José C. Riquelme

Incremental wrapper-based gene selection from microarray data for cancer classification

Gene expression microarray is a rapidly maturing technology that provides the opportunity to assay the expression levels of thousands or tens of thousands of genes in a single experiment. We present a new heuristic to select relevant gene subsets in order to further use them for the classification task. Our method is based on the statistical significance of adding a gene from a ranked-list to the final subset. The efficiency and effectiveness of our technique is demonstrated through extensive comparisons with other representative heuristics. Our approach shows an excellent performance, not only at identifying relevant genes, but also with respect to the computational cost.

Energy Time Series Forecasting Based on Pattern Sequence Similarity

This paper presents a new approach to forecast the behavior of time series based on similarity of pattern sequences. First, clustering techniques are used with the aim of grouping and labeling the samples from a data set. Thus, the prediction of a data point is provided as follows: first, the pattern sequence prior to the day to be predicted is extracted. Then, this sequence is searched in the historical data and the prediction is calculated by averaging all the samples immediately after the matched sequence. The main novelty is that only the labels associated with each pattern are considered to forecast the future behavior of the time series, avoiding the use of real values of the time series until the last step of the prediction process. Results from several energy time series are reported and the performance of the proposed method is compared to that of recently published techniques showing a remarkable improvement in the prediction.

Evolutionary learning of hierarchical decision rules

This paper describes an approach based on evolutionary algorithms, hierarchical decision rules (HIDER), for learning rules in continuous and discrete domains. The algorithm produces a hierarchical set of rules, that is, the rules are sequentially obtained and must therefore be tried until one is found whose conditions are satisfied. Thus, the number of rules may be reduced because the rules could be inside of one another. The evolutionary algorithm uses both real and binary coding for the individuals of the population. We tested our system on real data from the UCI repository, and the results of a ten-fold cross-validation are compared to C4.5s, C4.5Rules, See5s, and See5Rules. The experiments show that HIDER works well in practice.

An evolutionary approach to estimating software development projects

Abstract The use of dynamic models and simulation environments in connection with software projects paved the way for tools that allow us to simulate the behaviour of the projects. The main advantage of a Software Project Simulator (SPS) is the possibility of experimenting with different decisions to be taken at no cost. In this paper, we present a new approach based on the combination of an SPS and Evolutionary Computation. The purpose is to provide accurate decision rules in order to help the project manager to take decisions at any time in the development. The SPS generates a database from the software project, which is provided as input to the evolutionary algorithm for producing the set of management rules. These rules will help the project manager to keep the project within the cost, quality and duration targets. The set of alternatives within the decision-making framework is therefore reduced to a quality set of decisions.

An evolutionary algorithm to discover numeric association rules

Association rules are one of the most used tools to discover relationships among attributes in a database. Nowadays, there are many efficient techniques to obtain these rules, although most of them require that the values of the attributes be discrete. To solve this problem, these techniques discretize the numeric attributes, but this implies a loss of information. In a general way, these techniques work in two phases: in the first one they try to find the sets of attributes that are, with a determined frequency, within the database (frequent itemsets), and in the second one, they extract the association rules departing from these sets. In this paper we present a technique to find the frequent itemsets in numeric databases without needing to discretize the attributes. We use an evolutionary algorithm to find the intervals of each attribute that conforms a frequent itemset. The evaluation function itself will be the one that decide the amplitude of these intervals. Finally, we evaluate the tool with synthetic and real databases to check the efficiency of our algorithm.Association rules are one of the most used tools to discover relationships among attributes in a database. Nowadays, there are many efficient techniques to obtain these rules, although most of them require that the values of the attributes be discrete. To solve this problem, these techniques discretize the numeric attributes, but this implies a loss of information. In a general way, these techniques work in two phases: in the first one they try to find the sets of attributes that are, with a determined frequency, within the database (frequent itemsets), and in the second one, they extract the association rules departing from these sets. In this paper we present a technique to find the frequent itemsets in numeric databases without needing to discretize the attributes. We use an evolutionary algorithm to find the intervals of each attribute that conforms a frequent itemset. The evaluation function itself will be the one that decide the amplitude of these intervals. Finally, we evaluate the tool with synthetic and real databases to check the efficiency of our algorithm.

