Catálogo de publicaciones - libros

This paper builds on previous work in which a feature selection method based on Genetic Programming (GP) was applied to a database containing a very large set of features that were extracted from the speech of clinically depressed patients and control subjects, with the goal of finding a small set of highly discriminating features. Here, we report improved results that were obtained by applying a technique that constructs clusters of correlated features and a Genetic Algorithm (GA) search that seeks to find the set of clusters that maximizes classification accuracy. While the final feature sets are considerably larger than those previously obtained using the GP approach, the classification performance is much improved in terms of both sensitivity and specificity. The introduction of a modified fitness function that slightly favors smaller feature sets resulted in further reduction of the feature set size without any loss in classification performance.

The design of intelligent sensor systems requires sophisticated methods from conventional signal processing and computational intelligence. Currently, a significant part of the overall system architecture still has to be manually elaborated in a tedious and time consuming process by an experienced designer. Clearly, an automatic method for auto-configuration of sensor systems would be salient. In this paper, we contribute to the optimization of the feature computation step in the overall system design, investigating multi-level thresholding (MLT) and Gaussian windowing. Our goals are to compare these two feature computation methods and two evolutionary optimization techniques, i.e., genetic algorithm (GA) and particle swarm optimization (PSO). To compare with previous research work gas sensor benchmark data is used. In the comparison of GA and PSO the latter method provided superior results of 100% recognition in generalization for thresholding, which proved to be more powerful method.

This paper presents the results of applying a Genetic Programming (GP) based feature selection algorithm to find a small set of highly discriminating features for the detection of clinical depression from a patient’s speech. While the performance of the GP-based classifiers was not as good as hoped for, several Bayesian classifiers were trained using the features found via GP and it was determined that these features do hold good discriminating power. The similarity of the feature sets found using GP for different observational groupings suggests that these features are likely to generalize well and thus provide good results with other clinical depression speech databases.

Many machine learning methods just consider the quality of prediction results as their final purpose. To make the prediction process transparent (reversible), spline kernel based methods were proposed by Gunn. However, the original solution method, termed SUpport vector Parsimonious ANOVA (SUPANOVA) was computationally very complex and demanding. In this paper, we propose a new heuristic to compute the optimal sparse vector in SUPANOVA that replaces the original solver for the convex quadratic problem of very high dimensionality. The resulting system is much faster without the loss of precision, as demonstrated in this paper on two benchmarks: the iris data set and the Boston housing market data benchmark.

We present a multi-dimensional mapping strategy using multiobjective genetic programming (MOGP) to search for the (near-)optimal feature extraction pre-processing stages for pattern classification as well as optimizing the dimensionality of the decision space. We search for the set of mappings with optimal dimensionality to project the input space into a decision space with maximized class separability. The steady-state Pareto converging genetic programming (PCGP) has been used to implement this multi-dimensional MOGP. We examine the proposed method using eight benchmark datasets from the UCI database and the Statlog project to make quantitative comparison with conventional classifiers. We conclude that MMOGP outperforms the comparator classifiers due to its optimized feature extraction process.

In this paper, combination between a Fuzzy ARTMAP-based artificial neural network (ANN) model and the genetic algorithm (GA) for performing cooperative learning is described. In our previous work, we have proposed a hybrid network integrating the Fuzzy ARTMAP (FAM) network with the Dynamic Decay Adjustment (DDA) algorithm (known as FAMDDA) for tackling pattern classification tasks. In this work, the FAMDDA network is employed as the platform for the GA to perform weight reinforcement. The performance of the proposed system (FAMDDA-GA) is assessed by means of generalization on unseen data from three benchmark problems. The results obtained are analyzed, discussed, and compared with those from FAM-GA. The results reveal that FAMDDA-GA performs better than FAM-GA in terms of test accuracy in the three benchmark problems.

The Fuzzy Min-Max (FMM) network is a supervised neural network classifier that forms hyperbox fuzzy sets for learning and classification. In this paper, we propose modifications to FMM in an attempt to improve its classification performance in situations when large hyperboxes are formed by the network. To achieve the goal, the Euclidean distance is computed after network training. We also propose to employ both the membership value of the hyperbox fuzzy sets and the Euclidean distance for classification. To assess the effectiveness of the modified FMM network, benchmark pattern classification problems are first used, and the results from different methods are compared. In addition, a fault classification problem with real sensor measurements collected from a power generation plant is used to evaluate the applicability of the modified FMM network. The results obtained are analyzed and explained, and implications of the modified FMM network in real environments are discussed.

After long-term exploration, it has been well established for the mechanisms of electrocardiogram (ECG) in health monitoring of cardiovascular system. Within the frame of an intelligent home healthcare system, our research group is devoted to researching/developing various mobile health monitoring systems, including the smart ECG interpreter. Hence, in this paper, we introduce an adaptive fuzzy ECG classifier with orientation to smart ECG interpreters. It can parameterize the incoming ECG signals and then classify them into four major types for health reference: Normal (N), Premature Atria Contraction (PAC), Right Bundle Block Beat (RBBB), and Left Bundle Block Beat (LBBB).

This paper proposes a novel clustering algorithm for the structure learning of fuzzy neural networks. Our clustering algorithm uses the reward and penalty mechanism for the adaptation of the fuzzy neural networks prototypes at every training sample. Compared with the classical clustering algorithms, the new algorithm can on-line partition the input data, pointwise update the clusters, and self-organize the fuzzy neural structure. No priori knowledge of the input data distribution is needed for initialization. All rules are self-created, and they grow automatically with more incoming data. There are no conflicting rules in the created fuzzy neural networks. Our approach also shows that supervised clustering algorithms can be used for the structure learning of the self-organizing fuzzy neural networks. The identification of several typical nonlinear dynamic systems is developed to demonstrate the effectiveness of this learning algorithm.

Particle Swarm Optimization (PSO) algorithm has exhibited good performance across a wide range of application problems. But research on the Quadratic Assignment Problem (QAP) has not much been investigated. In this paper, we introduce a novel approach based on PSO for QAPs. The representations of the position and velocity of the particles in the conventional PSO is extended from the real vectors to fuzzy matrices. A new mapping is proposed between the particles in the swarm and the problem space in an efficient way. We evaluate the performance of the proposed approach with Ant Colony Optimization (ACO) algorithm. Empirical results illustrate that the approach can be applied for solving quadratic assignment problems and it has outperforms ACO in the completion time.