Earticle

Technological innovations over the years have accentuated the workings in corporate- connected organizations and different application platforms. Hence, a unified management information system (MIS) that can utilize the Web and propel programming developments is required. Software agents, the latest developments in computer software technology, can be utilized to rapidly and effortlessly build integrated information systems. Consequently, 59 research papers on the use of software agents in MIS were identified from top 40 MIS journals published between 2007 and 2017. Then, we reviewed and classified all the research papers according to two categories: application fields and application categories. The application fields consisted of eight sub-groups: manufacturing, telecommunication systems, traffic and transportation management, information filtering and gathering, electronic commerce, business process management, entertainment, and medical care; whereas the application categories consisted of three sub-groups: multi-agent systems, personal assistants, and multi-agent simulation. The research papers were further divided into journal and year of publication, and journal and application field. The objective of our research was to understand the trend of the use software agent technology in MIS by examining the published research paper beside to add knowledge and content to the information system academic discipline.

현대 사회의 위험을 예측하기 어려워지면서 회복력 개념을 중심으로 위기관리의 패러다임이 변화하고 있 다. 회복력은 재난 상황에 대응하고 회복하는 시스템의 능력이며, 주요 요인으로 시스템 내 행위자의 적응력이 강 조된다. 따라서 본 연구에서는 사회생태계의 재난복구과정에 대한 다행위자시스템 모델을 구축하고, 회복력 요인 에 따른 재난복구과정의 변화양상을 추정했다. 특히 본 연구에서는 적응력의 구성요소인 거버넌스 시스템에 주목 해 거버넌스의 구조 유형에 따라 달라지는 재난복구과정의 변화 패턴을 평가했다. 이를 위해 재난복구과정을 개념 화하고 행위자 간의 의사결정 및 상호작용 요소를 추출했으며, 적응적 복잡계를 모사하는데 유용한 Netlogo 프로 그램을 이용해 관련 시뮬레이션을 개발하고 시나리오 분석을 수행했다. 그 결과 거버넌스 구조 유형 중 운영조직에 의한 네트워크가 가장 안정적인 구조임을 확인할 수 있었다. 이 연구는 사회생태계의 회복력을 강화하는데 있어 시 스템 내 행위자에 초점을 두는 것이 유용함을 밝히며, 향후 실측 자료를 기반으로 한 재난복구모형 구축의 가능성 을 제시했다는 데 의의가 있다.

As the risk of modern society becomes difficult to predict, the risk management paradigm has changed centering on the “resilience” concept. Resilience is the ability of the system to respond to and recover from a disaster, and the main factor is the “adaptability” of actors in the system. Therefore, in this study, we build up a multi-agent system model for the disaster recovery process of socio-ecological system and estimated the change pattern of the process according to the resilience factors. In particular, this study focused on the governance system, which is a component of adaptability, and evaluated the change pattern in disaster recovery process depending on the type of governance structure. To do this, we conceptualized the disaster recovery process, extracted the actors’ decision-making and interaction elements, and developed simulation model and analyzed the scenarios using the Netlogo program, which is useful for simulating adaptive complex systems. The presented results suggest that the network by the administrative organization is the most stable structure among the types of governance structure. This study shows that it is useful to focus on the actors in the system to strengthen the resilience of the socio-ecological system, and suggest the possibility of constructing a disaster recovery model based on observation data.

Negotiation is a process of reaching an agreement on the terms of a transaction, such as price, quantity, for two or more parties. Negotiation tries to maximize the benefits for all parties concerned. Instead of using human-based negotiation, the e-commerce environment provides such an environment as adopting automated negotiation. Thus, choosing agent technology is appropriate for an automatic electronic negotiation platform, since autonomous software agents strive for the best deal on behalf of the human participants. Negotiation agents need a clear-cut definition of negotiation models or strategies. In reality, most bargaining systems embody nearly one negotiation model. In this article, we present a mobile agent negotiation system with reusable negotiation strategies that allows agents to dynamically embody a user’s favorite negotiation strategy which can be preinstalled as a component in the system. We develop a prototype system, which is fully implemented in compliance with FIPA specifications, and then, describe the benefits of using the system.