Finding representative patterns with ordered projections

This paper presents a new approach to 2nding representative patterns for dataset editing. The algorithm patterns by ordered projections (POP), has some interesting characteristics: important reduction of the number of instances from the dataset; lower computational cost (� (mn log n)) with respect to other typical algorithms due to the absence of distance calculations; conservation of the decision boundaries, especially from the point of view of the application of axis-parallel classi2ers. POP works well in practice withbothcontinuous and discrete attributes. The performance of POP is analysed in two ways: percentage of reduction and classi2cation. POP has been compared to IB2, ENN and SHRINK concerning the percentage of reduction and the computational cost. In addition, we have analysed the accuracy of k-NN and C4.5 after applying the reduction techniques. An extensive empirical study using datasets with continuous and discrete attributes from the UCI repository shows that POP is a valuable preprocessing method for the later application of any axis-parallel learning algorithm. ? 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Mining Numeric Association Rules with Genetic Algorithms

In this last decade, association rules are being, inside Data Mining techniques, one of the most used tools to find relationships among attributes of a database. Numerous scopes have found in these techniques an important source of qualitative information that can be analyzed by experts in order to improve some aspects in their environment.

Mining quantitative association rules based on evolutionary computation and its application to atmospheric pollution

This research presents the mining of quantitative association rules based on evolutionary computation techniques. First, a real-coded genetic algorithm that extends the well-known binary-coded CHC algorithm has been projected to determine the intervals that define the rules without needing to discretize the attributes. The proposed algorithm is evaluated in synthetic datasets under different levels of noise in order to test its performance and the reported results are then compared to that of a multi-objective differential evolution algorithm, recently published. Furthermore, rules from real-world time series such as temperature, humidity, wind speed and direction of the wind, ozone, nitrogen monoxide and sulfur dioxide have been discovered with the objective of finding all existing relations between atmospheric pollution and climatological conditions.

Evolutionary Generalized Radial Basis Function neural networks for improving prediction accuracy in gene classification using feature selection

Radial Basis Function Neural Networks (RBFNNs) have been successfully employed in several function approximation and pattern recognition problems. The use of different RBFs in RBFNN has been reported in the literature and here the study centres on the use of the Generalized Radial Basis Function Neural Networks (GRBFNNs). An interesting property of the GRBF is that it can continuously and smoothly reproduce different RBFs by changing a real parameter @t. In addition, the mixed use of different RBF shapes in only one RBFNN is allowed. Generalized Radial Basis Function (GRBF) is based on Generalized Gaussian Distribution (GGD), which adds a shape parameter, @t, to standard Gaussian Distribution. Moreover, this paper describes a hybrid approach, Hybrid Algorithm (HA), which combines evolutionary and gradient-based learning methods to estimate the architecture, weights and node topology of GRBFNN classifiers. The feasibility and benefits of the approach are demonstrated by means of six gene microarray classification problems taken from bioinformatic and biomedical domains. Three filters were applied: Fast Correlation-Based Filter (FCBF), Best Incremental Ranked Subset (BIRS), and Best Agglomerative Ranked Subset (BARS); this was done in order to identify salient expression genes from among the thousands of genes in microarray data that can directly contribute to determining the class membership of each pattern. After different gene subsets were obtained, the proposed methodology was performed using the selected gene subsets as new input variables. The results confirm that the GRBFNN classifier leads to a promising improvement in accuracy.

Time-Series Prediction: Application to the Short-Term Electric Energy Demand

This paper describes a time-series prediction method based on the kNN technique. The proposed methodology is applied to the 24-hour load forecasting problem. Also, based on recorded data, an alternative model is developed by means of a conventional dynamic regression technique, where the parameters are estimated by solving a least squares problem. Finally, results obtained from the application of both techniques to the Spanish transmission system are compared in terms of maximum, average and minimum forecasting errors.