• Journal of Information Technology Services
• /
• v.15 no.4
• /
• pp.85-95
• /
• 2016

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.

• The Journal of the Korea Contents Association
• /
• v.20 no.11
• /
• pp.292-300
• /
• 2020

According to the development of artificial intelligence technology, attempts have been made to interpret phenomena in various fields of the real world such as economic, social, and scientific fields through computer simulations using virtual artificial agents. In the existing artificial agent-based bargaining game analysis, there was a problem that did not reflect the cost incurred when the stage progresses in the real-world bargaining game and the depreciation of the bargaining target over time. This study intends to observe the effect on the bargaining game by adding the cost incurred in the bargaining stage and depreciation of the bargaining target over time (bargaining cost) to the previous artificial agent-based bargaining game model. As a result of the experiment, it was observed that as the cost incurred in the bargaining stage increased, the two artificial agents participating in the game had a share close to half the ratio and tried to conclude the negotiation in the early stage.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.1948-1953
• /
• 2007

Intelligent agent is to decide what customers need on the internet and offer them accurate information. In this paper, the system which can recommend the tourism items in terms of customer's needs is proposed by appling the intelligent agent to railway tourism system. Most of previous agents are focused on price. But, this study proposes the Railway tourism system which offers each customer the best suitable information based on quality of information and reputation. The customer's needs are analyzed through intelligent agent and the information which is suitable for customer's needs is obtained the Artificial Neural Network Model.

• The Journal of Korea Robotics Society
• /
• v.12 no.1
• /
• pp.55-64
• /
• 2017

This paper proposes combination of a cognitive agent architecture named Soar (State, operator, and result) and ROS (Robot Operating System), which can be a basic framework for a robot agent to interact and cope with its environment more intelligently and appropriately. The proposed Soar-ROS human-robot interaction (HRI) agent understands a set of human's commands by voice recognition and chooses to properly react to the command according to the symbol detected by image recognition, implemented on a humanoid robot. The robotic agent is allowed to refuse to follow an inappropriate command like "go" after it has seen the symbol 'X' which represents that an abnormal or immoral situation has occurred. This simple but meaningful HRI task is successfully experimented on the proposed Soar-ROS platform with a small humanoid robot, which implies that extending the present hybrid platform to artificial moral agent is possible.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1050-1053
• /
• 2005

There is no agreed definition of intelligence. The ability to adapt to the environments is a kind of intelligence. Expert functionally recognize environment using their five senses, and acquire and memorize knowledge necessary for operating machines. Knowledge that they cannot acquire directly is acquired in indirect ways. The purpose of intelligence machines is applying to machines experts' knowledge acquisition process and their skills in operating machine. An agent is an autonomous process that recognizes external environment, exchanges knowledge with external machines and performs an autonomous decision-making function in order to achieve common goals. This paper describes agent application for intelligence machine.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.44 no.1
• /
• pp.57-67
• /
• 2008

Recently, Korean shipbuilding industry is keeping up the position of world wide No. 1 in world shipbuilding market share. It is caused by endless efforts to develope new technologies and methods and fast development of IT technologies in Korea, to raise up its productivities and efficiency in shipbuilding industry with many kinds of optimizing methods including genetic algorithm or artificial life algorithm... etc. In this paper, we have suggested the artificial life algorithm with relay search micro genetic algorithm. and we have improved a defect of simple genetic algorithm for its slow convergence speed and added a variety of solution candidates with applying relay search simple genetic algorithm. Finally, we have developed intelligent agent system for ship CAE modeling. We have tried to offer some conveniences a ship engineer for repeated ship CAE modeling by changing ship design repeatedly and to increase its accuracy of a ship model with it.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.136-139
• /
• 2000

In this paper, we use U-Mart that is an agent-based artificial market model. U-Mart is more open than the other artificial market, because In U-Mart, not only computer program agents, but also human agents are able to participate in the market. Therefore, the market in U-Mart gets closer to the real markets and the agents that participate in the market make the complex decision. Moreover we expand to the number of brand to plural. This expansion causes to appear the several strategies to make a profit. As one of this example, we treat the portfolio and confirm the possibility of getting the constancy to make portfolio.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.2
• /
• pp.44-49
• /
• 2007

An agent is an abstract unit for problem solving in the field of distributed artificial intelligence, and an agent-based system is designed and implemented based on the definition of agent as its central concept. Agent modeling is advantageous to abstraction, disintegration and structuring for describing complex system, so its application is increased in various areas including air traffic control, power transmission, e-commerce and medicine. There is no agreed definition of agent but agents have common points as follows: autonomy, reactivity, pro-activeness and cooperation. An agent-oriented modeling is an approach of a concept different form existing object-oriented modeling. This study proposed the agent application for E-Beam manufacturing system. To evaluate the performance of the proposed process design, we used the JADE library. The JADE toolkit provides a FIPA-compliant agent platform and a package to develp Java agents. It provides a basic set of functionalities that are regarded as essential for an autonomous agent architecture.

• The Journal of the Korea Contents Association
• /
• v.10 no.10
• /
• pp.86-93
• /
• 2010

With the introduction of smart phones, the augmented reality became popular and is increasingly drawing attention. The augmented reality in the mobile devices is becoming an individual area to study. Many applications of the augmented reality have been studied, but there are just a few studies on its combination with artificial intelligence in games. In this study, an artificial intelligence algorithm was proposed, which dynamically converts the state of the 3D agent in the augmented reality environment using the 3-Axis acceleration sensor in the smart phone. To control the state of the agent to which the artificial intelligence is applied, users used to directly enter the data or use markers to detect them. The critical values, which were determined via test, were given to the acceleration sensor to ensure accurate state conversion. In this paper, makerless tracking technology was used to implement the augmented reality, and the state of the agent was dynamically converted using the 3-Axis acceleration seonsor.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.21-26
• /
• 2003

Negotiation plays a fundamental role in human cooperative activities, allowing people to resolve conflicts that could interfere with cooperative behaviors. Negotiation In multi-agent systems is achieved through the exchange of messages In a shared agent communication language (ACL). We introduce a rational negotiation meta-language for autonomous, self-interested, and resource-bounded artificial BDI agents. We then propose a negotiation protocol for BDI agents with communicative acts based on their mental states.