기존의 웹 기반 의료 서비스는 환자 자신이 직접 해당 사이트를 찾아 읽어보고 의사들과 e-mail로 상담하는 수준이었다. 환자는 자신의 증상과 유사한 정보가 어디에 있는지 알아야 하고 의사들은 e-mail을 일일이 읽고 답해 주어야만 한다. 그러나 메일 에이전트, 진단 에이전트 등이 존재하는 멀티 에이전트 시스템이 개발된다면 기존의 web 기반 의료 서비스의 단점을 보완할 수 있다. 본 논문에서는 JATLite 기반의 멀티 에이전트 시스템을 설계하여 자동으로 e-mail을 분석, 분류, 전달, 진단하는 시스템을 개발하였다. 제안된 멀티 에이전트는 메일 에이전트, 진단 에이전트, 중재 에이전트 등으로 구성된다. 메일 에이전트는 환자의 상담, 요청, 증상 등을 분석하여 해당하는 진단 에이전트에게 전달하는 일을 한다. 진단 에이전트는 지식베이스를 이용하여 환자의 요구사항에 가장 적절한 진단을 하게 된다. 중재 에이전트는 에이전트의 상태를 파악하여 작업을 지시하고 메일 에이전트와 진단에이전트간의 통신을 관리한다.

지능형 로봇의 사용자는 다양한 이유로 로봇의 상태 정보가 필요하다. 이러한 지능형 로봇의 상태 정보는 지능형 로봇을 구성하는 기능 에이전트의 상태 정보를 조합하여 생성할 수 있다. 하지만 기존 지능형 로봇 시스템은 1) 지능형 서비스 로봇의 상태 정보 생성을 위해 필요한 에이전트 상태 정보를 생성하지 않거나, 각기 다른 방법으로 생성하고 있어 이를 일괄적으로 수집할 수 없다. 또한 2) 복수의 사용자가 같은 정보를 요청하면 이를 여러 번 수집하여 데이터 중복성 문제가 발생하였고, 3) 한 가지 통신 방법만을 지원하여 사용자가 원하는 통신 방법을 제공하지 못한다는 한계점을 가지고 있다. 본 논문에서는 이러한 한계점을 해결하기 위한 지능형 서비스 로봇을 위한 멀티 에이전트 모니터링 시스템을 제안한다. 이 모니터링 시스템은 1) 기능 에이전트의 행위 수행에 따라 상태 정보를 생성하게 함으로써, 에이전트 상태 정보를 단일화된 방법으로 생성 및 수집할 수 있다. 또한 2) 모니터링 시스템이 사용자의 모니터링 수요에 따라 필요한 데이터를 한 번씩만 수집하여 데이터 중복성 문제를 해결하며, 3) 사용자가 원하는 통신 방법을 지원하는 프록시를 통해 상태 정보를 전달하여 통신 방법에 대한 호환성을 제공한다. 우리는 실험을 통해 이 모니터링 시스템이 다양한 통신 방법을 활용하여 여러 사용자에게 지능형 로봇의 상태 정보를 전달하는 것을 확인할 수 있었다.

Users of intelligent robots require access to the status data of the robots for various reasons. The status data of intelligent robots can be generated by combining the status data of the functional agents that constitute the intelligent robot. However, existing intelligent robot systems do not generate the necessary agent status data for creating the status data of intelligent service robots, or they generate it in different ways, making it impossible to collect this information in a uniform manner. Furthermore, these systems have limitations such as collecting the same information redundantly if multiple users request it and only using a single method of communication to deliver robot information, thereby failing to offer the communication methods desired by users. This paper proposes a multi-agent monitoring system for intelligent service robots designed to overcome these limitations. This monitoring system generates status data in response to the actions performed by functional agents, thereby allowing for the unified generation and collection of agent status data. Additionally, the monitoring system resolves data redundancy issues by collecting the necessary data just once, in accordance with user monitoring demands, and delivers status data through a proxy that supports the preferred communication methods of users, thereby providing compatibility with various communication methods. Through experiments, we have verified that this monitoring system can deliver the status data of intelligent robots to multiple users using various communication methods.

