Research Article High-Frequency Electroencephalographic Activity in Left Temporal Area Is Associated with Pleasant Emotion Induced by Video Clips Jukka Kortelainen, Eero Väyrynen, and Tapio Seppänen Department of Computer Science and Engineering, University of Oulu, P.O. Box 4500, 90014 Oulu, Finland Correspondence should be addressed to Jukka Kortelainen; jukortel@ee.oulu.i Received 17 November 2014; Revised 5 March 2015; Accepted 5 March 2015 Academic Editor: Carlos M. Travieso-Gonz´ alez Copyright © 2015 Jukka Kortelainen et al. his is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Recent indings suggest that speciic neural correlates for the key elements of basic emotions do exist and can be identiied by neuroimaging techniques. In this paper, electroencephalogram (EEG) is used to explore the markers for video-induced emotions. he problem is approached from a classiier perspective: the features that perform best in classifying person’s valence and arousal while watching video clips with audiovisual emotional content are searched from a large feature set constructed from the EEG spectral powers of single channels as well as power diferences between speciic channel pairs. he feature selection is carried out using a sequential forward loating search method and is done separately for the classiication of valence and arousal, both derived from the emotional keyword that the subject had chosen ater seeing the clips. he proposed classiier-based approach reveals a clear association between the increased high-frequency (15–32 Hz) activity in the let temporal area and the clips described as “pleasant” in the valence and “medium arousal” in the arousal scale. hese clips represent the emotional keywords amusement and joy/happiness. he inding suggests the occurrence of a speciic neural activation during video-induced pleasant emotion and the possibility to detect this from the let temporal area using EEG. 1. Introduction he understanding and measurement of emotional expe- riences is a critical task in afective computing, a nascent ield of study to understand the technological implications and possibilities of emotional computing [1]. Ater a few centuries of scientiic study, the current understanding of emotional expressions and the multimodal nature of audiovi- sual experience of emotion have evolved much from the early treatises on emotion [2]. Old views that attribute emotions and expressions thereof to monopolar emotional labels of acquired qualities or even God-given abilities [2], which were famously countered by Darwin in his classic book [3] have been superseded by modern approaches. he search for an atomic fundamental representation of afect, beyond the concept of basic emotions popular during the last half century [4], has resulted in, among other models of emo- tion, for example, component models of cognitive appraisal, the modern paradigm of dimensional model of emotion in the last few decades [5–7]. While static emotional labels are still very much relevant, a two-dimensional bipolar circumplex model of valence and arousal [5] can be seen as an essential representation of the afective space enhancing the strict label-based views of categorical emotions by integrating the emotional labels into a looser more malleable continuous structure. he dimensional model of valence and arousal is thus an important foundation for the technological study of emotion allowing, for example, via a projection of distinct emotional class labels into a low dimensional representation, a more eicient description of emotional data. Due to the recent advance in functional imaging modal- ities, certain brain areas, such as limbic system’s anterior cingulate cortex, amygdala, orbitofrontal cortex, and insular cortex, have been associated with the processing of emotional stimuli [8]. Studies have also been addressed to explore the distinct brain systems responsible for the processing of Hindawi Publishing Corporation Computational Intelligence and Neuroscience Volume 2015, Article ID 762769, 14 pages http://dx.doi.org/10.1155/2015/762769