Analysis of Affective State from Galvanic Skin Response Using Correlation Dimension and Embedding Dimension

In order to analyzing the differentiation of affective state from the Galvanic Skin Response, this paper does research on the combination of the embedding dimension and correlation dimension with nonlinear features. It uses the G-P algorithm to compute the connection points under the specific embedding dimension and unites the least squares (LS) to make nonlinear fitting on the connection points, the fitting slope is the correlation dimension, so the relationship of embedding dimension and correlation dimension can be got. through the relationship, the experimental results show that it can obvious distinguish the four affective of the Galvanic Skin Response, that means the method in this paper can be used in the differentiation of affective state from the Galvanic Skin Response.