최근 건설분야에 적용될 수 있는 자동화 시스템 개발을 위한 연구가 많이 수행되고 있다. 자동화 기술 적용시 효과가 높은 공종 중에서 건설기계의 의존도가 높고, 건축 및 토목공사에서 기본 공종인 토공을 대상으로 연구가 진행되어 왔다. 공사현장의 모델을 구축하여 자동화 시스템이 토공계획을 수립할 수 있는 기술과 단일 건설장비가 주어진 정보와 환경을 인지하여 작업을 수행할 수 있도록 하는 기술이 개발되었다. 자동화 토공시스템이 현장에 적용되기 위해서 해결되어야 할 문제들이 여전히 많이 있지만, 그중에서 중요한 한 가지가는 다수 및 다종의 건설장비들이 협업작업을 수행할 수 있도록 하는 기술을 제공해야만 하는 것이다. 본 연구에서는 사람들의 협업시스템과 의사결정 방법을 모방한 건설시공 시스템을 개발하는 것을 목표로 하고 있으며, 시스템 개발을 위하여 인공지능 분야에서 사용하고 있는 멀티에이전트 개념을 적용하였다. 멀티에이전트 기반 시스템 개발을 위하여 에이전트의 구성과 기능을 제안하고 있으며, 에이전트간 협업 및 중재를 위한 프레임워크를 제시하였다. 그리고 투입되는 건설장비인 다수의 굴삭기와 다짐장비의 효율적인 진로계획과 협업작업시 간섭효과의 최소화 및 중복작업 방지를 위한 방안도 제시하였다. 아직은 이론적인 개념을 제시하고 있는 단계로 가상 시뮬레이션에 의하여 효과를 검증하고 있으나, 추후에는 물리적인 시스템의 구축을 통하여 현장에 적용하기 위한 실증연구를 수행해야 할 것이다.

A number of studies have been conducted recently regarding the development of automation systems for the construction sector. Much of this attention has focused on earthwork because it is highly dependent on construction machines and is regarded as being basic for the construction of buildings and civil works. For example, technologies are being developed in order to enable earthwork planning based on construction site models that are constructed by automatic systems and to enable construction equipment to perform the work based on the plan and the environment. There are many problems that need to be solved in order to enable the use of automatic earthwork systems in construction sites. For example, technologies are needed for enabling collaborations between similar and different kinds of construction equipment. This study aims to develop a construction system that imitates collaborative systems and decision-making methods that are used by humans. The proposed system relies on the multi-agent concept from the field of artificial intelligence. In order to develop a multi-agent-based system, configurations and functions are proposed for the agents and a framework for collaboration and arbitration between agents is presented. Furthermore, methods are introduced for preventing duplicate work and minimizing interference effects during the collaboration process. Methods are also presented for performing advance planning for the excavators and compactors that are involved in the construction. The current study suggests a theoretical framework and evaluates the results using virtual simulations. However, in the future, an empirical study will be conducted in order to apply these concepts to actual construction sites through the development of a physical system.

정보화 시대의 요구에 대한 교육적 대응은 학습자중심의 교육이며, 정보통신 기술을 기반으로 한 원격 교육이다. WBI(Web Based Instruction)는 웹을 매체로 활용하여 원거리에 있는 학습자를 교육시키는 형태로서 교수자와 학습자간 상호작용을 가능하게 하고, 다양한 형태의 학습 자료를 제공하며, 공간적 제약을 극복할 수 있다는 장점이 있다. 차세대 웹 표준문서 포맷으로 부상되고 있는 XML(eXtensible Markup Language)을 사용한 규격에 대한 국내외적인 표준화 작업이 가속화되고 있으며, 최근 XML 보안에 대한 연구가 활성화 되고 있다. XML 보안은 XML 엘리먼트 암호화, XML 전자서명, XML 접근제어 등으로 분류되는데 특히 XML 전자서명은 XML문서를 이용하는 여러 분야에 사용되어 전자서명 시스템간의 상호 연동성을 높일 수 있다. 본 논문에서는 웹상에서 사용되어지는 공인인증서에 대한 사용자의 ID, PW로 인한 보안적 측면을 고려한 방법으로 XML 전자서명 기법을 이용한 다중인식 원격교육 에이전트 시스템을 제안 하였다.

