Spectral turbulence measuring as feature extraction method from EEG on affective computing

Abstract In biomedical and psychological applications dealing with EEG, a suitable selection of the most relevant electrodes is useful for lightening the data acquisition and facilitating the signal processing. Therefore, an efficient method for extracting and selecting features from EEG channels is desirable. Classification methods are more and more applied for obtaining important conclusions from diverse psychological processes, and specifically for emotional processing. In this work, an original and straightforward method, inspired by the spectral turbulence (ST) measure from electrocardiogram and the support vector machine-recursive feature elimination (SVM-RFE) algorithm, is proposed for classifying EEG signals. The goal of this study is to introduce the ST concept in applications of artificial intelligence related to cognitive processes and to determine the best EEG channels for distinguishing between two different experimental conditions. By means of this method, the left temporal region of the brain has revealed to be greatly involved in the affective valence processing elicited by visual stimuli.

[1]  Juan Manuel Górriz,et al.  Component-based technique for determining the effects of acupuncture for fighting migraine using SPECT images , 2013, Expert Syst. Appl..

[2]  A J Camm,et al.  Spectral turbulence analysis versus time-domain analysis of the signal-averaged ECG in survivors of acute myocardial infarction. , 1994, Journal of electrocardiology.

[3]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[4]  Charalampos Bratsas,et al.  Toward Emotion Aware Computing: An Integrated Approach Using Multichannel Neurophysiological Recordings and Affective Visual Stimuli , 2010, IEEE Transactions on Information Technology in Biomedicine.

[5]  E. Caref,et al.  Spectral turbulence analysis of the signal-averaged electrocardiogram and its predictive accuracy for inducible sustained monomorphic ventricular tachycardia. , 1991, The American journal of cardiology.

[6]  Julien Penders,et al.  Towards wireless emotional valence detection from EEG , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  M. Macas,et al.  Classification of the emotional states based on the EEG signal processing , 2009, 2009 9th International Conference on Information Technology and Applications in Biomedicine.

[8]  Elmar Wolfgang Lang,et al.  Feature Extraction and Classification of Biosignals - Emotion Valence Detection from EEG Signals , 2013, BIOSIGNALS.

[9]  Massoud Stephane,et al.  Multidimensional Analysis of the Abnormal Neural Oscillations Associated With Lexical Processing in Schizophrenia , 2013, Clinical EEG and neuroscience.

[10]  E. Basar,et al.  Event-related beta oscillations are affected by emotional eliciting stimuli , 2010, Neuroscience Letters.

[11]  Panagiotis D. Bamidis,et al.  A Framework Combining Delta Event-Related Oscillations (EROs) and Synchronisation Effects (ERD/ERS) to Study Emotional Processing , 2009, Comput. Intell. Neurosci..

[12]  Jurandir Nadal,et al.  Spectral turbulence analysis of the signal-averaged electrocardiogram of the atrial activation as predictor of recurrence of idiopathic and persistent atrial fibrillation. , 2006, International journal of cardiology.

[13]  S. Delplanque,et al.  Modulation of cognitive processing by emotional valence studied through event-related potentials in humans , 2004, Neuroscience Letters.

[14]  Graham Clarke,et al.  A user-independent real-time emotion recognition system for software agents in domestic environments , 2007, Eng. Appl. Artif. Intell..

[15]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.

[16]  Isabell Wartenburger,et al.  Insular activity during passive viewing of aversive stimuli reflects individual differences in state negative affect , 2009, Brain and Cognition.

[17]  Ana Maria Tomé,et al.  Application of SVM-RFE on EEG signals for detecting the most relevant scalp regions linked to affective valence processing , 2013, Expert Syst. Appl..

[18]  Cuntai Guan,et al.  Asymmetric Spatial Pattern for EEG-based emotion detection , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[19]  Jonas K. Olofsson,et al.  Affective picture processing: An integrative review of ERP findings , 2008, Biological Psychology.

[20]  E Donchin,et al.  A new method for off-line removal of ocular artifact. , 1983, Electroencephalography and clinical neurophysiology.

[21]  L. Aftanas,et al.  Affective picture processing: event-related synchronization within individually defined human theta band is modulated by valence dimension. , 2001, Neuroscience Letters.

[22]  Roberto Hornero,et al.  Analysis of spontaneous MEG activity in Alzheimer's disease using time-frequency parameters , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[23]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[24]  Gunnar Rätsch,et al.  Support Vector Machines and Kernels for Computational Biology , 2008, PLoS Comput. Biol..

[25]  Maren Grigutsch,et al.  EEG oscillations and wavelet analysis , 2005 .

[26]  W. Klimesch,et al.  Are event-related potential components generated by phase resetting of brain oscillations? A critical discussion , 2007, Neuroscience.