Automatic and Adaptive Classification of Electroencephalographic Signals for Brain Computer Interfaces
- PDF / 624,271 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 36 Downloads / 198 Views
ORIGINAL PAPER
Automatic and Adaptive Classification of Electroencephalographic Signals for Brain Computer Interfaces Germán Rodríguez-Bermúdez · Pedro J. García-Laencina
Received: 13 June 2012 / Accepted: 10 October 2012 / Published online: 2 November 2012 © Springer Science+Business Media New York 2012
Abstract 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
G. Rodríguez-Bermúdez · P. J. García-Laencina (B) Centro Universitario de la Defensa de San Javier (University Centre of Defence at the Spanish Air Force Academy), C/ Coronel López Peña s/n, 30720 Santiago de la Ribera, Spain e-mail: [email protected] G. Rodríguez-Bermúdez e-mail: [email protected]
methods, especially in terms of classification accuracy and computational cost. Keywords Biomedical engineering · Electroencephalographic signals · Brain computer interface · Feature selection · Linear discrimination · Adaptive systems
Introduction Nowadays there is an increasing global demand for more affordable and effective services and applications based on knowledge extraction from biomedical data. Biomedical signals are rich information sources which, when appropriately processed, have the potential to facilitate such advancements. Particularly, since the first systematic study on human electroencephalographic (EEG) signals in the early 1920s by Hans Berger [1] and their widespread acceptance 10 years later, the EEG signals have successfully and extensively used in research studies by covering a wide range of applications from clinical diagnosis to human machine interaction [2]. The EEG signal processing is an useful tool for practitioners in the treatment of several diseases, such as epilepsy, depression, sleep disorders, anxiety and learning disabilities [3–5]. In addition to its
Data Loading...
