Catálogo de publicaciones - libros

In this paper we introduce , a novel software utility for developing context-aware services, editing and deploying context situation models, and simulating perceptual components. , which stands for , is constructed as an open and extensible framework with rich graphical rendering capabilities, including 3D visualization. One of ’s main goals is to simulate interactions among people and objects in various settings such as presentation rooms, meetings halls, social places, homes, or car cockpits. Moreover, captures and models such environmental context and delivers the abstracted information to context-aware user services. Contextual models are designed as pluggable modules. They can be configured to build hierarchies of contextual models and deployed and reused across applications, agent systems or cognitive architectures. allows plugging-in various multi-modal sensing components such as body trackers, face detectors, speech recognition engines, gesture recognizers, etc. Therefore, switching from simulated to real components with is seamless, typically involving no change in the contextual models and the services.

This paper discusses an ontology-based reconfiguration agent that uses ontological knowledge of the manufacturing environment for the purpose of reconfiguration without human intervention. The current mass customization era requires increased flexibility and agility in the manufacturing systems to adapt changes in manufacturing requirements and environments. Our configuration agent minimizes the overheads of the current reconfiguration process by automating it. It infers facts about the manufacturing environment from the ontological knowledge model and then decides whether the current environment can support the given manufacturing requirements.

Cohesion and coupling are standard concepts in computer science. As in classic software, multi-agent systems (MASs) strive for high cohesion and low coupling. But MASs, by definition, do have some coupling, i.e., the agents seek out and discover other agents, and negotiate and cooperate with them, to accomplish some overall goal. Moreover, as different events occur, and different agents and different agent behaviors are called upon, the coupling values for the system change. This paper proposes a methodology for viewing these changing coupling relationships and clustering behaviors. In addition, the methodology is described as implemented as part of a standard agent monitoring tool.

FIPA-compliant agent platforms must include an Agent Management System, an Agent Communication Channel and a Director Facilitator (DF). The DF is centralized and it administers a register of agents which previously had been registered. Every agent could perform a search for an agent(s) that has specific characteristics or provides a determined service. A centralized DF is a potential point of failure and could cause network overload. The DFs could be distributed through the networked embedded controllers. This paper describes the development of a Distributed Director Facilitator (DDF) which keeps a local register of service providers including the name of the agents and the services provided, this means that every controller could have its own DDF, and agents hosted within a controller could query over the list of service providers.

While the need to build the Intrusion Detection Systems (IDS) based on on a distributed and cooperative (P2P) paradigm is being generally acknowledged, the field has been disconnected from the recent advances in the multi-agent research, most notably the field of trust modeling. Our contribution reviews recent implementations of IDS systems and presents them from an agent research perspective. We also identify the opportunities where the agent approaches can be successfully used. Agent techniques can make the IDS more adaptive, scalable and reliable while increasing their autonomy and reducing the maintenance requirements. Besides trust modeling, we propose that the distributed decision-making and planning techniques can be used to shorten the detection-response loop, making the system more robust while facing worm attacks.

We present a formal approach to conception of a dedicated security infrastructure based on the exception handling in the protected agents. Security-related exceptions are identified and handled by a dedicated reflective layer of the protected agent, or delegated to specialized intrusion management agents in the system if the local reflective layer fails to address the problem. Incidents are handled either directly, if a known remedy exists or indirectly, when an appropriate solution must be identified before response execution. The cooperation between the intrusion management agents and aggregation of their observations can make the system more resilient to misclassification than a solution based purely on signature matching.

In this paper we propose a new, smart strategy for efficient caching of user-defined software agents. The strategy is based on setting up minimum and maximum caching time for individual agents. These timings are formed on the basis of a way of calling an agent (type of input/output gateway serving a call, previous calls to the same agent, etc.), on the one hand, and past/current/ predicted system load, including waiting calls to be served in the near future for the same and other agents, on the other hand. As proven by the tests in real applications, the strategy is efficient, especially in the case of a mass-scale system with thousands and even millions of agents owned (and possibly programmed) by different users.

This paper addresses and introduces an overview on various multi-agent architectures applied to teams of metaheuristic agents for job shop scheduling applications, whose developed and examined on distributed problem solving environments. We reported a couple of topologies; ATEAM is a centrally coordinating method, which provides very good results when well-studied, on the other hand, architectures based on peer-to-peer technology provide wider flexibility in implementing various fashions. The experimentation for each targeted topology has revealed more details and attracts more attentions.

Making a production system readily reconfigurable in a bid to adapt to very fluid demand profile is pertinent to cost reduction and facility utilization objectives of the system. We consider a production scheduling methodology based on federated agent architecture designed for a flexible job shop with dynamic demand. The interaction protocol within the social network is based on a facilitated auction mechanism. This model employs competition at job centers to maximize financial returns and uses cooperation among facilitator agents to minimize weighted tardiness.

This paper deals with a real-time scheduling system of the holonic manufacturing systems (HMS). In the previous papers, real-time scheduling processes based on the utility values have been proposed and applied to the HMS. A simulation based procedure has also been implemented to estimate the future status of HMS and to determine the utility values aiming at improving scheduling method. However, it was assumed that only one holon in the HMS carries out the estimation for the ease of the estimation process. A simulation based real-time scheduling method is newly proposed, in the paper, to improve the estimation process which enable all the holons to estimate the future status of the HMS. An estimation process is developed for the individual holons to estimate the future status of HMS through the simulation. Some case studies of the real-time scheduling are carried out to verify the effectiveness of the proposed method.