Antonio J. Serrano-López

A low-complexity fuzzy activation function for artificial neural networks

A novel fuzzy-based activation function for artificial neural networks is proposed. This approach provides easy hardware implementation and straightforward interpretability in the basis of IF-THEN rules. Backpropagation learning with the new activation function also has low computational complexity. Several application examples ( XOR gate, chaotic time-series prediction, channel equalization, and independent component analysis) support the potential of the proposed scheme.

Profiled support vector machines for antisense oligonucleotide efficacy prediction

BackgroundThis paper presents the use of Support Vector Machines (SVMs) for prediction and analysis of antisense oligonucleotide (AO) efficacy. The collected database comprises 315 AO molecules including 68 features each, inducing a problem well-suited to SVMs. The task of feature selection is crucial given the presence of noisy or redundant features, and the well-known problem of the curse of dimensionality. We propose a two-stage strategy to develop an optimal model: (1) feature selection using correlation analysis, mutual information, and SVM-based recursive feature elimination (SVM-RFE), and (2) AO prediction using standard and profiled SVM formulations. A profiled SVM gives different weights to different parts of the training data to focus the training on the most important regions.ResultsIn the first stage, the SVM-RFE technique was most efficient and robust in the presence of low number of samples and high input space dimension. This method yielded an optimal subset of 14 representative features, which were all related to energy and sequence motifs. The second stage evaluated the performance of the predictors (overall correlation coefficient between observed and predicted efficacy, r; mean error, ME; and root-mean-square-error, RMSE) using 8-fold and minus-one-RNA cross-validation methods. The profiled SVM produced the best results (r = 0.44, ME = 0.022, and RMSE= 0.278) and predicted high (>75% inhibition of gene expression) and low efficacy (<25%) AOs with a success rate of 83.3% and 82.9%, respectively, which is better than by previous approaches. A web server for AO prediction is available online at http://aosvm.cgb.ki.se/.ConclusionsThe SVM approach is well suited to the AO prediction problem, and yields a prediction accuracy superior to previous methods. The profiled SVM was found to perform better than the standard SVM, suggesting that it could lead to improvements in other prediction problems as well.

Web mining based on Growing Hierarchical Self-Organizing Maps: Analysis of a real citizen web portal

This work is focused on the usage analysis of a citizen web portal, Infoville XXI (http://www.infoville.es) by means of Self-Organizing Maps (SOM). In this paper, a variant of the classical SOM has been used, the so-called Growing Hierarchical SOM (GHSOM). The GHSOM is able to find an optimal architecture of the SOM in a few iterations. There are also other variants which allow to find an optimal architecture, but they tend to need a long time for training, especially in the case of complex data sets. Another relevant contribution of the paper is the new visualization of the patterns in the hierarchical structure. Results show that GHSOM is a powerful and versatile tool to extract relevant and straightforward knowledge from the vast amount of information involved in a real citizen web portal.

Steady-state and tracking analysis of a robust adaptive filter with low computational cost

This paper analyses a new adaptive algorithm that is robust to impulse noise and has a low computational load [E. Soria, J.D. Martin, A.J. Serrano, J. Calpe, and J. Chambers, A new robust adaptive algorithm with low computacional cost, Electron. Lett. 42 (1) (2006) 60-62]. The algorithm is based on two premises: the use of the cost function often used in independent component analysis and a fuzzy modelling of the hyperbolic tangent function. The steady-state error and tracking capability of the algorithm are analysed using conservation methods [A. Sayed, Fundamentals of Adaptive Filtering, Wiley, New York, 2003], thus verifying the correspondence between theory and experimental results.

Regularized RBF Networks for Hyperspectral Data Classification

In this paper, we analyze several regularized types of Radial Basis Function (RBF) Networks for crop classification using hyperspectral images. We compare the regularized RBF neural network with Support Vector Machines (SVM) using the RBF kernel, and AdaBoost Regularized (ABR) algorithm using RBF bases, in terms of accuracy and robustness. Several scenarios of increasing input space dimensionality are tested for six images containing six crop classes. Also, regularization, sparseness, and knowledge extraction are paid attention.

Fast communication: Non-linear RLS-based algorithm for pattern classification

A new non-linear recursive least squares (RLS) algorithm is presented in the context of pattern classification problems. The algorithm incorporates the non-linearity of the filters output in the updating rules of the classical RLS algorithm. The proposed method yields lower stationary error levels when compared to the standard LMS and RLS algorithms in a classical application of pattern classification, such as the channel equalization problem.

Use of SOMs for footwear comfort evaluation

The comfort in footwear is essential because the foot is one of the structures of the human body that supports more weight. Moreover, consumers are demanding ever higher and higher levels of comfort and functionality in shoes. Hence, the analysis of the comfort in the footwear industry is of great interest. This paper proposes the use of SOMs to qualitatively evaluate data related to comfort in footwear provided by the Spanish Technological Institute for Footwear and Related Industries. This work also studies which factors can be decisive when buying footwear, revealing interesting hidden relationships and qualitative patterns. For this purpose, the features that may play a relevant role in this framework, and the crucial relationships between them are studied for the comfort of a given shoe. This study tries to find the way of jointly representing comfort valuations for different areas of the foot with different variables (related to physical characteristics of the testers and characteristics or physical measures of foot-footwear) in order to find out if there is a difference between buying/not buying groups.

Machine Learning for Modeling the Biomechanical Behavior of Human Soft Tissue

An accurate modeling of the biomechanical properties of human soft tissue is crucial in many clinical applications, such as, radiotherapy administration or surgery. The finite element method (FEM) is the usual choice to carry out such modeling due to its high accuracy. However, FEM is computationally very costly, and hence, its application in real-time or even off-line with short delays are still challenges to overcome. This paper proposes a framework based on Machine Learning to learn FEM modeling, thus having a tool able to yield results that may be sufficiently fast for clinical applications. In particular, the use of ensembles of Decision Trees has shown its suitability in modeling the behavior of the liver and the breast.

Analysis of ventricular fibrillation signals using feature selection methods

Feature selection methods in machine learning models are a powerful tool to knowledge extraction. In this work they are used to analyse the intrinsic modifications of cardiac response during ventricular fibrillation due to physical exercise. The data used are two sets of registers from isolated rabbit hearts: control (G1: without physical training), and trained (G2). Four parameters were extracted (dominant frequency, normalized energy, regularity index and number of occurrences). From them, 18 features were extracted. This work analyses the relevance of each feature to classify the records in G1 and G2 using Logistic Regression, Multilayer Perceptron and Extreme Learning Machine. Three feature selection methods are presented: one based on the output variation, other on the classification results and, finally, another method based in the variation in ROC curve. Although we obtained different sorting of features for each used classifier, the features related to the mean value and standard deviation of dominant frequency and regularity index were the most relevant, stating that the modifications in VF response produced by physical exercise are related to the cardiac activation rate, as to the regularity of that activation.

Letters: Efficient pruning of multilayer perceptrons using a fuzzy sigmoid activation function

This Letter presents a simple and powerful pruning method for multilayer feed forward neural networks based on the fuzzy sigmoid activation function presented in [E. Soria, J. Martin, G. Camps, A. Serrano, J. Calpe, L. Gomez, A low-complexity fuzzy activation function for artificial neural networks, IEEE Trans. Neural Networks 14(6) (2003) 1576-1579]. Successful performance is obtained in standard function approximation and channel equalization problems. Pruning allows to reduce network complexity considerably, achieving a similar performance to that obtained by unpruned networks.