How to Do Things With Words

An Introduction to MultiAgent Systems.

Today, the need for architectures and computational models for large-scale open multi-agent systems is considered to be a key issue for the success of agent technology in real-world scenarios. This paper analyzes the significant unsolved problems that must be taken into account in order to develop real, open multi-agent systems. It identifies requirements and related open issues, discusses how some of these requirements have been tackled by current technologies, and explains how the THOMAS architecture is able to give support to these open issues. This paper also describes the THOMAS abstract architecture and computational model for large-scale open multi-agent systems based on a service-oriented approach that specifically addresses the design of virtual organizations. An application example for the management of a travel agency system, which demonstrates the new features of the proposal, is also presented.

An abstract architecture for virtual organizations: The THOMAS approach

Industrial Agents explains how multi-agent systems improve collaborative networks to offer dynamic service changes, customization, improved quality and reliability, and flexible infrastructure. Learn how these platforms can offer distributed intelligent management and control functions with communication, cooperation and synchronization capabilities, and also provide for the behavior specifications of the smart components of the system. The book offers not only an introduction to industrial agents, but also clarifies and positions the vision, on-going efforts, example applications, assessment and roadmap applicable to multiple industries. This edited work is guided and co-authored by leaders of the IEEE Technical Committee on Industrial Agents who represent both academic and industry perspectives and share the latest research along with their hands-on experiences prototyping and deploying industrial agents in industrial scenarios.Learn how new scientific approaches and technologies aggregate resources such next generation intelligent systems, manual workplaces and information and material flow systemGain insight from experts presenting the latest academic and industry research on multi-agent systemsExplore multiple case studies and example applications showing industrial agents in a variety of scenariosUnderstand implementations across the enterprise, from low-level control systems to autonomous and collaborative management units

Industrial Agents: Emerging Applications of Software Agents in Industry

In many settings Web services are now perceived as the first choice technology to provide neatly encapsulated functionality for Web-based computation. To date, many standards have been produced and adoption is accelerating across numerous application domains. This uptake has long been recognized by members of software agent community with several approaches reported that explore various means of extending the utility of Web services with the autonomous control offered by agents. This paper reports on the recent work of several members of this community to consolidate their approaches into a common specification describing how to seamlessly interconnect FIPA compliant agent systems with W3C compliant Web services. This work has been conducted within the context of the IEEE FIPA Agent and Web Service Integration working group and will be shortly published as a new FIPA specification.

The IEEE FIPA approach to integrating software agents and web services

Web services framework has been evolved in context of convergence of Web and service oriented computing and then to Web services resource framework acting as basis for grid computing. It provides a loose coupled and implementation neutral infrastructure for distributed applications. On the other hand, multi agent systems has evolved as distributed system in context of autonomic computing having ultimate aim of self-managing systems to overcome their rapidly growing complexity and to enable their further growth. In this paper, we present our solution for dynamic and seamless integration of type the distributed systems. It would help in facilitating the requirements of next generation distributed applications requiring higher demands and complexity. The AgentWeb Gateway acts as middleware between both the technologies for dynamic integration and provides protocol transformations including service discovery, service description and service invocation.

AgentWeb Gateway - a middleware for dynamic integration of multi agent system and Web services framework

Disparate types of data including biological and environmental have been used in supervised learning to predict a specific disease outcome. However, social determinants of health, which have been explored very little, promise to be signiﬁcant predictors of public health problems such as malaria and anemia among children. We considered studying their contribution power in malaria and anemia predictions based on Variable Importance in Projection (VIP). This innovative method has potential advantages as it analyzes the impact of independent variables on disease prediction. In addition, we applied ﬁve machine learning algorithms to classify both diseases, using social determinants of health data, and compared their results. Of them all, artiﬁcial neural networks gave the best results of 94.74% and 84.17% accuracy for malaria and anemia prediction, respectively. These results are consistent and reﬂect the signiﬁcance of non-medical factors in disease prediction.

Assessing the relative importance of social determinants of health in malaria and anemia classiﬁcation based on machine learning techniques.

Agents and grid computing are distinct standards each defined by its own specifications. Semantic grid aims at providing semantic annotations for grid entities, WSMO is a language for semantic markup of grid services and provide semantic layer over grid resources. On the other hand, agents are intelligent software entities that can act semantically for interoperation with other agents in MAS. FIPA provides standard for MAS where agents speak FIPA ACL as the communication language while FIPA SL is the semantic language. Both FIPA SL and WSMO differ in terms of syntax, semantics and implementation constraints, which prevents interoperability between agents and grid services. This research addresses the issue of interoperability between FIPA agents and grid services by proposing a communication framework for interoperation; SOA compliant FIPA ACL ontology is developed; that provides the necessary vocabulary that not only adheres to the FIPA specifications but is also used by grid services.

SOA compliant FIPA agent communication language

Autonomous cache-provision agreement for scalability of directory facilitator in MAS

Semantic grid activities havetaken momentumwith theadvancements andresearch inexisting gridandrelated technologies. Software agents havebeendetermined askey resource entities inthesemantic gridvision buttheir role is still ambiguous. Ourapproach isthatsemantics areneeded in gridsforinteroperability betweensoftware agentsat knowledge level. Oneofthemostimportant goals ofsemantic gridistobring seamless automation ingridwhichcanbe visualized asautonomous software agents fulfilling a given agenda ofgoals withleast humanintervention. Incurrent grid scenario, duetolackofsemantics, agents cannotunderstand services whichdrastically affects thenegotiation, coordination andcooperation capabilities toformvirtual organizations. Hencesemantics arehighly desirable soastoactasacatalyst toenhance thecapabilities ofsoftware agents inorder tobring seamless automation ingrid. Ourcontribution inthepaperis to identify theresearch issues and theirsolutions to incorporate thecapabilities ofsoftware agents that canhelp in achieving semantic grid goals.

Hiroki Suguri

Papers

AgentWeb Gateway - a middleware for dynamic integration of multi agent system and Web services framework

Assessing the relative importance of social determinants of health in malaria and anemia classiﬁcation based on machine learning techniques.

SOA compliant FIPA agent communication language

Autonomous cache-provision agreement for scalability of directory facilitator in MAS

Role of SoftwareAgents inrealizing Semantic Grid