Journal of Intelligent & Fuzzy Systems - Volume 12, issue 1

Authors: Maojo, Victor | Crespo, Jose

Article Type: Other

Citation: Journal of Intelligent & Fuzzy Systems, vol. 12, no. 1, pp. 1-3, 2002

Authors: Genkin, Alexander | Kulikowski, Casimir A. | Muchnik, Ilya

Article Type: Research Article

Abstract: In this paper we show how several problems in different areas of data mining and knowledge discovery can be viewed as finding the optimal covering of a finite set. Many such problems arise in biomedical and bioinformatics research. For example, protein functional annotation based on sequence information is an ubiquitous bioinformatics problem. It consists of finding a set of homolog (high similarity) sequences of known function to a given amino acid sequence of unknown function from …the various annotated sequence data bases. These can then be used as clues in suggesting further experimental analysis of the new protein. In the present paper we show that these optimization problems can be stated as maximizations of submodular functions on the set of candidate subsets -- a generalization that may be especially useful when conclusions from data mining need to be interpreted by human experts. This is common to a number of examples we consider below: diagnostic hypothesis generation, logical methods of data analysis, conceptual clustering, and proteins functional annotations. Show more

Keywords: protein functional annotation, medical decision making, set covering causal model, submodular function, optimal algorithm

Citation: Journal of Intelligent & Fuzzy Systems, vol. 12, no. 1, pp. 5-17, 2002

Authors: Ohno-Machado, Lucila | Vinterbo, Staal | Weber, Griffin

Article Type: Research Article

Abstract: Microarray technologies have allowed the measurement of expression of multiple genes simultaneously. Gene expression levels can be used to classify tissues into diagnostic or prognostic categories. As measurements from different microarray technologies are made in different scales (which are not guaranteed to be linear and not easily re-scalable), it is helpful to develop an easy-to-interpret technology-independent classification scheme. To capture the essentials of the problem of classification using gene expression data, we …show how fuzzy logic can be applied using two examples. Using information from genes previously shown to be important, the classification performance of the fuzzy inference is similar to that of other classifiers, but simpler and easier to interpret. The fuzzy inference system has the theoretical advantage that it does not need to be retrained when using measurements obtained from a different type of microarray. Although the data sets for gene expression analysis utilized in this paper are relatively small, they are among the largest available in this domain. Show more

Citation: Journal of Intelligent & Fuzzy Systems, vol. 12, no. 1, pp. 19-24, 2002

Authors: Inza, Iñaki | Sierra, Basilio | Blanco, Rosa | Larrañaga, Pedro

Article Type: Research Article

Abstract: In the last years, there has been a large growth in gene expression profiling technologies, which are expected to provide insight into cancer related cellular processes. Machine Learning algorithms, which are extensively applied in many areas of the real world, are not still popular in the Bioinformatics community. We report on the successful application of four well known supervised Machine Learning methods (IB1, Naive-Bayes, C4.5 and CN2) to cancer class prediction problems in three DNA microarray …datasets of huge dimensionality (Colon, Leukemia and NCI-60). The essential gene selection process in microarray domains is performed by a sequential search engine, evaluating the goodness of each gene subset by a wrapper approach which executes, by a leave-one-out process, the supervised algorithm to obtain its accuracy estimation. By the use of the gene selection procedure, the accuracy of supervised algorithms is significantly improved and the number of genes of the classification models is notably reduced for all datasets. Show more

Citation: Journal of Intelligent & Fuzzy Systems, vol. 12, no. 1, pp. 25-33, 2002

Authors: Gamberger, Dragan | Lavrač, Nada | Krstačić, Goran

Article Type: Research Article

Abstract: The confirmation rule set concept, presented in this paper, provides a framework for reliable decision making. This framework enables flexible formation of a confirmation rule set, by incorporating rules induced by machine learning algorithms as well as human encoded expert rules. The only conditions for including a rule into the confirmation rule set are its high predictive accuracy and relative independence from other rules in the rule set. This paper introduces the concept of confirmation rule …sets, together with an algorithm for selecting relatively independent rules from a set of acceptable confirmation rules. It presents also two approaches to confirmation rule induction: first, an exhaustive confirmation rule construction algorithm that was used to discover diagnostic rules in the coronary heart disease diagnosis problem, and second, a heuristic confirmation rule construction algorithm that was used for subgroup discovery in the coronary heart disease risk group detection problem. Show more

Citation: Journal of Intelligent & Fuzzy Systems, vol. 12, no. 1, pp. 35-48, 2002

Authors: Keravnou, E.T.

Article Type: Research Article

Abstract: Time representation and temporal reasoning are of crucial importance to clinical diagnosis. In this paper we present a general model for diagnostic knowledge, the Causal-Temporal-Action (C-T-A) model. This has a central tri-planar structure for the representation, in causal terms, of knowledge on disorders and physiological processes. The central structure is bounded by two other, orthogonal planes that represent temporal constraints and therapeutic actions. These planes function to constrain the existences of the temporal …entities residing on the central structure. A major focus of the paper is the temporal constraints plane of the C-T-A model. An abstract structure, the Abstract Temporal Graph (ATG) is proposed for the representation of temporal constraints. Specific cases of the ATG structure encountered in the literature on temporal clinical diagnosis are discussed and algorithms for checking the consistency and satisfiability of temporal constraints are presented. These algorithms are of relevance to the validation of diagnostic knowledge and patient data and the evaluation of diagnostic hypotheses. Show more

Keywords: clinical diagnosis, time representation, temporal reasoning, abductive diagnosis, Causal-Temporal-Action (C-T-A) model, temporal constraints, Abstract Temporal Graph (ATG)

Citation: Journal of Intelligent & Fuzzy Systems, vol. 12, no. 1, pp. 49-67, 2002

Authors: Paetz, Jürgen | Brause, Rüdiger

Article Type: Research Article

Abstract: In medical data analysis classification combined with rule generation is a common technique to obtain diagnosis results together with a rule based explanation. In this contribution we apply a neural network based rule generator in the domain of septic shock research. The septic shock is of special interest in intensive care medicine due to its high lethality rate. We describe the functionality of the neuro-fuzzy algorithm and present classification and rule generation results of our analysis. …Because we repeated our analysis with randomly selected test data to calculate statistically valid mean results, we generated one neural network with different architecture for each repetition. To decide the important question which of the different models should be used in the application phase, we propose a useful method based on similarity measures for rules resp. rule sets to select one representative network out of the set of trained networks. Show more

Citation: Journal of Intelligent & Fuzzy Systems, vol. 12, no. 1, pp. 69-78, 2002