• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.456-459
• /
• 1999

In this paper, we propose a method of unconstrained handwritten numeral recognition using image dithering and multiple modular MLPs. The set of sample numeral patterns is subdivided into clusters which are extended by their radius. On each extended cluster, we constructed MLPs network as the expert recognizer of corresponding cluster. The gating network is also trained by an MLPs to weigh the outputs of expert MLPs. In training and test phase of the recognizer, we utilize the multiple dithered numeral images and the combination of the outputs for corresponding dithered images. Experimental results show that our recognition method works very well.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.149.5-149
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent´s dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless ...

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.248-254
• /
• 2022

Educational innovations are first created, improved or applied educational, didactic, educative, and managerial systems and their components that significantly improve the results of educational activities. The development of pedagogical technology in the global educational space is conventionally divided into three stages. The role of innovative technologies in Higher School practice is substantiated. Factors of effectiveness of the educational process are highlighted. Technology is defined as a phenomenon and its importance is emphasized, it is indicated that it is a component of human history, a form of expression of intelligence focused on solving important problems of being, a synthesis of the mind and human abilities. The most frequently used technologies in practice are classified. Among the priority educational innovations in higher education institutions, the following are highlighted. Introduction of modular training and a rating system for knowledge control (credit-modular system) into the educational process; distance learning system; computerization of libraries using electronic catalog programs and the creation of a fund of electronic educational and methodological materials; electronic system for managing the activities of an educational institution and the educational process. In the educational process, various innovative pedagogical methods are successfully used, the basis of which is interactivity and maximum proximity to the real professional activity of the future specialist. There are simulation technologies (game and discussion forms of organization); technology "case method" (maximum proximity to reality); video training methodology (maximum proximity to reality); computer modeling; interactive technologies; technologies of collective and group training; situational modeling technologies; technologies for working out discussion issues; project technology; Information Technologies; technologies of differentiated training; text-centric training technology and others.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.496-499
• /
• 1999

This paper describes a medular neural network(MNN) for a vision system which tracks a given object using a sequence of images from a camera unit. The MNN is used to precisely recognize the given robot endeffector and to minize the processing time. Since the robot endeffector can be viewed in many different shapes in 3-D space, a MNN structure, which contains a set of feedforwared neural networks, co be more attractive in recognizing the given object. Each single neural network learns the endeffector with a cluster of training patterns. The training patterns for a neural network share the similar charateristics so that they can be easily trained. The trained MNN is less sensitive to noise and it shows the better performance in recognizing the endeffector. The recognition rate of MNN is enhanced by 14% over the single neural network. A vision system with the MNN can precisely recognize the endeffector and place it at the center of a display for a remote operator.

• 인지과학
• /
• 제7권1호
• /
• pp.75-84
• /
• 1996

본 논문에서는 필기체 숫자 인식 프로그램을 설계하는데 있어서의 구조적인 면의 중요성을 강조하고 두가지 구조적 설계에 대해서 기술한다.첫째로는 숫자 인식 프로그램에 대한 모듈러 설계를 기술하고 그에 대한 이점들을 기술한다.첫째로는 숫자 인식 프로그렘에 대한 모듈러 설계를 기술하고 그에 대한 이점들을 기술한다.이러한 구조에서 인식기는 10개의 이진 부인식기로 구성되어있으며,각각의 부인식기는 단지 하나의 부류에 대해서만 책임을 진다.규칙기반 휸련과 신경망 기반 훈련을 기술한다. 둘째로는 두개 혹은 그 이상의 인식기를 파이프라인으로 연결하였다.파이프라인에서 두번째 인식기는 첫번째 인식기에서 인식된 패턴을 검증하는 역할을 담당하거나,첫번째 인식기에서 거부된 패턴을 재인시하는 역할을 담당한다.이제까지 얻어진 실험결과는 제안된 구조설계의 장점을 보여주고 있다.

• 한국산업융합학회 논문집
• /
• 제13권1호
• /
• pp.49-54
• /
• 2010

Lean 6 sigma has recently been used to describe a management system which combines lean management and 6 sigma. The marriage between Lean manufacturing and 6 sigma has proven to be a powerful tool for cutting waste and improving the organization operations. Time and quality are the most important metrics in improving any company's production and profit performance. lean 6 sigma is a management innovation for improving production efficiency, process quality, cost reduction, investment efficiency and customer's satisfaction. in this paper, Advanced cell line is builded the home appliance goods of the LCD TV final assembly line of domestic company line, training the multi-skilled man and controlling the production information system based on Lean 6 sigma.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.59-64
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to chose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state- action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem. we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL)as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.321-324
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement Beaming is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement loaming is different from supervised teaming in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement loaming algorithms like Q-learning do not require defining or loaming any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning(AMMQL) as an improvement of the existing Modular Q-Learning(MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 춘계학술대회
• /
• pp.833-835
• /
• 2014

본 연구에서는 호흡동조방사선치료(Respiratory Gating Radiation Therapy, RGRT)에서 매우 중요한 요소 중에 하나인 호흡의 안정성을 효과적으로 향상 시킬 수 있는 호흡연습장치(respiratory training system)를 개발하였다. 개발한 호흡연습장치는 개인고유의 호흡주기를 적용하여 환자에게 편안한 호흡유도를 제공한다. 충분한 연습시간을 부여하기 위해 언제 어디서나 쉽고 간편하게 연습 할 수 있도록 휴대형 기기에 모듈화 시켰으며, 이를 환자에게 제공함으로써 호흡동조방사선치료의 효율성과 정확성을 높이고자 했다. 호흡연습장치를 사용했을 때 호흡의 규칙성, 안정성, 지속성 향상 정도를 알아보기 위해 5명을 대상으로 실험을 진행 하고자 한다. 개인이 자유롭게 호흡하는 '자유호흡(free breathing)' 개인고유 호흡주기를 적용하여 시청각 프로그램을 통해 호흡을 유도하는 '모니터호흡(guide breathing)' 호흡연습 후 시청각 프로그램 없이 호흡하는 '예측호흡(predict breathing)' 3가지 호흡법의 데이터를 이용하여 호흡주기(period)와 호흡깊이(amplitude) 및 호흡패턴(Area)의 변화를 정량적으로 분석함으로써 휴대형 호흡연습장치의 유용성을 평가하고자 한다.

• ETRI Journal
• /
• 제17권3호
• /
• pp.1-16
• /
• 1995

An advanced real-time satellite simulator (ARTSS) has been developed to support the ground operations activities of the ETRI satellite control system, such as testing of the system facilities, validation of flight control procedures, verification of satellite commands as well as training of the ground operators. The design of ARTSS is based on the top-down approach and makes use of a modular programming to ensure flexibility in modification and expansion of the system. Graphics-based monitoring and control facilities enhance the satellite simulation environment. The software spacecraft model in ARTSS simulates the characteristics of a geostationary communication satellite using a momentum bias three-axis stabilization control technique. The system can be also interfaced with a hardware payload subsystem such as Ku-band communication transponder to enhance the simulator capability. Therefore, ARTSS is a high fidelity satellite simulation tool that can be used on low-cost desk top computers. In this paper, we describe the design features, the simulation models and the real-time operating functions of the simulator.