Internet becomes absolutely necessary tools due to rapid progress of information technology. Educational correspondence about an age of information demand is focused on a learner and remote education based on information technology WBI(Web Based Instruction) is a formation that remotly educate a learner using web, possible mutual reaction between instructor and learner, submit various studying material, has a good point to overcome spatial restriction. Internal and external standardization working is accelerated and recently XML security studies are activated using XML which is next generation web standard document format. In this paper, we propose multi-Certification of agent system using XML digital signature to satisfy security requirement.

다중 에이전트 강화 학습(Multi-Agent Reinforcement Learning, MARL)은 에이전트가 시행착오를 통해 최적 의 정책을 상호 작용하고 학습하는 기계학습의 한 분야로, 여러 에이전트가 동시에 동일한 환경에서 상호 작용하고 학습하는 복잡한 시나리오를 처리한다. 이러한 복잡한 상호작용을 분석하고 이해하기는 어려운 일이며, 기존의 분석 방법으로는 이러한 복잡성을 충분히 분석에 반영하고 해석하는 데 한계가 있다. 이러한 문제를 해결하기 위해 우리 는 MARL 환경에서 에이전트의 정책과 상호작용을 시각화하고 분석할 수 있는 시각화 시스템인 MARLViz를 제공 한다. 이 시스템은 다양한 환경에서의 에이전트를 산점도로 나타내어 행동 차이를 요약적으로 보여주고 에이전트의 행동 패턴을 공간상에 시각화하는 열지도를 통해 사용자가 에이전트 간 복잡한 상호작용 패턴을 이해하고 비교할 수 있도록 설계되었다. 또한, MARLViz를 통해 에이전트들의 행동을 이해하기 위한 과업 수행을 효과적으로 수행할 수 있음을 보이기 위해 대표적인 분석 시나리오를 사례 연구의 형식으로 제시한다.

Multi-Agent Reinforcement Learning (MARL) is a subfield of machine learning in which agents interact and learn optimal policies through trial and error in a shared environment, handling complex scenarios where multiple agents interact simultaneously. Analyzing and understanding these intricate interactions is a challenging task, and existing methods often fall short of adequately capturing and interpreting this complexity. To address this issue, we present MARLViz, a visualization system designed to visualize and analyze agent policies and interactions in MARL environments. MARLViz represents agents in various environments using scatterplots to provide a summary of behavioral differences and visualizes agents' behavioral patterns on a spatial heatmap, enabling users to understand and compare complex interaction patterns among agents. Furthermore, we demonstrate the effectiveness of MARLViz in comprehending agents' behavior through a case study, showcasing its capability in facilitating the understanding of task performance in MARL environments.

대형 언어 모델의 발전으로 코드 자동 생성뿐만 아니라 코드 리팩토링까지 자동화하려는 시도가 활 발히 이루어지고 있다. 그러나 단일 모델이 전체 리팩토링 과정을 처리하는 방식은 구조적 한계와 기 능 보존의 어려움을 가지는 문제를 야기한다. 본 논문은 이러한 문제를 해결하고자 역할 분담형 멀팉 에이전트 구조를 기반으로 한 코드 리팩토링 자동화 시스템을 설계하고 구현하였다. 각 에이전트는 분 석, 수정, 검증, 리뷰를 독립적으로 수행하며, 실제 리팩토링 과제를 통해 자동화 흐름과 품질 평가 체 계를 구성하였다.

본 연구는 ChatGPT-4o, 역할 기반 멀티 AI(Artificial Intelligence, 인공지능) 에이전트, RAG(Retrieval- Augmented Generation, 검색기반 증강생성) 구조를 결합한 주식 투자 분석 자동화 시스템을 구현하였다. 재무ㆍ비재무 데이터, 뉴스 감성, 산업 경쟁력, ESG(Environmental, Social, and Governance) 정보를 실시간 수집․분석하여 해석 가능한 투자 보고서를 생성하는 것이 목표이다. 본 연구 시스템은 DART(Data Analysis, Retrieval and Transfer System, 전자공시시스템), 한국은행 ECOS(Economic Statistics System, 경제통계시스템), Google News & Finance API(Application Programming Interface, 응용 프로그램 인터페이스)와 연동하여 데이터 수집을 자동화하고, 11종 AI 에이전트를 통해 계획 수립, 분석, 예측, 종합 판단을 수행한다. 머신러닝 예측과 LLM(Large Language Model, 대규모 언어 모델) 기반 설명을 결합해 블랙박스 모델의 해석 한계를 보완하였다. 실험 결과, 분석 계획부터 최종 보고서 작성까지 전 과정이 자동화되었으며, 통합 분석 결과는 실제 투자 판단에 활용 가능함을 확인하였다. 본 연구는 금융 AI 분야에서 실시간․설명가능․자동화 분석 프레임워크를 제시하며, 투자자문․로보어드바이저 ․IR(IR(Investor Relations, 투자자 관계) 지원 등 다양한 분야에 적용 가능하다.

