Pablo A. D. Castro

Applying biclustering to text mining: an immune-inspired approach

With the rapid development of information technology, computers are proving to be a fundamental tool for the organization and classification of electronic texts, given the huge amount of available information. The existent methodologies for text mining apply standard clustering algorithms to group similar texts. However, these algorithms generally take into account only the global similarities between the texts and assign each one to only one cluster, limiting the amount of information that can be extracted from the texts. An alternative proposal capable of solving these drawbacks is the biclustering technique. The biclustering is able to perform clustering of rows and columns simultaneously, allowing a more comprehensive analysis of the texts. The main contribution of this paper is the development of an immune-inspired biclustering algorithm to carry out text mining, denoted BIC-aiNet. BIC-aiNet interprets the biclustering problem as several two-way bipartition problems, instead of considering a single two-way permutation framework. The experimental results indicate that our proposal is able to group similar texts efficiently and extract implicit useful information from groups of texts.

Designing ensembles of fuzzy classification systems: an immune-inspired approach

In this work we propose an immune-based approach for designing of fuzzy systems. From numerical data and with membership function previously defined, the immune algorithm evolves a population of fuzzy classification rules based on the clonal selection, hypermutation and immune network principles. Once AIS are able to find multiple good solutions of the problem, accurate and diverse fuzzy systems are built in a single run. Hence, we construct an ensemble of these classifier in order to achieve better results. An ensemble of classifiers consists of a set of individual classifiers whose outputs are combined when classifying novel patterns. The good performance of an ensemble is strongly dependent of individual accuracy and diversity of its components. We evaluate the proposed methodology through computational experiments on some datasets. The results demonstrate that the performance of the obtained fuzzy systems in isolation is very good. However when we combine these systems, a significant improvement is obtained in the correct classification rate, outperforming the single best classifier.

BAIS: A Bayesian Artificial Immune System for the effective handling of building blocks

Significant progress has been made in theory and design of Artificial Immune Systems (AISs) for solving hard problems accurately. However, an aspect not yet widely addressed by the research reported in the literature is the lack of ability of the AISs to deal effectively with building blocks (partial high-quality solutions coded in the antibody). The available AISs present mechanisms for evolving the population that do not take into account the relationship among the variables of the problem, potentially causing the disruption of high-quality partial solutions. This paper proposes a novel AIS with abilities to identify and properly manipulate building blocks in optimization problems. Instead of using cloning and mutation to generate new individuals, our algorithm builds a probabilistic model representing the joint probability distribution of the promising solutions and, subsequently, uses this model for sampling new solutions. The probabilistic model used is a Bayesian network due to its capability of properly capturing the most relevant interactions among the variables. Therefore, our algorithm, called Bayesian Artificial Immune System (BAIS), represents a significant attempt to improve the performance of immune-inspired algorithms when dealing with building blocks, and hence to solve efficiently hard optimization problems with complex interactions among the variables. The performance of BAIS compares favorably with that produced by contenders such as state-of-the-art Estimation of Distribution Algorithms.

MOBAIS: A Bayesian Artificial Immune System for Multi-Objective Optimization

Significant progress has been made in theory and design of artificial immune systems (AISs) for solving multi-objective problems accurately. However, an aspect not yet widely addressed by the research reported in the literature is the lack of ability of the AIS to deal effectively with building blocks (high-quality partial solutions coded in the antibody). The available AISs present mechanisms for evolving the population that do not take into account the relationship among the variables of the problem, causing the disruption of these high-quality partial solutions. Recently, we proposed a novel immune-inspired approach for single-objective optimization as an attempt to avoid this drawback. Our proposal replaces the traditional mutation and cloning operators with a probabilistic model, more specifically a Bayesian network representing the joint distribution of promising solutions and, subsequently, uses this model for sampling new solutions. Now, in this paper we extend our methodology for solving multi-objective optimization problems. The proposal, called Multi-Objective Bayesian Artificial Immune System (MOBAIS), was evaluated in the well-known multi-objective Knapsack problem and its performance compares favorably with that produced by contenders such as NSGA-II, MISA, and mBOA.

