Francesco Agostaro

A conversational agent based on a conceptual interpretation of a data driven semantic space

In this work we propose an interpretation of the LSA framework which leads to a data-driven “conceptual” space creation suitable for an “intuitive” conversational agent. The proposed approach allows overcoming the limitations of traditional, rule-based, chat-bots, leading to a more natural dialogue.

A Collaborative Environment for Service Providing in Cultural Heritage Sites

We present a model which can be used to describe hybrid entities in an augmented reality environment. An architectural description of the model is firstly given. Next, a FIPA-compliant agent description of the model is proposed. Finally the paper discusses an overview and some implementation details of a project dealing with Augmented Reality context aware services in a cultural heritage site. These services are provided based on visitors customized profiles and current position in the site, as revealed by a positioning site implemented with low cost Bluetooth devices (cellular phones, PDAs, USB terminals).

Mobile agents, globus and resource discovery*

Publisher Summary This chapter discusses grid technology and some related problem. The overview of grids, in terms of application fields and needed protocols is given. The common feature of all grid architectures is a coordinated and controlled resource sharing between the members of a dynamic multi-institutional virtual community. The members of such a community agree on which resources will be shared and which members of the community will be enabled to access these resources, thus defining a set of sharing rules and permissions. The Globus project is discussed, which is nowadays the de facto standard for grid environments, with emphasis on its resource discovery components. Finally, the chapter discusses resource discovery as an application of the mobile agents paradigm and show how this approach can be used for general, scalable, and multi-purpose resource search and location.

Mobile agents and grid computing

Publisher Summary This chapter describes mobile agents as an effective solution for grid service provision. A short overview is first introduced on the grid paradigm and the most known research activities in the field. Then, mobile agents are discussed and a comparison with the remote procedure call (RPC) method is made as far as the most effective solution to minimize network overload and fault occurrences is concerned. The common feature of all grid architectures is a coordinated and controlled resource sharing between the members of a dynamic multi-institutional virtual community. Community members agree on a set of sharing rules and permissions, by which resources to be shared and members to be enabled to access these resources, can be defined. Resource sharing can take place by using suitable protocol architecture for interoperability. The resources to be shared in a grid environment can be both physical resources and services being a service a network enabled entity, which provides some capability. In a service-oriented view, interoperability can be achieved by a standard way of defining service interfaces and protocols to be used for service invocation.

Mobile agent application fields

Publisher Summary Mobile agents are a recent paradigm for software design, which extends object oriented programming features. An agent can perform its task autonomously; a mobile agent can carry out complex tasks that require the agent to migrate from a network place to another one. Mobile agent application fields are many. It can replace web services in other cases, mobile agents and web services can be an effective solution together. The chapter discusses the three mobile agent application fields, which are: parallel and distributed computing, data mining and information retrieval, and networking. An overview of the development platforms is also discussed. Data mining and information retrieval systems often rely on centralized management. According to this approach, data are collected from remote sources to one central host, thus rising network load and communication cost. Mobile agents provide remote resources local access capabilities; hence, they are an interesting option for data mining and information retrieval system design. A mobile agent approach reduces data collection from remote sites and therefore also reduces communication costs.