In this work, a novel valence recognition system applied to EEG signals is presented. It consists of a feature extraction block followed by a wrapper classification algorithm. The proposed feature extraction method is based on measures of relative energies computed in short‐time intervals and certain frequency bands of EEG signal segments time‐locked to the stimuli presentation. These measures represent event‐related desynchronization/synchronization of underlying brain neural networks. The subsequent feature selection and classification steps comprise a wrapper technique based on two different classification approaches: an ensemble classifier, i.e., a random forest of classification trees and a support vector machine algorithm. Applying a proper importance measure from the classifiers, the feature elimination has been used to identify the most relevant features of the decision making both for intrasubject and intersubject settings, using single trial signals and ensemble averaged signals, respectively. The proposed methodologies allowed us to identify a frontal region and a beta band as the most relevant characteristics, extracted from the electrical brain activity, in order to determine the affective valence elicited by visual stimuli.
Part of the book: Emotion and Attention Recognition Based on Biological Signals and Images
Despite the vast literature on event-related potentials (ERPs), many clinical professionals are still unaware of the huge variety of possible applications they offer. The aim of this chapter is not to show the classical use of ERPs, focused on analyzing the first steps of information processing (sensory pathways). On the contrary, this chapter will be focused on the use of these ERPs in the assessment of cognitive function. In particular, this chapter is mainly focused on the use of ERPs to better understand the neural bases of cognitive impairment from the electrical activity of the brain. Describing all the possible ERP components and their cognitive meaning is a huge endeavor, and this chapter will only be focused on three of them: contingent negative variation (CNV), mismatch negativity (MMN), and P300. To improve the reader’s knowledge about these ERPs in cognition, a specific description will be given about the stimulation required to obtain the specific component, the topography, and latency shown. Moreover, a description of the neurophysiological bases of the component, its relationship with psychological processes and neural sources will be also included. Pathological alterations suffered by the component will also be briefly described.
Part of the book: Event-Related Potentials and Evoked Potentials