Multi‐objective feature selection using a Bayesian artificial immune system

Purpose – The purpose of this paper is to apply a multi‐objective Bayesian artificial immune system (MOBAIS) to feature selection in classification problems aiming at minimizing both the classification error and cardinality of the subset of features. The algorithm is able to perform a multimodal search maintaining population diversity and controlling automatically the population size according to the problem. In addition, it is capable of identifying and preserving building blocks (partial components of the whole solution) effectively.Design/methodology/approach – The algorithm evolves candidate subsets of features by replacing the traditional mutation operator in immune‐inspired algorithms with a probabilistic model which represents the probability distribution of the promising solutions found so far. Then, the probabilistic model is used to generate new individuals. A Bayesian network is adopted as the probabilistic model due to its capability of capturing expressive interactions among the variables of ...

Learning Ensembles of Neural Networks by Means of a Bayesian Artificial Immune System

In this paper, we apply an immune-inspired approach to design ensembles of heterogeneous neural networks for classification problems. Our proposal, called Bayesian artificial immune system, is an estimation of distribution algorithm that replaces the traditional mutation and cloning operators with a probabilistic model, more specifically a Bayesian network, representing the joint distribution of promising solutions. Among the additional attributes provided by the Bayesian framework inserted into an immune-inspired search algorithm are the automatic control of the population size along the search and the inherent ability to promote and preserve diversity among the candidate solutions. Both are attributes generally absent from alternative estimation of distribution algorithms, and both were shown to be useful attributes when implementing the generation and selection of components of the ensemble, thus leading to high-performance classifiers. Several aspects of the design are illustrated in practical applications, including a comparative analysis with other attempts to synthesize ensembles.

Conceptual and Practical Aspects of the aiNet Family of Algorithms

In this paper, a review of the conceptual and practical aspects of the aiNet (Artificial Immune Network) family of algorithms will be provided. This family of algorithms started with the aiNet algorithm, proposed in 2002 for data clustering and, since then, several variations have been developed for data clustering, biclustering and optimization in general. Although the algorithms will be positioned with respect to other pertinent approaches from the literature, the emphasis of this paper will be on the formalization and critical analysis of the set of contributions produced along almost one decade of research in this specific theme, together with the provision of insights for further extensions.

Genetic design of fuzzy knowledge bases - a study of different approaches

The objective of this work is to design, implement and test two different genetic fuzzy systems approaches with the purpose of analyzing the performance of both when applied to classification problems. In the first approach the fuzzy sets are defined previously by fuzzy clustering and the rule base is automatically generated and optimized using genetic algorithms. In the second approach the data base is the object of genetic algorithm learning, instead of the rule base. In this case, the rule base is generated by means of an auxiliary method (Wang & Mendell). Investigations of both methods developed earlier by the authors are described and then, the results of the comparison experiments performed in the present work are presented. The methods have been selected for investigation with the objective of analyzing the performance and the size of the resulting knowledge bases generated through genetic algorithms applied to different KB components.

Multi-objective Bayesian Artificial Immune System: Empirical Evaluation and Comparative Analyses

Recently, we have proposed a Multi-Objective Bayesian Artificial Immune System (MOBAIS) to deal effectively with building blocks (high-quality partial solutions coded in the solution vector) in combinatorial multi-objective problems. By replacing the mutation and cloning operators with a probabilistic model, more specifically a Bayesian network representing the joint distribution of promising solutions, MOBAIS takes into account the relationships among the variables of the problem, avoiding the disruption of already obtained high-quality partial solutions. The preliminary results have indicated that our proposal is able to properly build the Pareto front. Motivated by this scenario, this paper better formalizes the proposal and investigates its usefulness on more challenging problems. In addition, an important enhancement regarding the Bayesian network learning was incorporated into the algorithm in order to speed up its execution. To conclude, we compare MOBAIS with state-of-the-art algorithms taking into account quantitative aspects of the Pareto front found by the algorithms. MOBAIS outperforms the contenders in terms of the quality of the obtained solutions and requires an amount of computational resource inferior or compatible with the contenders.

Feature Subset Selection by Means of a Bayesian Artificial Immune System

This paper proposes the application of a novel bio-inspired algorithm as a search engine to the feature subset selection problem. We may interpret our algorithm as an estimation of distribution algorithm that adopts an artificial immune system to implement the search process in the space of all features and a Bayesian network to implement the probabilistic model of the promising solutions. The characteristics of the proposed algorithm are the capability of effectively identifying and manipulating building blocks, maintenance of diversity in the population, and automatic control of the population size. These properties allow the algorithm to perform a multimodal search, known to be of great relevance in feature selection problems. Experiments on five datasets were carried out in order to evaluate the proposed methodology in classification problems and its performance compares favorably to that produced by contenders.