This study implemented an automated stock investment analysis system combining ChatGPT-4o, role-based multi-AI (Artificial Intelligence) agents, and a RAG (Retrieval-Augmented Generation) framework. It aims to collect and analyze financial/non-financial data, news sentiment, industry competitiveness, and ESG (Environmental, Social, and Governance) information in real time, producing interpretable investment reports. The system integrates with DART(Data Analysis, Retrieval and Transfer System) similar to the U.S. SEC(Securities and Exchange Commission), Bank of Korea ECOS(Economic Statistics System), and Google News & Finance API (Application Programming Interface) for automated data retrieval. Eleven AI agents perform planning, analysis, prediction, and integrated judgment. Machine learning models are combined with LLM-based explanations to overcome black-box interpretability limits. Results show the system automates the entire process from planning to final report generation, and the integrated analysis is applicable to investment decision-making. This research offers a real-time, explainable, automated framework for financial AI, with potential uses in investment advisory, robo-advisors, and corporate IR (Investor Relations) support.

Coupling strength represents the interaction intensity between individuals, which is likely to affect both the convergence and stability properties of multi-agent system. In this paper, a coupling strength based approach is proposed to study the internal interaction mechanisms of multi-agent system. Inspired by the interaction behaviors of biological flocks, three factors, including position, velocity and number of neighbors, are first proposed to generate its relationship with interaction intensity. Then, coupling strength is analytically constructed by synthesizing these factors. Finally, two different cases, with both fixed and varying coupling strength, are simulated to illustrate the effectiveness of the proposed coupling strength in flocking control applications. Moreover, the effects of each factor on flocking are extensively studied.

The rapid and widespread construction of structures calls for rigorous structural health monitoring (SHM) programs throughout the construction, operation and maintenance phases. Thus, much of a structure’s success or failure depends upon efficient SHM programs. The basic technology underlying the SHM program’s ability to detect cracks and failures can be incorporated with Wireless Sensor Network technology for more robust SHM. The agility of the WSN is, therefore, a prominent factor for a successful SHM program. Unpredictable external events, such as earthquakes or serious impacts are an inevitable fact of life. During such an event, the WSN should continue to be active and efficient enough to perform the assigned tasks without failure. The never miss an opportunity scheme (NMAOS) model, which is a prototype based on multi-agent technology, is proposed in this paper to provide agility to the Wireless Sensor Network.

Hadith is everything attributed to Prophet Muhammad Peace Be Upon Him (PBUH) such as says, deeds, explanations, decisions or characteristics of his creation. Each Hadith is composed of two main parts: Isnad and Matn. Isnad processing is one of the unique features of Islam nation, which concentrates on the narrations of the prophet. Before 1400 years, Hadith scholars set the rules and wrote the books to distinguish between the right narrations that really related to the prophet and the lied one. All Hadiths are texts written in Arabic classical language. Processing the Arabic language is a difficult task due to the specificities of this language and the scarcity of the digital resources (grammars, lexicon and corpus). In this paper, we suggest a method for Hadith Isnad processing based on the Multi-Agent approach. We designed and implemented a system composed of five agents, which are: preprocessing agent, lexical agent, morphological agent, replacing agent and syntactical agent. These agents cooperate to analyze Hadith Isnad and to provide the parse tree, Isnad tree and the received method. This system is based on a large database that we created using XML technology to ensure the re-usability, the scalability and the interoperability.

