Catálogo de publicaciones - libros

Set-valued Information Systems(SVISs) are generalized forms of Crisp Information Systems(CISs) and common in practice. This paper defines a fuzzy inclusion relation in Fuzzy Set-valued Information Systems(FSVISs). By means of two parameters of inclusion degree and , we define the rough sets in FSVISs, which are used to approximate fuzzy concepts in FSVISs. Furthermore, in terms of the maximum elements in the lattice derived from the universe according to decision attributes, we present the definitions and measuring methods of decision rules in FSVISs. Some examples have been given for illustration.

Although undirected cycles in directed graphs of Bayesian belief networks have been thoroughly studied, little attention has so far been given to a systematic analysis of directed (feedback) cycles. In this paper we propose a way of looking at those cycles; namely, we suggest that a feedback cycle represents a family of probabilistic distributions rather than a single distribution (as a regular Bayesian belief network does). A non-empty family of distributions can be explicitly represented by an ideal of conjunctions with interval estimates on the probabilities of its elements. This ideal can serve as a probabilistic model of an expert’s uncertain knowledge pattern; such models are studied in the theory of algebraic Bayesian networks. The family of probabilistic distributions may also be empty; in this case, the probabilistic assignment over cycle nodes is inconsistent. We propose a simple way of explicating the probabilistic relationships an isolated directed cycle contains, give an algorithm (based on linear programming) of its consistency checking, and establish a lower bound of the complexity of this checking.

In this paper we investigate the effectiveness of applying fuzzy controllers to create strong computer player programs in the domain of backgammon. our proposed mechanism, consists of a fuzzy controller that dynamically evaluates the perceived strength of the board configurations it receives. Fuzzeval employs an evaluation function that adjusts the membership functions linked to the linguistic variables employed in the knowledge base. The membership functions are aligned to the average crisp input that was successfully used in the past winning games. Fuzzeval mechanisms are adaptive and have the simplicity associated with fuzzy controllers. Our experiments show that Fuzzeval improves its performance up to 42% after a match of only one hundred backgammon games played against a strong intermediate level program.

In this paper, a new fuzzy logic-based approach to production scheduling in the presence of uncertain disruptions is presented. The approach is applied to a real-life problem of a pottery company where the uncertain disruption considered is glaze shortage. This disruption is defined by two parameters that are specified imprecisely: number of glaze shortage occurrences and glaze delivery time. They are modelled and combined using standard fuzzy sets and level 2 fuzzy sets, respectively. A predictive schedule is generated in such a way as to absorb the impact of the fuzzy glaze shortage disruption. The schedule performance measure used is makespan. Two measures of predictability are defined: the average deviation and the standard deviation of the completion time of the last job produced on each machine. In order to analyse the performance of the predictive schedule, a new simulation tool FPSSIM is developed and implemented. Various tests carried out show that the predictive schedules have good performance in the presence of uncertain disruptions.

In Multi-agent based simulation (MABS) systems, computational models are built as multi-agent systems (MAS). Replication of these models can contribute to improve the reliability of the results and understanding of the system. One of the main problems for facilitating replication is the lack of a simulation integrated environment that supports the whole research process from conceptual modeling to simulation implementation and analysis. We address this issue providing a high-level conceptual modeling abstraction for simulation development, including transformation tools that facilitate the implementation of simulations on different simulation platforms. In this way, agent-based simulation development process is driven by modeling, because users focus on conceptual modeling, while implementation code is generated automatically.

Communication among agents in swarm intelligent systems and more generally in multiagent systems, is crucial in order to coordinate agents’ activities so that a particular goal at the collective level is achieved. From an agent’s perspective, the problem consists in establishing communication policies that determine , , and to communicate with others. In general, communication policies will depend on the nature of the problem being solved. This means that the solvability of problems by swarm intelligent systems depends, among other things, on the agents’ communication policies, and setting an incorrect set of policies into the agents may result in finding poor solutions or even in the unsolvability of problems. As a case study, this paper focus on the effects of letting agents use different communication policies in ant-based clustering algorithms. Our results show the effects of using different communication policies on the final outcome of these algorithms.

In most practical situations, agents need to continuously improve or repair their plans. In a multiagent system agents also need to coordinate their plans. Consequently, we need methods such that agents in a multiagent system can construct, coordinate, and repair their plans. In this paper we focus on the problem of coordinating plans without exchanging explicit information on dependencies, or having to construct a global set of constraints. Our approach is to combine a propositional plan repair algorithm for each agent with a blackboard that auctions subgoals on behalf of the agents. Both the details of a first construction and some initial experimental results are discussed.

In this paper we propose a framework for controlling and executing problem solving methods in a work-flow context. The framework is founded on an extension and scaling-up of the electronic institutions theory and the use of artificial intelligence techniques in a multi agent environment. We discuss electronic institutions’s theory extensions for enabling intelligent organizations using our approach. As a proof of concept of the proposal we present the prototype of a help-desk information system for assigning advisors and monitoring their performance using artificial intelligence techniques for automated reasoning.

This work describes an application of extended behavior networks to the control of an agent in the game Unreal Tournament. Extended Behavior Networks (EBNs) are a class of action selection architectures capable of selecting a good set of actions for complex agents situated in continuous and dynamic environments. They have been successfully applied to the Robocup, but never before used in computer games. We verify the quality of the action selection mechanism and its correctness in a series of experiments. Then we asses the performance of an agent using an EBN against a plain reactive agent with identical sensory-motor apparatus and against a totally different agent built around finite-state machines. We discuss the results of our experiments, point our future work and conclude that extended behavior networks are a good control mechanism for game agents.

The present document explores how air pollution can be assessed from a multiagent point of view. In order to do so, a traffic system was simulated using agents as a way to measure if air pollution levels go down when the traffic lights employ a multigent cooperative system that negotiates the green light duration of each traffic light, in order to minimize the time a car has to wait to be served in an intersection. The findings after running some experiments where lanes of each direction are congested incrementally showed, that using this technique, there is a significant decrease in air pollution over the simulated area which means that traffic lights controlled by the multiagent system do improve the levels of air pollution.