Olfaction-enhanced multimedia experience is becoming vital for strengthening the sensation of reality and the quality of user experience. One approach to investigate olfactory perception is to analyze the alterations in brain activity during stimulation with different odors. In this article, the changes in the electroencephalogram (EEG) when perceiving hedonically-different odors are studied. Results of within and across-subject analysis are presented. We show that EEG-based odor classification using brain activity is possible and can be used to automatically recognize odor pleasantness when a subject-specific classifier is trained. However, it is a challenging problem to design a generic classifier.