Germán Rodríguez-Bermúdez

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.

Automatic and Adaptive Classification of Electroencephalographic Signals for Brain Computer Interfaces

Extracting knowledge from electroencephalographic (EEG) signals has become an increasingly important research area in biomedical engineering. In addition to its clinical diagnostic purposes, in recent years there have been many efforts to develop brain computer interface (BCI) systems, which allow users to control external devices only by using their brain activity. Once the EEG signals have been acquired, it is necessary to use appropriate feature extraction and classification methods adapted to the user in order to improve the performance of the BCI system and, also, to make its design stage easier. This work introduces a novel fast adaptive BCI system for automatic feature extraction and classification of EEG signals. The proposed system efficiently combines several well-known feature extraction procedures and automatically chooses the most useful features for performing the classification task. Three different feature extraction techniques are applied: power spectral density, Hjorth parameters and autoregressive modelling. The most relevant features for linear discrimination are selected using a fast and robust wrapper methodology. The proposed method is evaluated using EEG signals from nine subjects during motor imagery tasks. Obtained experimental results show its advantages over the state-of-the-art methods, especially in terms of classification accuracy and computational cost.

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.

Lessons for Technological Innovation Analysis. A Case of Study Based on McLuhan Tetrad Applied to Laser Cleaning Machines

One of the main purposes for a Project Management course under the Industrial Engineering grade is to lead the students by early applying their multidisciplinary competences to a professional framework, in order to develop their active profile to encourage them to always look for the best available techniques to brings organizations up to date. This paper summarizes how the McLuhan Tetrad help the students to handle the laser cleaning technique as a case of study.

Technological Immersion in Industrial Engineering for a Project Management Course to Develop Dual Use Technology

Technological Immersion (TI) is defined as an approach process to current industrial activity. It is focused on improving the competitive standards of the production activity by analyzing innovation processes, which were regulated by any standard that summarizes most of the international and relevant knowledge on Innovation Management Processes (for Spain, this is the regulation UNE166000). It allows using education on Project Management as a basic foundation to develop dual use technologies for security and defense purposes and for any other industry framework as well. The aim of this case study is to compile, under a TI scope, the experiences acquired by the students of the fourth course at the University Centre of Defense at the Spanish Air Force Academy, when studying the last generation of films that may have high strategic interest for defense as well as for many industrial applications. The TI was performed through a workshop about UNE166000 (Spanish Regulation), McLuhan Tetrad and other lessons on Innovation Management, the main purpose being to teach the students how to draft a professional report about the technological and knowledge transfer opportunities that these films may generate in order to develop new industrial advantages on dual use industry.

On discrete models of fractal dimension to explore the complexity of discrete dynamical systems

A fractal structure is a countable family of coverings which displays accurate information about the irregularities that a set presents when being explored with enough level of detail. It is worth noting that fractal structures become especially appropriate to provide new definitions of fractal dimension, which constitutes a valuable measure to test for chaos in dynamical systems. In this paper, we explore several approaches to calculate the fractal dimension of a subset with respect to a fractal structure. These models generalize the classical box dimension in the context of Euclidean subspaces from a discrete viewpoint. To illustrate the flexibility of the new models, we calculate the fractal dimension of a family of self-affine sets associated with certain discrete dynamical systems.

Classifying BCI signals from novice users with Extreme Learning Machine

Abstract Brain computer interface (BCI) allows to control external devices only with the electrical activity of the brain. In order to improve the system, several approaches have been proposed. However it is usual to test algorithms with standard BCI signals from experts users or from repositories available on Internet. In this work, extreme learning machine (ELM) has been tested with signals from 5 novel users to compare with standard classification algorithms. Experimental results show that ELM is a suitable method to classify electroencephalogram signals from novice users.

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.