An emotion recognition system on the basis of physiological signals is presented in this paper. electroencephalographic signals of the brain (EEG) and peripheral physiological signals is passe through a multimodal fusion process. three specific areas of valance-arousal emotional space is used. The acquisition protocol used here is based on a subset of pictures which correspond to this arousal emotional space. Preprocessing and feature extraction methods are so optimised so that emotion-specific characteristics can be extracted from input signals very easily. peripheral signals,
EEG’s, and both are alternately used to evaluate the performance of two classifiers. The stiudies and results imply the need for using brain signals as peripherals in emotion assessment.

METHODOLOGY
-Dataset Description
The database of this work is available on enterface.net which is a site of an organisation at establishing a tradition of collaborative, localized research and development work by gathering, in a single place, a group of senior project leaders, researchers.

-preprocessing and feature extraction
The information bearing features are extracted for classification.
-Peripheral features
GSR referred to Galvanic skin Resistance, basically measures the conductivity of the skin, which increases, if the skin is sweaty. Mean, Mean of derivative, Mean of derivative for negative
values, proportion of negative samples in the derivative vs. all samples are the features that are extracted.

For more details, refer the report available at:
http://bme.aut.ac.ir/mhmoradi/EN.Confere...ignals.pdf