• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.8
• /
• pp.171-180
• /
• 2020

Smart Factory consists of digital automation solutions throughout the production process, including design, development, manufacturing and distribution, and it is an intelligent factory that installs IoT in its internal facilities and machines to collect process data in real time and analyze them so that it can control itself. The smart factory's equipment works in a physical combination of numerous hardware, rather than a virtual character being driven by a single object, such as a game. In other words, for a specific common goal, multiple devices must perform individual actions simultaneously. By taking advantage of the smart factory, which can collect process data in real time, if reinforcement learning is used instead of general machine learning, behavior control can be performed without the required training data. However, in the real world, it is impossible to learn more than tens of millions of iterations due to physical wear and time. Thus, this paper uses simulators to develop grid sortation systems focusing on transport facilities, one of the complex environments in smart factory field, and design cooperative multi-agent-based reinforcement learning to demonstrate efficient behavior control.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.315-318
• /
• 2011

최근 인간-컴퓨터 상호작용 분야에 있어서 사용자와의 원활한 협력을 위해 각종 센서 정보로부터 사용자 의도를 인식하고 행동을 예측하여 대응하는 의도대응 인터페이스에 대한 연구가 주목 받고 있다. 이는 사람들 사이에서는 자연스러운 일이며, 인간의 의도대응 과정을 모방하여 공학적으로 구현하는 연구가 활발히 진행 중이다. 본 논문에서는 보다 효과적으로 사용자의 의도에 대응하기 위해서 거울 뉴런과 마음의 이론을 기반으로 하는 사람의 의도대응 과정을 분석하고 이를 바탕으로 인터페이스에 적용 가능한 의도대응 방법을 제안한다. 본 논문에서는 센서로부터 즉각적으로 인식하여 대응 가능한 기본의도와 추가적인 지식을 통해 추론 가능하며 기본의도의 조합으로 이루어진 복합의도에 대해 계층적으로 대응하는 방법을 제안한다. 제안하는 방법은 행동네트워크를 이용하여 기본의도에 대해 즉각적으로 대응을 생성하며, 복합의도에 대하여 계획 기반 방법을 통해 대응 시퀀스를 생성하고 대응을 수행한다. 제안하는 방법은 일정 관리와 집안 관리 서비스를 제공하는 인공비서 시스템에 적용되었으며, 다양한 의도와 상황에 대한 생성 대응을 분석함으로써 사용자의 의도와 관측된 행동을 반영하여 적합한 대응을 생성함을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.12 no.11
• /
• pp.1593-1608
• /
• 2009

If a certain relay node in multi-hop wireless networks might become a malicious node that does not cooperate with other nodes or a selfish node, network throughput will be dramatically decreased. Most of existing ad hoc routing protocols assuming that the nodes will fully cooperate with other nodes do not resolve the problem of network performance degradation due to malicious and selfish nodes. This paper presents the CARE (Cooperative Ad hoc routing protocol based REputation) scheme incorporating the reputation management that can achieve a multi-hop wireless network with high throughput performance. The proposed scheme provides the horizontal cross-layer approach which can identify misbehaving malicious, selfish nodes dropped out of the hop-by-hop based packet processing in the network and then set up an optimal packet routing path that will detour misbehaving nodes. And the vertical cross-layer approach contained in the CARE scheme attempts to improve the quality of routing paths by exploiting the quality of link information received from the MAC layer. Besides, it provides high TCP throughput by exploiting the reputation values of nodes acquired from the network layer into the transport layer. A case study on experiments and simulations shows that the CARE scheme incorporating vertical and horizontal cross-layer approaches yields better performance in terms of the low rate of packet loss, fast average packet delivery time, and high TCP throughput between end-to-end nodes.

• Journal of The Korean Association For Science Education
• /
• v.38 no.5
• /
• pp.667-680
• /
• 2018

The purpose of this study is to investigate 1) the types of knowledge students ask for in their reading comprehension of science textbooks using an online annotation system, 2) the accuracy of the knowledge provided by the students to their peers, 3) the frequency of knowledge sharing behaviors, 4) the evaluation of the effect of collaborative reading, and 5) the trust among peers as knowledge sharers. Questions made by 241 students in the second grade of middle school using an online annotation system in two chapters of the science textbook were analyzed using Bloom's revised taxonomy and their answers were grouped according to five accuracy categories. Also, questionnaires for the evaluation of the effectiveness of collaborative reading comprehension and of trust among the students were used. The students asked their peers 'understanding questions' which comprised almost 80% of the total questions they made and were similar with individual metacognitive strategies for reading comprehension. Of the total threads, 71% has scientifically correct threads shared by the students. The frequency of the knowledge sharing behaviors was high but this was affected by the rewards (point system). Students evaluated that collaborative reading comprehension conducted through an online annotation system were helpful in their learning. In addition, the ratio of students trusting their peers who did the knowledge sharing is over 80%. This study shows that when students use an online annotation system, they can fill one another's cognitive gaps in the reading process by sharing knowledge. Also, collaborative reading using an online annotation system has proved that cognitive individualization is possible through sharing knowledge interactively and dynamically, unlike reading hard copies of textbooks which are a one way information transfer.

