Session Program


  • 12 July 2017
  • 08:00AM - 10:00AM
  • Room: Normanna
  • Chairs: Jesús Alcalá-Fdez and José M. Alonso

Software for Soft Computing-I

Abstract - This paper presents a toolkit for automatic generation and analysis of fuzzy sets (FS) from data. Toolkits are vital for the wider dissemination, accessibility and implementation of theoretic work and applications on FSs. There are currently several toolkits in the literature that focus on knowledge representation and fuzzy inference, but there are few that focus on the automatic generation and comparison of FSs. As there are several methods of constructing FSs from data, it is important to have the tools to use these methods. This paper presents an open-source, python- based toolkit, named fuzzycreator, that facilitates the creation of both conventional and non-conventional (non-normal and non-convex) type-1, interval type-2 and general type-2 FSs from data. These FSs may then be analysed and compared through a series of tools and measures (included in the toolkit), such as evaluating their similarity and distance. An overview of the key features of the toolkit are given and demonstrations which provide rapid access to cutting-edge methodologies in FSs to both expert and non-expert users.
Abstract - SPARQL has been adopted as query language for the Semantic Web. RDF and OWL have also been established as vocabularies to describe ontologies in this setting. While RDF/OWL/SPARQL have been designed for querying crisp information, some contexts require to manage uncertainty, vagueness and imprecise knowledge. In this paper a SPARQL extension, called FSA-SPARQL (Fuzzy Sets and Aggregators based SPARQL) is proposed, in which queries can involve different fuzzy connectives and (aggregation) operators. The language has been implemented as an extension of the ARQ Jena SPARQL engine and it is equipped with a Web tool from which queries can be executed on-line.
Abstract - Refer4Learning is an application that helps teachers in the early stages of children education to work on basic concepts such as color, size, or position of simple geometric objects. This type of concepts are imprecise by nature and, thus, establishing the correspondence between an expression of natural language that uses these concepts and the reality that is intended to be described is a matter of degree. In this work, we explain how Refer4Learning performs the selection of visual scenes to practice with these concepts through the use of referring expressions, which are noun phrases aimed at identifying a given object within a scene. As we shall see, this is done through the use of a specificity measure together with appropriate fuzzy models to deal with the mentioned basic visual concepts.
Abstract - Since intuitionistic fuzzy sets (IFSs) have been applied to solve problems in topics like decision-making or pattern recognition, the study of similarity measures aiming to compare this kind of fuzzy sets has become a challenging research subject. When proposed, a similarity measure is usually tested to demonstrate its properties and advantages over the others. However, those tests are occasionally performed using a small number of examples that do not allow a researcher or practitioner to detect potential drawbacks. In this paper, an open-source software package whereby a researcher can empirically assess several (configurations of) similarity measures while comparing IFSs that characterize experience-based evaluations is proposed and presented. By means of the proposed package, one can (1) build a large number of IFSs according to different learning scenarios, (2) compare those IFSs using existing or novel similarity measures, and (3) generate a comprehensive report about how each similarity measure reflects a perceived similarity. Reports generated by the package show that only a few of the existing similarity measures reflect properly a perceived similarity when IFSs resulting from opposite learning scenarios are compared to each other.
Abstract - The software presented in this paper is an implementation of an intuitionistic fuzzy inference system. Such type of fuzzy inference systems provide an extra layer of uncertainty, called indeterminacy, that the user can integrate in the antecedents and consequents of the fuzzy system. The additional calculations required to make an inference in this type of system need a negligible extra amount of computational resources, making it a low-cost alternative to type-2 fuzzy inference systems. At the current time, no other implementation of such type of systems exist that is open source and free of charge. The software is developed in Clojure in order to leverage the Java libraries, the JVM itself, and the capabilities of the programming language to implement concurrency in a convenient manner. However, the goal of this implementation is to provide a language-agnostic interface based in a REST API, which can be used by any programming language capable of handling HTTP requests. A comparison between a traditional type-1 fuzzy inference is provided, where the reader can observe how the indeterminacy affects the outputs of the system.
Abstract - In this paper, we describe VICLEO, a visualization tool that performs a graph representation of the meaning of a statement based on the concepts of semantic field and semantic similarity measures. As the main novelty, VICLEO extends the concept of semantic field to a whole sentence and clusters it into fuzzy sets, where the degree of membership of the sentence components is obtained applying semantic similarity measures. Furthermore, VICLEO is endowed with a visual interactive interface which allows the user to navigate through the semantic field of the statement.