 그래프 분석, 꺾은선 그래프 분석)을 구성하였으며, 학생들의 학습 상황을 시각적으로 표현하여 직관적 파악이 가능하게 하였다. 이러한 분석 방법은 학생들의 평가 결과를 파악하기 쉽고, 학생의 학습 상황을 직관적으로 파악하여 학습에 도움을 줄 수 있으며, 학생 스스로 자신의 문제점을 모니터링하여 자기주도 학습 계획을 세우는 데 도움을 줄 수 있으므로 수학 교수 학습에서 활용 가치가 있을 것이다.