• Review of KIISC
• /
• v.9 no.3
• /
• pp.83-96
• /
• 1999

본 논문에서는 독립 에이젼트 기반의 침입탐지 시스템을 구현하고자 한다. 침입 탐 지 시스템의 메시지 유실 및 메시지 내 정보에 대한 처리를 보다 안정적으로 제공하기 위해 단위침입 행동별로 학습된 모니터링 프로세스에서 전송되는 사용자 위협 행동 메시지에 대 한 처리를 담당하는 조정자 에이전트 시스템을 제안한다. 본 논문에서 제안된 조정자는 안 정화된 메시지 처리 문제 뿐아니라 기존모델의 에이젼트간 협력 작업에 의해 처리되었던 침 입 판단 기능 및 모니터링 프로세스들의 관리기능 또한 수행하도록 하게 된다. 따라서 시스 템의 유연성 및 확장성 향상을 도모하도록 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.31-34
• /
• 2009

유비쿼터스 환경에서 상황인지 능력을 가진 지능적 컴퓨팅 개체들 중 사람에게 의존적이지 않고 독립적으로 행동할 수 있는 개체는 유비쿼터스 로봇으로 볼 수 있다. 이러한 로봇은 최근 상호협력 함으로서 보다 최적화된 서비스를 제공하는 연구가 진행되고 있으며, 또한 다수의 로봇이 포함된 환경일 때는 특정한 작업을 수행하기 위하여 특정 로봇의 선별에 관한 연구가 진행 중이다. 본 논문에서는 유비쿼터스 환경에서 서로 다른 기능과 구조를 가지고 있는 지능형 로봇들이 협력하여 특수한 상황이나 임무를 그룹으로 대처할 수 있는 로봇 그룹핑을 설계하고 이를 구현한 결과에 대하여 기술한다. 다수의 로봇 중에서 특정 임무수행을 위한 로봇의 선별 알고리즘은 Entropy를 이용하여 결정 트리를 생성하였다. 또한 Grouping을 위한 Group Layer를 설계하여 구현하였다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.6
• /
• pp.173-180
• /
• 2021

Non Orthogonal Multiple Access (NOMA) is a technology to guarantee the explosively increased Quality of Service(QoS) of users in 5G networks. NOMA can remove the frequent orthogonality in Orthogonal Multiple Access (OMA) while allocating the power differentially to classify user signals. NOMA can guarantee higher communication speed than OMA. However, the NOMA has one disadvantage; it consumes a more energy power when the distance increases. To solve this problem, relay nodes are employed to implement the cooperative NOMA control idea. In a cooperative NOMA network, relay node participations for cooperative communications are essential. In this paper, a new bandwidth allocation scheme is proposed for cooperative NOMA platform. By employing the idea of Vickrey-Clarke-Groves (VCG) mechanism, the proposed scheme can effectively prevent selfishly actions of relay nodes in the cooperative NOMA network. Especially, base stations can pay incentives to relay nodes as much as the contributes of relay nodes. Therefore, the proposed scheme can control the selfish behavior of relay nodes to improve the overall system performance.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.1
• /
• pp.83-108
• /
• 2019

This study investigated South Korean citizens' political communication and deliberation through Twitter during the 2014 General Election, focusing on influential opinion leaders' political information behaviors. Individual semi-structured interviews were administered with 13 opinion leaders using the multiple interview modes of email interviews, Skype interview and face to face interviews. Through the analytical lens of the theory of Information Worlds, the chosen social types and social norms of opinion leaders impacted their political information behaviors, including how they assessed, shared, exchanged, or avoided information, and, in turn, created boundaries between and around their information worlds that allowed for both conflict and synergy.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.1
• /
• pp.135-146
• /
• 2022

A safe working environment is an important and crucial factor in the operation of a firm, and is also essential for logistics companies in supply chain management. This study confirmed that the safety climate and safety prevention activities have a positive relationship with safety behavior from the perspective of domestic small and medium-sized logistics companies that continue their business relationships by signing contracts with large logistics companies. In addition, the moderating role of regulatory uncertainty and competition uncertainty in the previous positive relationship was empirically examined.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.587-594
• /
• 2001

Multi-agent system fits to the distributed and open internet environments. In a multi-agent system, agents must cooperate with each other through a coordination procedure, when the conflicts between agents arise. Where those are caused by the point that each action acts for a purpose separately without coordination. But previous researches for coordination methods in multi-agent system have a deficiency that they cannot solve correctly the cooperation problem between agents, which have different goals in dynamic environment. In this paper, we suggest the automatic coordination model for multi-agent system using neural network and reinforcement learning in dynamic environment. We have competitive experiment between multi-agents that have complexity environment and diverse activity. And we analysis and evaluate effect of activity of multi-agents. The results show that the proposed method is proper.