Evolutionary optimization of classifiers and features for single-trial EEG Discrimination.docVIP

BioMedical Engineering OnLine BioMedCentral Research Open Access Evolutionary optimization of classifiers and features for single-trial EEG Discrimination Malin CB ?berg* and Johan Wessberg Address: Department of Neuroscience and Physiology, G?teborg University, G?teborg, 413 90, Sweden Email: Malin CB ?berg* - malin.aberg@neuro.gu.se; Johan Wessberg - johan.wessberg@physiol.gu.se * Corresponding author Published: 23 August 2007 Received: 30 May 2007 Accepted: 23 August 2007 BioMedical Engineering OnLine 2007, 6:32 doi:10.1186/1475-925X-6-32 This article is available from: /content/6/1/32 ? 2007 ?berg and Wessberg; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Abstract Background: State-of-the-art signal processing methods are known to detect information in single-trial event-related EEG data, a crucial aspect in development of real-time applications such as brain computer interfaces. This paper investigates one such novel approach, evaluating how individual classifier and feature subset tailoring affects classification of single-trial EEG finger movements. The discrete wavelet transform was used to extract signal features that were classified using linear regression and non-linear neural network models, which were trained and architecturally optimized with evolutionary algorithms. The input feature subsets were also allowed to evolve, thus performing feature selection in a wrapper fashion. Filter approaches were implemented as well by limiting the degree of optimization. Results: Using only 10 features and 100 patterns, the non-linear wrapper approach achieved the highest validation classification accuracy (subject mean 75%), closely followed by the