The primary purpose of this thesis is to design an experiment, which can be used for quantifying pain. This was made possible by using dry electroencephalography (EEG) in conjunction with a Support Vector Machines classifier (SVM). Normal gel-based electrode EEG has been validated as a reliable tool for objectively measuring pain. Yet, to date there are few documented trials, which use dry-EEG for pain quantification. SVM classifiers have been proved accurate, when classifying pain intensity. Therefore, we believe EEG combined with SVM could increase statistical power in pain classification. Due to the subjectivity of pain, currently clinicians mainly rely on the patient self-report. In addition, hyper/low sensitivity to pain may vary in certain cultures and backgrounds, which may be perceived as drug seeking behavior by clinicians. Therefore, this research could offer the tools needed to objectively describe pain, eliminate observer error, and individualize treatment based on background and culture.