Juan Méndez

Short-term wind power forecast based on cluster analysis and artificial neural networks

In this paper an architecture for an estimator of short-term wind farm power is proposed. The estimator is made up of a Linear Machine classifier and a set of k Multilayer Perceptrons, training each one for a specific subspace of the input space. The splitting of the input dataset into the k clusters is done using a k-means technique, obtaining the equivalent Linear Machine classifier from the cluster centroids. In order to assess the accuracy of the proposed estimator, some experiments will be carried out with actual data of wind speed and power of an experimental wind farm. We also compute the output of an ideal wind turbine to enrich the dataset and estimate the performance of the estimator on one isolated turbine.

A Procedure for Biological Sensitive Pattern Matching in Protein Sequences

A Procedure for fast pattern matching in protein sequences is presented. It uses a biological metric, based on the substitution matrices as PAM or BLOSUM, to compute the matching. Biological sensitive pattern matching does pattern detection according to the available empirical data about similarity and affinity relations between amino acids in protein sequences. Sequence alignments is a string matching procedure used in Genomic; it includes insert/delete operators and dynamic programming techniques; it provides more sophisticate results that other pattern matching procedures but with higher computational cost. Heuristic procedures for local alignments as FASTA or BLAST are used to reduce this cost. They are based on some successive tasks; the first one uses a pattern matching procedure with very short sequences, also named k-tuples. This paper shows how using the L1 metric this matching task can be efficiently computed by using SIMD instructions. To design this procedure, a table that maps the substitution matrices is needed. This table defines a representation of each amino acid residue in a n-dimensional space of lower dimensionality as possible; this is accomplished by using techniques of Multidimensional Scaling used in Pattern Recognition and Machine Learning for dimensionality reduction. Based on the experimental tests, the proposed procedure provides a favorable ration of cost vs matching quality.

Exploring the Use of Local Binary Patterns as Focus Measure

In this work local binary patterns based focus measures are presented. Local binary patterns (LBP) have been introduced in computer vision tasks like texture classification or face recognition. In applications where recognition is based on LBP, a computational saving can be achieved with the use of LBP in the focus measures. The behavior of the proposed measures is studied to test if they fulfill the properties of the focus measures and then a comparison with some well know focus measures is carried out in different scenarios.

Multimodal Attention System for an Interactive Robot

Social robots are receiving much interest in the robotics community. The most important goal for such robots lies in their interaction capabilities. An attention system is crucial, both as a filter to center the robot’s perceptual resources and as a mean of letting the observer know that the robot has intentionality. In this paper a simple but flexible and functional attentional model is described. The model, which has been implemented in an interactive robot currently under development, fuses both visual and auditive information extracted from the robot’s environment, and can incorporate knowledge-based influences on attention.

GD: A Measure Based on Information Theory for Attribute Selection

In this work a measure called GD is presented for attribute selection. This measure is defined between an attribute set and a class and corresponds to a generalization of the Mantaras distance that allows to detect the interdependencies between attributes. In the same way, the proposed measure allows to order the attributes by importance in the definition of the concept. This measure does not exhibit a noticeable bias in favor of attributes with many values. The quality of the selected attributes using the GD measure is tested by means of different comparisons with other two attribute selection methods over 19 datasets.

A systematic method for exploring contour segment descriptions

Abstract A new methodology has been developed for the comparative analysis of different contour characterization methods in the context of a structural approach for an artificial vision system. This methodology has been designed for testing the description of contour segments using characterization methods that have been used in applications dealing with isolated forms. The proposed schema is modular and comprises three major steps: a segmentation stage, which is based on a rule-based segmentation machine; a labeling stage, which is dependent on the characterization method used to describe the contour segments and in which the problem of defining classes or typologies of segments is also considered; and a learning and recognition stage, which uses fast tree classifiers and combines their evidence by means of the Dempster-Shafer combination rule. Experimental results are presented using the Fourier-Bessel transform as the contour characterization method.

Useful computer vision techniques for human-robot interaction

This paper describes some simple but useful computer vision techniques for human-robot interaction. First, an omnidirectional camera setting is described that can detect people in the surroundings of the robot, giving their angular positions and a rough estimate of the distance. The device can be easily built with inexpensive components. Second, we comment on a color-based face detection technique that can alleviate skin-color false positives. Third, a simple head nod and shake detector is described, suitable for detecting affirmative/negative, approval/dissaproval, understanding/disbelief head gestures.

A Procedure to Compute Prototypes for Data Mining in Non-structured Domains

This paper describes a technique for associating a set of symbols with an event in the context of knowledge discovery in database or data mining. The set of symbols is related to the keywords in a database which is used as an implicit knowledge source. The aim of this approach is to discover the significant keyword groups which best represent the event. A significant contribution of this work is a procedure which obtains the representative prototype of a group of symbolic data. It can be used for both, unsupervised learning to describe classes, and supervised learning to compute prototypes. The procedure involves defining an objective function and the subsequent hypothesis-exploring system and obtaining an advantageous procedure regarding computational costs.

Computing Voronoi Adjacencies in High Dimensional Spaces by Using Linear Programming

Some algorithms in Pattern Recognition and Machine Learning as neighborhood-based classification and dataset condensation can be improved with the use of Voronoi tessellation. This paper shows the weakness of some existing algorithms of tessellation to deal with high-dimensional datasets. The use of linear programming can improve the tessellation procedures by focusing on Voronoi adjacency. It will be shown that the adjacency test based on linear programming is a version of the polytope search. However, the polytope search procedure provides more information than a simple Boolean test. This paper proposes a strategy to use the additional information contained in the basis of the linear programming algorithm to obtain other tests. The theoretical results are applied to tessellate several random datasets, and also for much-used datasets in Machine Learning repositories.

Experiments and Reference Models in Training Neural Networks for Short-Term Wind Power Forecasting in Electricity Markets

Many published studies in wind power forecasting based on Neural Networks have provided performance factors based on error criteria. Based on the standard protocol for forecasting, the published results must provide improvement criteria over the persistence or references models of its same place. Persistence forecasting is the easier way of prediction in time series, but first order Wiener predictive filter is an enhancement of pure persistence model that have been adopted as the reference model for wind power forecasting. Pure enhanced persistence is simple but hard to beat in short-term prediction. This paper shows some experiments that have been performed by applying the standard protocols with Feed Forward and Recurrent Neural Networks architectures in the background of the requirements for Open Electricity Markets.