• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.73-77
• /
• 2001

본 논문에서는 부분적으로 관측 가능한 환경에서 사전의 모델 정보 없이 확률적인 행동 정책을 학습하는 상태 조직화 강화 학습 모델을 제안한다. 기존의 강화학습은 환경 모델을 사전에 필요로 하고 상태 전체의 관측이 필요하기 때문에 학습 이전에 문제에 대해 알아야 한다는 제약이 있다. 또한 작은 문제에 대해서는 잘 적용되지만 상태의 수가 매우 많고 부분적으로만 관측한 경우가 많은 실제 문제에는 그대로 적용하기가 불가능하다. 이러한 두 가지 단점을 해결하기 위해 본 논문에서는 사전의 모델 정보 없이 부분적인 관측값으로부터 상태와 행동 정책을 동시에 학습해 나가는 강화 학습 모델을 제안하고, 제안된 방법을 부분적으로만 관측이 가능한 미로 탐색 문제에 적용하였다.

• English Language & Literature Teaching
• /
• v.15 no.2
• /
• pp.1-25
• /
• 2009

The purpose of this study is to explore the potential of peer coaching for EFL teachers' professional development. For this study, 12 college teachers in Korea participated in a 10-week program. They were 7 males and 5 females, ranging in age from 24 to 37 years. Data were collected through semi-structured interviews. Reflective analysis was used to analyze individual interview data. From the findings, two significant categories of peer coaching were identified: positive and negative responses to peer coaching experience. However, the overriding themes that emerged from the data were the benefits of peer coaching. The participants were almost unanimous in their acknowledgement of the advantages of peer coaching, such as reflective support through other's eyes, improved working environments, greater teaching strategies, higher professional self-esteem, and awareness of self-directed learning. Negative responses also appeared, mostly in regard to the working principles of implementation; the major issues of difficulties were time management, complexities of implementation procedure, stress and personal vulnerability, and relative lack of reflection and feedback skills. Demonstrating the participants' experiences towards the peer coaching program, this study provides EFL teachers with useful insights into peer coaching as an effective tool of their professional development.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.2
• /
• pp.192-197
• /
• 2009

In this paper, we proposed the obstacle avoidance system using a single camera image and LM(Levenberg-Marquart) neural network fuzzy controller. According to a robot technology adapt to various fields of industry and public, the robot has to move using self-navigation and obstacle avoidance algorithms. When the robot moves to target point, obstacle avoidance is must-have technology. So in this paper, we present the algorithm that avoidance method based on fuzzy controller by sensing data and image information from a camera and using the LM neural network to minimize the moving error. And then to verify the system performance of the simulation test.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.887-890
• /
• 1993

By introducing the notion of constraint-oriented fuzzy inference, we will show that it provides us ways of fuzzy control methods that has abilities of adaptation, learning and self-organization. The basic supporting techniques behind these abilities are“hard”processing by Artificial Intelligence or traditional computational framework and“soft”processing by Neural Network or Genetic Algorithm techniques. The reason that these techniques can be incorporated to fuzzy control systems is that the notion of“constraint”itself has two fundamental properties, that is, the“modularity”property due to its declarativeness and the“logicality”property due to its two-valuedness. From the former property, the modularity property, decomposing and integrating constraints can be done easily and efficiently, which enables us to carry out the above“soft”processing. From the latter property, the logicality property, Qualitative Reasoning and Instance Generalization by Symbolic Reasoning an be carried out, thus enabling the“hard”processing.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.1
• /
• pp.22-30
• /
• 2001

This paper describes a neural network based fuzzy PID control scheme. The PID controller is being widely used in industrial applications. However, it is difficult to determine the appropriated PID gains in nonlinear systems and systems with long time delay and so on. In this paper, we re-analyzed the fuzzy controller as conventional PID controller structure, and proposed a neural network based self tuning fuzzy PID controller of which output gains were adjusted automatically. The tuning parameters of the proposed controller were determined on the basis of the conventional PID controller parameters tuning methods. Then they were adjusted by using proposed neural network learning algorithm. Proposed controller was simple in structure and computational burden was small so that on-line adaptation was easy to apply to. The experiment on the magnetic levitation system, which is known to be heavily nonlinear, showed the proposed controller's excellent performance.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.400-409
• /
• 2003

Collaborative filtering (CF) recommendation is a knowledge sharing technology for distribution of opinions and facilitating contacts in network society between people with similar interests. The main concerns of the CF algorithm are about prediction accuracy, speed of response time, problem of data sparsity, and scalability. In general, the efforts of improving prediction algorithms and lessening response time are decoupled. We propose a three-step CF recommendation model which is composed of profiling, inferring, and predicting steps while considering prediction accuracy and computing speed simultaneously. This model combines a CF algorithm with two machine learning processes, SOM (Self-Organizing Map) and CBR (Case Based Reasoning) by changing an unsupervised clustering problem into a supervised user preference reasoning problem, which is a novel approach for the CF recommendation field. This paper demonstrates the utility of the CF recommendation based on SOM cluster-indexing CBR with validation against control algorithms through an open dataset of user preference.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.617-620
• /
• 2018

