Fundamenta Informaticae - Volume 147, issue 2-3

Authors: Polkowski, Lech T. | Nowak, Bartosz

Article Type: Research Article

Abstract: In this work, we approach the problem of data analysis from a new angle: we investigate a relational method of separation of data into disjoint sub–data employing a modified betweenness relation, successfully applied by us in the area of behavioral robotics, and, we set a scheme for applications to be studied. The effect of the action by that relation on data is selection of a sub–data, say, ‘kernel’ with the property that each thing in it is a convex combination, in a sense explained below, of some other things in the kernel. One can say that kernel thus exhibited is …‘self–closed’. Algorithmically, this is achieved by means of a new construct, called by us a ‘dual indiscernibility matrix’. On the other hand, the complement to kernel consists of things in the data, which have some attribute values not met in any other thing. It is proper to call this complement to kernel the residuum . We examine both the kernel and the residuum from the point of view of quality of classification into decision classes for a few standard data sets from the UC Irvine Repository finding the results very satisfactory. Conceptually, our work is set in the framework of rough set theory and rough mereology and the main tool in inducing of the betweenness relation is the Łukasiewicz rough inclusion. Apart from the classification problem, we propose some strategies for conflict resolution based on concepts introduced in this work, and in this way we continue conflict analysis in rough set framework initiated by Zdzisław Pawlak. Show more

Keywords: rough inclusion, betweenness, Euclidean representation of a granule, hyper–granules, coalitions, conflict resolutions, classifier synthesis

DOI: 10.3233/FI-2016-1411

Citation: Fundamenta Informaticae, vol. 147, no. 2-3, pp. 337-352, 2016

Authors: Przybyła-Kasperek, Małgorzata

Article Type: Research Article

Abstract: Issues that are related to decision making that is based on dispersed knowledge are discussed in the paper. A dispersed decision-making system that was proposed in the earlier paper of the author is used in this paper. In the system the process of combining classifiers in coalitions is very important and negotiation is applied in the clustering process. The main aim of the article is to compare the results obtained using five different methods of conflict analysis in the system. All of these methods are used when the individual classifiers generate probability vectors over decision classes. The most popular methods …are considered - a sum rule, a product rule, a median rule, a maximum rule and a minimum rule. An additional aim is to compare the results obtained with using a dispersed decision-making system with the results obtained when the prediction results are aggregated directly using the conflict analysis methods. Tests, that were performed on data from the UCI repository are presented in the paper. The best methods in a particular situation are also indicated. It was found that some methods do not generate satisfactory results when there are dummy agents in a dispersed data set. That is, there are undecided agents who assign the same probability value to many different decision values. Another conclusion was that the use of a dispersed system improves the efficiency of inference. Show more

Keywords: decision support system, dispersed knowledge, conflict analysis, sum rule, product rule, median rule, maximum rule, minimum rule

DOI: 10.3233/FI-2016-1412

Citation: Fundamenta Informaticae, vol. 147, no. 2-3, pp. 353-370, 2016

Authors: Skowron, Andrzej | Jankowski, Andrzej

Article Type: Research Article

Abstract: In several papers we have discussed a computing model, called the Interactive Granular Computing (IGrC), for interactive computations on complex granules. In this paper, we compare two models of computing, namely the Turing model and the IGrC model.

Keywords: granular computing, rough set, interaction, information granule, physical object, complex granule, interactive granular computing

DOI: 10.3233/FI-2016-1413

Citation: Fundamenta Informaticae, vol. 147, no. 2-3, pp. 371-385, 2016