Joaquín Roca-Dorda

A new approach for teaching power electronics converter experiments

This paper presents a new methodological approach to teaching power electronics converter experiments. This approach is based on a reconfigurable hardware-software platform for use in converter experiments in a basic power electronics course. This course is an optional subject, and, therefore, the experiments need to motivate the students. The platform is controlled by software (made in a LabVIEW environment) run on a PC. The student can control the fundamental parameters of the selected converter topology through the user interface and, with a little work, can compare the results with a real circuit. An example of use of the methodology in an inverter experiment is included.

EFFICIENT AUTOMATIC SELECTION AND COMBINATION OF EEG FEATURES IN LEAST SQUARES CLASSIFIERS FOR MOTOR IMAGERY BRAIN–COMPUTER INTERFACES

Discriminative features have to be properly extracted and selected from the electroencephalographic (EEG) signals of each specific subject in order to achieve an adaptive brain-computer interface (BCI) system. This work presents an efficient wrapper-based methodology for feature selection and least squares discrimination of high-dimensional EEG data with low computational complexity. Features are computed in different time segments using three widely used methods for motor imagery tasks and, then, they are concatenated or averaged in order to take into account the time course variability of the EEG signals. Once EEG features have been extracted, proposed framework comprises two stages. The first stage entails feature ranking and, in this work, two different procedures have been considered, the least angle regression (LARS) and the Wilcoxon rank sum test, to compare the performance of each one. The second stage selects the most relevant features using an efficient leave-one-out (LOO) estimation based on the Allens PRESS statistic. Experimental comparisons with the state-of-the-art BCI methods shows that this approach gives better results than current state-of-the-art approaches in terms of recognition rates and computational requirements and, also with respect to the first ranking stage, it is confirmed that the LARS algorithm provides better results than the Wilcoxon rank sum test for these experiments.

Efficient feature selection and linear discrimination of EEG signals

Abstract Brain–Computer Interface systems (BCIs) based on Electroencephalogram (EEG) signal processing allow us to translate the subjects brain activities into control commands for computer devices. This paper presents an efficient embedded approach for feature selection and linear discrimination of EEG signals. In the first stage, four well-known feature extraction methods are used: Power spectral features, Hjorth parameters, Autoregressive modelling and Wavelet transform. From all the obtained features, the proposed method efficiently selects and combines the most useful features for classification with less computational requirements. Least Angle Regression (LARS) is used for properly ranking each feature and, then, an efficient Leave-One-Out (LOO) estimation based on the PRESS statistic is used to choose the most relevant features. Experimental results on motor-imagery BCIs problems are provided to illustrate the competitive performance of the proposed approach against other conventional methods.

Exploring dimensionality reduction of EEG features in motor imagery task classification

A Brain-Computer Interface (BCI) system based on motor imagery (MI) identifies patterns of electrical brain activity to predict the user intention while certain movement imagination tasks are performed. Currently, one of the most important challenges is the adaptive design of a BCI system. For solving it, this work explores dimensionality reduction techniques: once features have been extracted from Electroencephalogram (EEG) signals, the high-dimensional EEG data has to be mapped onto a new reduced feature space to make easier the classification stage. Besides the standard sequential feature selection methods, this paper analyzes two unsupervised transformation-based approaches – Principal Component Analysis and Locality Preserving Projections – and the Local Fisher Discriminant Analysis (LFDA), which works in a supervised manner. The dimensionality in the projected space is chosen following a wrapper-based approach by an efficient leave-one-out estimation. Experiments have been conducted on five novice subjects during their first sessions with MI-based BCI systems in order to show that the appropriate use of dimensionality reduction methods allows increasing the performance. In particular, obtained results show that LFDA gives a significant enhancement in classification terms without increasing the computational complexity and, then, it is a promising technique for designing MI-based BCI system.

Task complexity modulates pilot electroencephalographic activity during real flights

Most research connecting task performance and neural activity to date has been conducted in laboratory conditions. Thus, field studies remain scarce, especially in extreme conditions such as during real flights. Here, we investigated the effects of flight procedures of varied complexity on the in-flight EEG activity of military helicopter pilots. Flight procedural complexity modulated the EEG power spectrum: highly demanding procedures (i.e., takeoff and landing) were associated with higher EEG power in the higher frequency bands, whereas less demanding procedures (i.e., flight exercises) were associated with lower EEG power over the same frequency bands. These results suggest that EEG recordings may help to evaluate an operators cognitive performance in challenging real-life scenarios, and thus could aid in the prevention of catastrophic events.

Testing the Self-Similarity Exponent to Feature Extraction in Motor Imagery Based Brain Computer Interface Systems

A Brain Computer Interface (BCI) system is a tool not requiring any muscle action to transmit information. Acquisition, preprocessing, feature extraction (FE), and classification of electroencephalograph (EEG) signals constitute the main steps of a motor imagery BCI. Among them, FE becomes crucial for BCI, since the underlying EEG knowledge must be properly extracted into a feature vector. Linear approaches have been widely applied to FE in BCI, whereas nonlinear tools are not so common in literature. Thus, the main goal of this paper is to check whether some Hurst exponent and fractal dimension based estimators become valid indicators to FE in motor imagery BCI. The final results obtained were not optimal as expected, which may be due to the fact that the nature of the analyzed EEG signals in these motor imagery tasks were not self-similar enough.

Feed-Forward Neural Network Architectures Based on Extreme Learning Machine for Parkinson’s Disease Diagnosis

Feed-Forward Neural Networks have been successfully applied for solving many biomedical problems. However, its design stage is far slower than required in practice. Recently, Extreme Learning Machine (ELM) has been proposed to solve this drawback. This paper presents several ELM architectures and its application for a real problem of recognizing Parkinson’s disease. Experimental results show the usefulness of the ELM-based neural networks.

Statistical Data Mining and Artificial Neural Networks: A Case of Study in Financial Modeling

Nowadays, an organization or institution works with a huge amount of information about itself and its environment. This data has the potential to predict the evolution of interesting variables or trends in the outside environment. Data mining is the process that uses a variety of data analysis tools to discover meaningful patterns, trends and relationships in data that may be used to make valid predictions. In the last decades, artificial neural network-based technology stands out as one of the most suitable approaches. The goals of this work are to give a comprehensive analysis of the data mining process, to present the last advances on neural networks and its application for modeling financial data. In particular, an efficient neural network model is constructed for modeling the return on assets from other financial variables.

Prototipo de Unidad de Registro EDF Para Holter Digital de Bajo Costo

This paper describes the development of a recording unit for biomedical signals based upon standard secure digital memory cards, supporting the European Data Format (EDF) for the implementation of a low cost digital Holter. This device takes advantage of the possibilities offered by these wide spread memory cards (which are currently mass produced at very low prices due to their use in digital cameras and other handheld devices), in order to ease the implementation of long term digital signal acquisition, as happens with ECG records for HRV analysis. The use of recently introduced microcontrollers supporting these devices, as well as native USB support, may lead towards a future reduction of the price of these devices.