딥러닝 기술에 있어서 대량의 학습 데이터가 필요하다는 한계점을 극복하기 위한 시도로서, 적은 데이터 만으로도 좋은 성능을 낼 수 있는 few-shot 학습 모델이 꾸준히 발전하고 있다. 하지만 few-shot 학습 모델의 가장 큰 단점인 적은 데이터로 인한 과적합 문제는 여전히 어려운 숙제로 남아있다. 본 논문에서는 모델 압축에 사용되는 distillation 기법을 사용하여 few-shot 학습 모델의 학습 문제를 개선하고자 한다. 이를 위해 대표적인 few-shot 모델인 Siamese Networks, Prototypical Networks, Matching Networks에 각각 distillation을 적용하였다. 본 논문의 실험결과로써 단순히 결과값에 대한 참/거짓 뿐만 아니라, 참/거짓에 대한 신뢰도까지 같이 학습함으로써 few-shot 모델의 학습 문제 개선에 도움이 된다는 것을 실험적으로 증명하였다.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.1-9
• /
• 2018

With developments in science and technology and improvement in living standards, human life expectancy is steadily increasing worldwide. For effective healthcare, it is necessary to check health conditions according to individuals' behavior and acquire prior knowledge on possible diseases. In this study, we classified the diseases that are major causes of death in Korea by referring to data provided by the Korea National Health and Nutrition Examination Survey. We selected indexes that could be used as indicators of major diseases and created the LCBB-SC. In the LCBB-SC, the data are systematically subdivided into related fields to provide integrated data related to each disease and to provide an infrastructure that can be used by researchers. In addition, by developing a web interface allowing for self-symptom assessments, this resource will be beneficial to people who want to check their own health condition using a list of diseases that might be caused by their behaviors.

• Journal of Service Research and Studies
• /
• v.11 no.2
• /
• pp.37-66
• /
• 2021

This study aims to provide self-development opportunities to hair salons service workers through e-learning and provide the foundation of sustainable hair salons management by cultivating good talents to hair salons service business executives. In particular, the factors affecting e-learning achievement are identified according to learner characteristics to see whether these factors affect the satisfaction of e-learning learners and also affect the performance of management. The results of the study are summarized as follows. As a result of hypotheses testing on the relationship between e-learning learning environment and e-learning satisfaction, it was found that the higher the level of e-learning content quality is, the higher the satisfaction of e-learning is, the higher the satisfaction of e-learning is, and that the higher the quality level of the support infrastructure is, the higher the satisfaction of e-learning is. The results of the hypotheses testing on the moderating effect of learner factors showed that the influence of the quality of the support infrastructure on the e-learning satisfaction differs according to the level of the learner's goal consciousness. However, it was found that the influence of content quality on e-learning satisfaction according to the level of the learners goal awareness, the influence of content quality on e-learning satisfaction according to the level of the aggressiveness of the learners learning attitude, and the influence of the quality of the support infrastructure on the e-learning satisfaction according to the level of the aggressiveness of learners learning attitude were found to identically demonstrate no moderating effects. The results of hypotheses testing on the relationships among e-Learning performance show that the higher the satisfaction of e-learning was, the higher the customer orientation was, and the higher the satisfaction of e-learning was, the higher the contribution of management performance was, and the higher the customer orientation was, the higher the contribution of management performance was. The implications of this study are as follows. First, the actual path of realiting e-learning performance could be identified that is this study provided organizational decision makers involved in the hair salons service operations with practical guidance for the introduction and expansion of successful educational systems. Second, the e-learning environment derived from the theoretical background is different from the e-learning environment required by the learners.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.419-422
• /
• 2003

To improve the recognition accuracy of a developed artificial odor discrimination system for three mixture fragrance recognition, Fuzzy Similarity based Self-Organized Network inspired by Immune Algorithm (F-SONIA) is proposed. Minimum, average, and maximum values of fragrance data acquisitions are used to form triangular fuzzy numbers. Then the fuzzy similarity treasure is used to define the relationship between fragrance inputs and connection strengths of hidden units. The fuzzy similarity is defined as the maximum value of the intersection region between triangular fuzzy set of input vectors and the connection strengths of hidden units. In experiments, performances of the proposed method is compared with the conventional Self-Organized Network inspired by Immune Algorithm (SONIA), and the Fuzzy Learning Vector Quantization (FLVQ). Experiments show that F-SONIA improves recognition accuracy of SONIA by 3-9％. Comparing to the previously developed artificial odor discrimination system that used FLVQ as pattern classifier, the recognition accuracy is increased by 14-25％.