To reveal how the ancient kiln has evolved along DongHe River Basin in Jingdezhen –Jiangxi Province of China, and further reflect the interaction of the political situation, the institutions and the natural environment, we create ancient virtual maps of study area and propose such constructs to unambiguously denote a integration system by combining the advantages of multi-agents, PSO and CA in time and space. We apply the system to model a dynamic interaction environment and conduct a series of spatial analyses of the land-use pattern from 1271 to 1554. Compared with model PSO-CA, the simulation result of this new model is of richer changing hierarchy and can better reflect the whole process from the first to the last firing. Meantime, the index Moran's I of simulation using the hybrid method is much closer to the actual Moran's I, which can better reflect the interaction between political environment and natural environment of different dynasties with the lack of ancient GIS spatial data.

The multi-agent systems (MAS) have become a very powerful paradigm in the development of complex computer systems. The modeling of these systems can reduce this complexity during the development phases. The Model-Driven Architecture (MDA) approach can be used to resolve this problem. It allows designers to model their systems at different abstraction levels, providing them with automatic model transformations to incrementally refine abstract models into concrete ones. This paper presents a MDA approach to develop multi-agent system with the derivation of the behavior of a given system agent from its global requirements. The suggested approach is based on the definition of an appropriate requirements meta-model (Computational Independent Meta-Model CIMM) and the definition of a target design meta-model (Platform Independent Meta-model PIMM). The CIM models are specified using UML activity diagram extended with collaborations to describe the system global behavior. The agent’s behavior model (PIM) is in the form of distributed UML state machines. Automatic model transformations between these two models have been designed in order to govern the derivation process. A real application of telediagnosis in neuroscience has been developed using this approach.

Multi Agent System (MAS) is an assembly of autonomous, proactive and dynamic entities called agents. These agents provide some service once an event is invoked. By providing the designated service the MAS achieves a specific goal. A logic based formal analysis of MAS is necessary to understand the system, its structure and dynamics. A systematic and sequential methodology is used for analysis of MAS. As a result of analysis several constructs in form of templates is obtained to represent the different facets of MAS. This is extremely necessary as it allows to explicitly identify how agents directly or indirectly interact or coordinate and collaborate with each other. This paper proposes an Architectural Design Language called Agent Description Language (ADL) that will be required to map these analysis templates to the design phase. Establishing the correctness of the structural transformation and correspondence from analysis to design phase constitutes the other side of the proposal. The proposed ADL has been used to get the corresponding classes of the templates generated. Jason, the universal MAS programming language has been used to implement the ADL classes to get the logical design which conforms to the conceptual design phase. The case study of Medical Emergency Service (MES) has also been taken to illustrate the proposals and findings.

In recent years Agent technology has had a significant growth in all fields, especially in the field of E-health. Agent-oriented software engineering based on agent-oriented methodology is a novel phenomenon in the field of software engineering, which nowadays, is used in the production of distributed systems. The special features of agent such as intelligence and autonomy, cause reduction in running costs and performing automatic functions in some systems like electronic health which have been implemented by Agent technology. Using New communication technologies, distributed systems and intelligent Agents are also considered as a novel phenomenon in medicine. This paper aims to analyze the Agent-oriented Software engineering, Agent Oriented Programming, Multi Agent System as well as providing agent-based system for the hospital by the utilization of agent characteristics.

Satellite network is the essential part of the future generation of hybrid communication networks. Considering the surging demands for multimedia traffic across the globe, the dynamic time-varying topology of low earth orbit (LEO) satellite network and the flaws of existing QoS (Quality of Service) routing algorithms, a novel QoS routing algorithm applying multi-agent system (MAQR) for LEO satellite network is proposed in this paper. The algorithm design three types of mobile agents: node management agent (NMA), active perception agent (APA) and executive agent (EA). NMA adaptively perceives external environment and deals with traffic request and controls routing. APA is responsible for collecting information of non-local satellite nodes and links. EA is in charge of path maintenance and update. MAQR algorithm introduces link duration into a cost function and then minimizes the cost function to find optimum paths that simultaneously satisfy delay and bandwidth constrains. Besides, when current QoS path is deteriorated, new QoS path can be discovered without rerouting. Simulation results show that MAQR algorithm not only has lower call blocking probability and handover call dropping probability, but takes both routing efficiency and algorithm overhead into account as well.