• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.51-58
• /
• 2009

Reinforcement learning is a sub area of machine learning concerned with how an agent ought to take actions in an environment so as to maximize some notion of long-term reward. In the case of multi-agent, especially, which state space and action space gets very enormous in compared to single agent, so it needs to take most effective measure available select the action strategy for effective reinforcement learning. This paper proposes a multi-agent reinforcement learning model based on fuzzy inference system in order to improve learning collect speed and select an effective action in multi-agent. This paper verifies an effective action select strategy through evaluation tests based on Robocup Keepaway which is one of useful test-beds for multi-agent. Our proposed model can apply to evaluate efficiency of the various intelligent multi-agents and also can apply to strategy and tactics of robot soccer system.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.299-308
• /
• 2014

Various literatures related computing of information processing have been recently shown the researches inspired from the remarkably excellent human capabilities which recognize and categorize very complex visual patterns such as body motions and facial expressions. Applied from human's outstanding ability of perception, the classification function of visual sequences without context information is specially crucial task for computer vision to understand both the coding and the retrieval of spatio-temporal patterns. This paper presents a biological process based action recognition model of computer vision, which is inspired from visual information processing of human brain for action recognition of visual sequences. Proposed model employs the structure of neural fields of bio-inspired visual perception on detecting motion sequences and discriminating visual patterns in human brain. Experimental results show that proposed recognition model takes not only into account several biological properties of visual information processing, but also is tolerant of time-warping. Furthermore, the model allows robust temporal evolution of classification compared to researches of action recognition. Presented model contributes to implement bio-inspired visual processing system such as intelligent robot agent, etc.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.4
• /
• pp.368-374
• /
• 2013

Maintenance works for current high-rise buildings significantly depend on human labor, unlike other construction processes that are gradually being automated. Herein, this paper proposes robotic building maintenance system using motion control, in specific, reducing a system jerk which is directly subjected to improve the process performance and economic feasibility. The sensor for detecting straight and curvature section of the building facade, moreover rail-joint segment can be detected and be utilized for reducing jerk of the system. Analysis of the proposed system error caused by excessive vibration, e.g. jerk motion is introduced. To enhance the stability and safety of the system, herein, the strategy is proposed for enhancing the performance of the system based on anti-jerk motion control algorithm which comes out increasing the stability and sustainability of the integrated system, as well.

• Journal of KIISE:Software and Applications
• /
• v.35 no.7
• /
• pp.424-430
• /
• 2008

Identifying crosscutting concerns during requirements engineering phase is one of the most essential parts in Aspect-Oriented Software Development. Considering crosscutting concerns in the earlier phase of the development improves consistency among requirements so that it can help maintain software systems efficiently and effectively. It also provides a systematic way to manage requirements changes by supporting traceability throughout the software lifecycle. Thus, identifying tangled and scattered concerns, and encapsulating them into separate entities must be addressed from the early phase of the development. To do so, first, functional and non-functional concerns must be clearly separated. Second, a pointcut where a main concern meets crosscutting concerns should be defined and specified precisely. Third, it is required to detect conflicts being occurred during composition of crosscutting concerns from the earlier phase. Therefore, this paper proposes a systematic approach to identifying and specifying crosscutting concerns using goal-scenario based requirements analysis. And we demonstrate the applicability of the approach by applying it into the intelligent service robot system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.6
• /
• pp.1139-1145
• /
• 2014

User recognition technology, which identifies or verifies a certain individual is absolutely essential under robotic environments for intelligent services. The conventional face recognition algorithm using single distance face image as training images has a problem that face recognition rate decreases as distance increases. The face recognition algorithm using face images by actual distance as training images shows good performance but this has a problem that it requires user cooperation. This paper proposes the LDA-based long distance face recognition method which uses multiple distance face images from a zoom camera for training face images. The proposed face recognition technique generated better performance by average 7.8% than the technique using the existing single distance face image as training. Compared with the technique that used face images by distance as training, the performance fell average 8.0%. However, the proposed method has a strength that it spends less time and requires less cooperation to users when taking face images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1060-1065
• /
• 2011

In this paper, the proposed method is recognized the hands using color information with input image of the camera. It controls the mouse pointer using recognized hands. In addition, specific commands with the mouse pointer is designed to perform. Most users felt uncomfortable since existing interaction multimedia systems depend on a particular external input devices such as pens and mouse However, the proposed method is to compensate for these shortcomings by hand without the external input devices. In experimental methods, hand areas and backgrounds are separated using color information obtaining image from camera. And coordinates of the mouse pointer is determined using coordinates of the center of a separate hand. The mouse pointer is located in pre-filled area using these coordinates, and the robot will move and execute with the command. In experimental results, the recognition of the proposed method is more accurate but is still sensitive to the change of color of light.

• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.290-298
• /
• 2015

This paper suggests a multi-agent message transport architecture based on the message-oriented middleware ZeroMQ. Compared with the other middlewares such as CORBA, Ice, and Thrift, ZeroMQ receives a good score in the evaluation of performance, QoS (Quality of Service), patterns, user friendliness, and resources. The suggested message transfer architecture borrowed many basic concepts like agent platform, AMS (Agent Management System), and MTS (Message Transfer System) from FIPA (Foundation for Intelligent Physical Agents) standard multi-agent specifications, and the architecture inherited the strength of the architecture from the multi-agent framework SMAF (Smart Multi-Agent Framework). The architecture suggested in this paper is a novel peer-to-peer architecture which is not known to the ZeroMQ community. In the suggested architecture, every MTS agent uses only one ZeroMQ router socket to support peer-to-peer communication among MTS agents. The suggested architecture can support closely collaborating software areas such as intelligent robots as well as the traditional application areas of multi-agent architecture. The suggested architecture has interoperability and scalability with the ZeroMQ devices and patterns.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.854-856
• /
• 2014

Has been released of make it possible to control the using for smart devices of a wide variety home appliances and electronics in smart appliances in accordance with the one person multi devices. In addition, is increasing rapidly for the number of the product on cleaning robot and refrigerator, air conditioning, TV, etc. these devices are using the implement up DLNA system. And at home and abroad for development and has provided with Iot and Alljoyn such systems. But currently using home appliances or electronic devices of there are a lot of the operating system non installed than the installed products. In addition, smart appliances do not use for user than buying existing electronic products a lot more. In addition, more occur for smart appliances of that do not use for the user on smart appliances rather than buying existing electronics. In this paper, Suggested and implemented for system of control such as smart devices to existed home appliance on not have an operating system, Using mobile device for want users to quantify the data to transfer from arduino board.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.210-212
• /
• 2021

In modern society, various digital equipment are being distributed due to the influence of the 4th industrial revolution, and they are used in a wide range of fields such as automated processes, intelligent CCTV, medical industry, robots, and drones. Accordingly, the importance of the preprocessing process in a system operating based on an image is increasing, and an algorithm for effectively reconstructing an image is drawing attention. In this paper, we propose a filter algorithm based on a combined weight value to reconstruct an image in a complex noise environment. The proposed algorithm calculates the weight according to the spatial distance and the weight according to the difference between the pixel values for the input image and the pixel values inside the filtering mask, respectively. The final output was filtered by applying the join weights calculated based on the two weights to the mask. In order to verify the performance of the proposed algorithm, we simulated it by comparing it with the existing filter algorithm.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2009.04a
• /
• pp.226-229
• /
• 2009

굴삭기는 다양한 산업 분야에서 폭넓게 이용되고 있는 대표적인 장비임에도 불구하고 작업 환경은 매우 열악하여 굴삭 조종자는 각종 소음이나 진동, 분진에의 노출뿐만 아니라 산업재해의 위험성 또한 높다. 이러한 문제점들을 타개하기 위하여 현재 국내에서는 2006년부터 지능형굴삭시스템(Intelligent Excavating System)에 의한 자동화된 굴삭기의 개발을 위하여 연구를 진행 중에 있다. 자동화 굴삭시스템 구축에 있어서 센싱(sensing)을 통해 획득된 지형 및 주변 환경정보를 활용하여 숙련공의 휴리스틱스(heuristics)를 바탕으로 설계된 모듈을 통해 최적의 굴삭 작업 계획을 세우고, GUI (Graphic User Interface)를 제공하여 실시간 작업진행 상태 파악 및 모니터링(monitoring) 내용을 굴삭기 조종자와 공사 감독관에게 제공하는 Task Planning System의 개발은 생산성, 안전성, 작업의 품질 및 장비의 성능에도 지대한 영향을 미치며 자동화된 굴삭시스템을 개발함에 있어서 필수적으로 요구되어지는 핵심기술이다. 본 논문에서는 자동화 굴삭시스템을 위한 자동화 계획생성 시스템인 Task Planning System의 현재까지 진행된 연구 내용과 모니터링 및 작업에 대한 최소간섭을 위한 Task Planning System Interface를 소개한다.