• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.175-181
• /
• 2021

This paper analyzes the artificial intelligence-based approach for short-term energy consumption prediction. In this paper, we employ the reinforcement learning algorithms to improve the limitation of the supervised learning algorithms which usually utilize to the short-term energy consumption prediction technologies. The supervised learning algorithm-based approaches have high complexity because the approaches require contextual information as well as energy consumption data for sufficient performance. We propose a deep reinforcement learning algorithm based on multi-agent to predict energy consumption only with energy consumption data for improving the complexity of data and learning models. The proposed scheme is simulated using public energy consumption data and confirmed the performance. The proposed scheme can predict a similar value to the actual value except for the outlier data.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.589-591
• /
• 2003

현재 대부분 e-Learning에서 이루어지고 있는 교육은 학습(Loaming)이 아닌 단순 훈련(Trainning)만이 이루어지고 있다. e-Learning에서 진정한 학습이 이루어지기 위해서는 학습자의 수준에 맞는 적응적(Adaptive), 적시적(Just-in-Time) 학습이 단편적이 아닌 연속적, 통합적으로 이루어져야 한다. 이를 위해서는 기술적 관점뿐만 아니라, 발견적 학습(heuristic learning)관점에서 학습자원이 기술되고, 컴퓨터(에이전트)가 학습자원의 구성요소인 학습목표(Goal), 학습내용(Content), 학습맥락(Context), 학습구조(Structure), 학습전략(Strategy)의 의미(Semantic)와 관계(Relation)를 이해해 학습자에게 필요한 정보만을 검색, 추론해주고 이를 학습자 수준에 맞게 재가공해 학습자에게 지식(Knowledge)을 적응적(Adaptive), 적시적(Just-in-Time)으로 전달해주는 e-Learning 학습 환경이 필수적이다. 메타데이터(RDF), 온톨로지(Ontology), 에이전트(Agent) 매커니즘의 시멘틱 웹을 e-Learning 환경에 적용함으로써 학습자원의 구성요소의 의미와 관계를 파악해 적응적(Adaptive)으로 지식을 전달해 주어 자기 주도적 학습(Self-directed Loaming)을 실현해 줄 수 있다.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2001.05a
• /
• pp.152-158
• /
• 2001

Since web_based tutoring systems are generally composed with passive and static hypertext, they could not provide adaptive learning environments according to learning ability of each student. In this study, we suggest an intelligent tutoring system, which grasps the learning state of student and provides each student with dynamic learning materials suitable to individual feature based on learning result. It is an agent based system, in which, courseware knowledge for learning is effectively constructed, the proper feedback according to learning assessment is inferred, and it is given to each student.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.447-456
• /
• 2004

Information extraction is a process of recognizing and fetching particular information fragments from a document. In order to extract information uniformly from many heterogeneous information sources, it is necessary to produce information extraction rules called a wrapper for each source. Previous methods of information extraction can be categorized into manual wrapper generation and automatic wrapper generation. In the manual method, since the wrapper is manually generated by a human expert who analyzes documents and writes rules, the precision of the wrapper is very high whereas it reveals problems in scalability and efficiency In the automatic method, the agent program analyzes a set of example documents and produces a wrapper through learning. Although it is very scalable, this method has difficulty in generating correct rules per se, and also the generated rules are sometimes unreliable. This paper tries to combine both manual and automatic methods by proposing a new method of learning information extraction rules. We adopt the scheme of supervised learning in which a user-interface agent is designed to get information from the user regarding what to extract from a document, and eventually XML-based information extraction rules are generated through learning according to these inputs. The interface agent is used not only to generate new extraction rules but also to modify and extend existing ones to enhance the precision and the recall measures of the extraction system. We have done a series of experiments to test the system, and the results are very promising. We hope that our system can be applied to practical systems such as information-mediator agents.

• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1431-1438
• /
• 2004

Reinforcement learning learns policies for accomplishing a task's goal by experience through interaction between agent and environment. Q-learning, basis algorithm of reinforcement learning, has the problem of curse of dimensionality and slow learning speed in the incipient stage of learning. In order to solve the problems of Q-learning, new function approximation methods suitable for reinforcement learning should be studied. In this paper, to improve these problems, we suggest Fuzzy Q-Map algorithm that is based on online fuzzy clustering. Fuzzy Q-Map is a function approximation method suitable to reinforcement learning that can do on-line teaming and express uncertainty of environment. We made an experiment on the mountain car problem with fuzzy Q-Map, and its results show that learning speed is accelerated in the incipient stage of learning.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.644-649
• /
• 2021

Self-Imitation Learning is a simple off-policy actor-critic algorithm that makes an agent find an optimal policy by using past good experiences. In case that Self-Imitation Learning is combined with reinforcement learning algorithms that have actor-critic architecture, it shows performance improvement in various game environments. However, its applications are limited to reinforcement learning algorithms that have actor-critic architecture. In this paper, we propose a method of applying Self-Imitation Learning to Deep Q-Network which is a value-based deep reinforcement learning algorithm and train it in various game environments. We also show that Self-Imitation Learning can be applied to Deep Q-Network to improve the performance of Deep Q-Network by comparing the proposed algorithm and ordinary Deep Q-Network training results.

• Electronics and Telecommunications Trends
• /
• v.35 no.6
• /
• pp.137-149
• /
• 2020

Several multi-agent reinforcement learning (MARL) algorithms have achieved overwhelming results in recent years. They have demonstrated their potential in solving complex problems in the field of real-time strategy online games, robotics, and autonomous vehicles. However these algorithms face many challenges when dealing with massive problem spaces in sparse reward environments. Based on the centralized training and decentralized execution (CTDE) architecture, the MARL algorithms discussed in the literature aim to solve the current challenges by formulating novel concepts of inter-agent modeling, credit assignment, multiagent communication, and the exploration-exploitation dilemma. The fundamental objective of this paper is to deliver a comprehensive survey of existing MARL algorithms based on the problem statements rather than on the technologies. We also discuss several experimental frameworks to provide insight into the use of these algorithms and to motivate some promising directions for future research.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.12
• /
• pp.1039-1044
• /
• 2005

This paper presents a robotic agent design and application in the ubiquitous intelligent space. We set up an experimental environment with Bluetooth host, Bluetooth client, furniture and home appliance, and robotic agents. First, the agents basically performed patrol guard to detect unexpected penetration, and to keep home safely from gas-leakage, electric leakage, and so on. They were out to patrol fur a robbery while navigating in a living room and a private room. In this task, we used an area-based action making and a hexagon-based Q-learning to control the agents. Second, the agents communicate with Bluetooth host device to access and control a home appliance. The Bluetooth host offers a manual control to person by inquiring a client robot when one would like to check some place especially. In this exercise, we organize asynchronous connection less (ACL) between the host and the client robots and control the robot maneuver by Bluetooth host controller interface (HCI).

• 한국HCI학회:학술대회논문집
• /
• 2008.02b
• /
• pp.78-84
• /
• 2008

The traditional intelligent teachable system has mainly focused on knowledge and cognition. It has overlooked motivational aspects of learners. Motivation is an important factor in learning making learners to have interests in a given task and persist it. Although the systems include cognitive as well as motivational factors, the effects of ITS on interest are not equivalent depending on individual characteristics. This study is to investigate how influence learners' response patterns to their interests and also examined effects of individual characteristics on interest in teachable agent (TA). In this experiment, we used KORI which is a new type of ITS that learner teach computer agent based on the instructional method of learning by teaching'. In the beginning of experiments, metacognition, achievement goal orientation and self-efficacy were measured as individual characteristics. Then, participants were asked to use KORI at home during 10 days. After using KORI the level of interest were measured. The result showed that metacognition was positively related with interest, whereas performance goal orientation and mastery goal orientation were negatively related to interest. It suggests t hat different individual characteristics should be considered to promote learners' intrinsic motivation in TA.

• Journal of Korean Society of Rural Planning
• /
• v.27 no.2
• /
• pp.77-89
• /
• 2021

To predict the level of residents' participation in rural tourism project, we used agent-based model. The decision-making mechanism which calculates the utility related to attitude, subjective norm, perceived behavioral control of planned behavior theory was applied to the residents' decision to participate. As a result of the simulation over a period of 20 years, in the baseline scenario set similar to the general process of promoting rural projects, the proportion of indigenous people decreased and the participation rate decreased. In the scenarios with different learning frequencies in perceived behavioral control, overall participation rate decreased. Learning every five years had the effect of increasing the participation rate slightly. Participation rates increased significantly in the scenario that consider economic aspects and reputation in attitude and did not decline in the scenario where population composition was maintained. The virtuous cycle effect of subjective norm according to changes in participation rate due to influence of attitude and perceived behavioral control shows the dynamic relationship.