Radical Agent-Based Approach for Intelligence Analysis

2004

Abstract. The Web offers a huge amount of valuable information, but it is very hard and time consuming for humans to retrieve thousands of web pages related to a concept, filter the relevant ones, analyse this information and integrate it in some knowledge repository. A Knowledge Management Platform that performs these tasks has been developed in the hTechSight IST project.

2011

AOIS is a multi-agent system that supports the sharing of information among a community of users connected through the Internet. In respect to Web search engines, this system enhances the search through domain ontologies, avoids the burden of publishing the information on the Web and guaranties a controlled and dynamic access to the information. The use of agent technologies has made the realization of three of the main features of the system straightforward: i) filtering of information coming from different users, on the basis of the previous experience of the local user, ii) pushing of new information that can be of interest for a user, and iii) delegation of access capabilities, on the basis of a reputation network, built by the agents of the system on the community of its users.

Proceedings of the 2nd International Conference on Web Intelligence, Mining and Semantics - WIMS '12, 2012

The Semantic Web aims at augmenting the WWW with meaning, assisting people and machines in comprehending Web content and better satisfying their requests. Intelligent agents are considered to be greatly favored by Semantic Web technologies, because of the interoperability the latter will achieve. As a result, a plethora of multi-agent systems is already in use. One of the main problems in these systems is the lack of sufficient discovery and interaction monitoring tools. This paper reports on the design and implementation of advanced agent discovery services. These services are distinguished in two main categories; namely advanced semantic directory and discovery services (yellow pages) and trust-based discovery services which support among others interaction monitoring tools. Their implementation, including the associated graphical interface, was integrated into the EMERALD framework, a knowledge-based framework for interoperating agents. Finally, a software trade use case scenario is presented, which better displays the potential of the proposed approach.

A Semantic Web Perspective, 2005

In this chapter, we approach some significant concepts consistent with knowledge and cognitive processes that are essential for any kind of contemporary organization. Therefore, after citing a generic approach to knowledge management and its facilitating tools, along with a description of software agents and their categories, we indicate precious elements and details for the prerequisites while designing and implementing such intelligent solutions. As prerequisites, we deem organizational context, programming, and developing tools. We then discuss collaborative agent systems, known as agent societies, and present some appealing implementations of complex agent systems. Finally, we portray some of our thoughts regarding the perspective of employing smart agent technology in our everyday life.

2005

In the past, database searches have focused on the relatively static environments of centralized and distributed enterprise databases. In these environments, informa-tion is centrally managed and the structure of data is consistent. Today, however, information critical to TRW customers is usually derived from a variety of sources that may be distributed over a vast geographic area. The access media is most likely through the Internet, an intranet, or some private network where information may be stored in online databases, legacy databases, or the World Wide Web. Most current solutions require the development of ad hoc software to handle these complex network and database environments. Such approaches are costly and lack reusability. A better approach to satisfy these needs is to utilize an infrastructure that employs a dynamic, intelligent agent-based architecture, with agent commu-nication, data fusion and mining, and the capability to resolve semantics over heterogeneous data sou...

Information Fusion, 2010

… Systems (AOIS-2002 at AAMAS* 02), …, 2002

Web retrieval is now one of the most important issues in computer science, and we believe that applying multi-agent systems to this area is a promising approach. We introduce Kodama 1 system, which is being developed and in use at Kyushu University, as a multi-agent-based approach to build a distributed Information Retrieval (IR) system that lets users retrieve relevant distributed information from the Web. We reported methods to agentify the Web, and to cluster the agentified domain into communities. In order to investigate the performance of our system, we carried out several experiments in multiple Server Agent domains and developed a smart query routing mechanism for routing the user's query. The results ensure that the idea of Web page agentification, clustering and routing techniques promise to achieve more relevant information.

International Joint Conference on Artificial Intelligence, 2003

In the Web, extractor agents process classes of pages (like 'call for papers' pages, researchers' pages, etc), neglecting the relevant fact that some of them are interrelated forming clusters (e.g., science). We propose here an architecture for cognitive multi-agent systems to retrieve and classify pages from these clusters, based on data extraction. To enable cooperation, two design requirements are crucial: (a) a Web vision coupling a vision for contents (classes and attributes to be extracted) to a functional vision (the role of pages in information presentation); (b) explicit representation of agents' knowledge and abilities in the form of ontologies, both about the cluster's domain and agents' tasks. Employing this Web vision and agents' cooperation can accelerate the retrieval of useful pages. We got encouraging results with two agents for the page classes of scientific events and articles. A comparison of results to similar systems comes up with two requirements for such systems: functional categorization and a thoroughly detailed ontology of the cluster.

Computational & Mathematical Organization Theory, 2004

Collective intelligence is defined as the ability of a group to solve more problems than its individual members. It is argued that the obstacles created by individual cognitive limits and the difficulty of coordination can be overcome by using a collective mental map (CMM). A CMM is defined as an external memory with shared read/write access, that represents problem states, actions and preferences for actions. It can be formalized as a weighted, directed graph. The creation of a network of pheromone trails by ant colonies points us to some basic mechanisms of CMM development: averaging of individual preferences, amplification of weak links by positive feedback, and integration of specialised subnetworks through division of labor. Similar mechanisms can be used to transform the World-Wide Web into a CMM, by supplementing it with weighted links. Two types of algorithms are explored: 1) the co-occurrence of links in web pages or user selections can be used to compute a matrix of link strengths, thus generalizing the technique of "collaborative filtering"; 2) learning web rules extract information from a user's sequential path through the web in order to change link strengths and create new links. The resulting weighted web can be used to facilitate problem-solving by suggesting related links to the user, or, more powerfully, by supporting a software agent that discovers relevant documents through spreading activation.