Alfonso Bosch

Reasoning with disjunctive fuzzy temporal constraint networks

The disjunctive fuzzy temporal constraint network (DFTCN) model is a framework that allows reasoning with fuzzy qualitative and quantitative complex temporal constraints. However, its general complexity is exponential. In this work, we review methods that can reduce this complexity, based on graph topology and preprocessing. The final goal is to integrate all these methods into a general tool for temporal reasoning with DFTCN.

An Intelligent System for Therapy Control in a Distributed Organization

This paper describes a decision-making system for phytosanitary control advicing. The solution adopted consists of developing a Web-accessible information system based on a multi-agent architecture, integrating knowledge-based techniques and classical information analysis and management techniques. CommonKADS was used for the design of some knowledge-based agents. Internet implementation and integration was done in a knowledge-based system implementation environment, with programs executed on the Web server.

Knowledge Model of a Therapy Administration Task – Applied to an Agricultural Domain

This work presents an application of the CommonKADS methodology to define of a knowledge model for a therapy admini- stration task, reusing CommonKADS task templates. A knowledge- based system for solving the problem of phytosanitary strategy selec- tion in greenhouses has been constructed using this knowledge model. As a result, we have defined a therapy administration task template that can be reused to construct additional knowledge models for other knowledge-based systems.

A proposal for Projekt Management Using CommonKADS

This work describes a proposal for software lifecycle and project management when developing knowledge based systems using CommonKADS methodology. To build this proposal, an analysis of the similarities between software engineering and knowledge engineering was made. As a result, the anchor point milestones and the invariant definitions from the spiral model lifecycle for software development have been translated to CommonKADS methodology. This proposal is being applied to a project in order to develop a phytosanitary advisor system used by farmers in greenhouse crops.

Temporal Approaches in Data Mining. A Case Study in Agricultural Environment

In this work we present an study of the application of data mining techniques in an interesting domain, the Integrated Control. We found that in this dynamic domain, non-temporal data mining techniques are not suitable, needing to find a good temporal model. After a comparative study of several candidate models, we propose the use of the inter-transaction approach.

Series-Parallel and Tree-Decomposition Approaches for Fuzzy Constraint Networks

In this work, we present a Disjunctive Fuzzy Constraint Networks model for continuous domains, which generalizes the Disjunctive Fuzzy Temporal Constraint Networks model for temporal reasoning, and we propose the use of the series-parallel and tree-decomposition approaches for simplifying its processing. After a separate empirical evaluation process of both techniques, a combined evaluation process over the same problem repository has been carried out, finding that series-parallel problems practically subsume tree-decomposable problems.

An abductive method for solving a treatment problem

The work analyzes a therapy planning problem in an agricultural domain in which where there are no standard treatment protocols. For this reason, the skeletal planning method cannot be applied, and the use of an abductive method is therefore proposed. This work is part of a broader project, the main goal of which is the development of a knowledge based system for phytosanitary advice. For this knowledge based system, the CommonKADS methodology has been selected. In order to apply the method, we present a general formalization of therapeutic problems that is domain independent, and afterwards we show how to find solutions for this problem using a treatment task decomposition.