Journal of Intelligent & Fuzzy Systems - Volume 18, issue 6

Article Type: Other

Citation: Journal of Intelligent & Fuzzy Systems, vol. 18, no. 6, pp. 525-526, 2007

Authors: Chen, Xiujuan | Li, Yong | Harrison, Robert | Zhang, Yan-Qing

Article Type: Research Article

Abstract: Classification of biomedical data faces a special challenge because of the characteristics of the data: too few data examples with too many features. How to improve the classification performance or the generalization ability of a classifier in the biomedical domain becomes one of the active research areas. One approach is to build a fusion model to combine multiple classifiers together and result in a combined classifier which can achieve a better performance than any of its …composing individual classifiers. In this paper, we propose a SVM classifier fusion model to combine multiple SVMs by applying the knowledge of fuzzy logic and genetic algorithms. The fuzzy logic system (FLS) is constructed based on SVM accuracies and distances of data examples to SVM hyperplanes in SVM feature spaces. A genetic algorithm (GA) is used to tune the fuzzy membership functions (MFs) in the FLS and determine the optimal fuzzy fusion model. We have applied the proposed model to two biomedical data: colon tumor data and ovarian cancer data. Our experiment shows that multiple SVM classifiers complement each other well in the proposed fusion model and the ensemble achieves a better, more robust and more reliable performance than individual composing SVMs. Show more

Keywords: Fuzzy logic, evolutionary computation, genetic algorithms, bioinformatics, medical informatics, support vector machines, ensembles, classification

Citation: Journal of Intelligent & Fuzzy Systems, vol. 18, no. 6, pp. 527-541, 2007

Authors: Park, Han-Saem | Cho, Sung-Bae

Article Type: Research Article

Abstract: Clustering analysis of the gene expression profiles has been used for identifying the functions of unknown genes. Fuzzy clustering method, which is one category of clustering, assigns one sample to multiple clusters as their degrees of membership. It is more appropriate for analyzing gene expression profiles because genes usually belong to multiple functional families. However, general clustering methods have problems that they are sensitive to initialization and can be trapped into local optima. In this paper, …we propose an evolutionary fuzzy clustering method with Bayesian validation which uses a genetic algorithm for fuzzy clustering process of gene expression profiles and Bayesian validation method for the fitness evaluation process. We have conducted in-depth experiments to verify the usefulness of the proposed method with well-known gene expression profiles of SRBCT and Saccharomyces. Show more

Keywords: Evolutionary clustering, fuzzy clustering, Bayesian validation, gene expression profiles

Citation: Journal of Intelligent & Fuzzy Systems, vol. 18, no. 6, pp. 543-559, 2007

Authors: Ghosh, Ashish | Sen, Anindya

Article Type: Research Article

Abstract: The present paper attempts to employ hybrid genetic algorithms (GAs) to solve the flexible-ligand docking problem i.e. predicting the binding conformation of a flexible ligand molecule into a rigid protein. Our hybrid GA scheme uses the concept of Lamarckian genetics to perform a local search about an individual, followed by replacing it with a better solution found in its neighborhood. Two local search schemes have been investigated and their performance relative to the standard GA have …been compared. Preliminary results obtained on a set of three protein-ligand complexes are encouraging. Show more

Citation: Journal of Intelligent & Fuzzy Systems, vol. 18, no. 6, pp. 561-574, 2007

Authors: Lopes, Heitor S. | Perretto, Mauricio

Article Type: Research Article

Abstract: An important problem in Bioinformatics is the reconstruction of phylogenetic trees. A phylogenetic tree aims at unveiling the evolutionary relationship between several species. In this way, it is possible to know which species are more closely related to one another and which are more distantly related. Established methods for phylogeny work fine for small or moderate number of species, but they become unfeasible for large-scale phylogeny. This work proposes a methodology using the Ant Colony Optimization …(ACO) paradigm for the problem. A phylogenetic tree is viewed as a fully-connected graph using a matrix of distances between species. We search for the shortest path in this graph, turning the problem to an instance of the well-known traveling salesman problem. After, we describe how to build a tree using the directed graph and the pheromone matrix obtained by the ACO. Two data sets were used to test the system. The first one was used to investigate the sensitivity of the control parameters and to define their default values. The second data set was used to analyze the scalability of the system for a large number of sequences. Results show that the proposed method is as good as or even better than the other conventional methods and very efficient for large-scale phylogeny. Show more

Keywords: Bioinformatics, phylogenetic tree, Ant Colony Optimization

Citation: Journal of Intelligent & Fuzzy Systems, vol. 18, no. 6, pp. 575-583, 2007