Exploring the Use of Spatial Information in Emotion Classification Using Functional Connectivity and Channel Distribution

Advancements in neuroscience, especially in estimation technique of functional connectivity and brain networks, have been instrumental in emotion classification. However, conventional methods that utilize feature vectors or connectivity matrices do not entirely harness the spatial information of brain activity. We propose the Sliding Functional Connectivity Convolution (SFCC), which constructs brain networks by leveraging the spatial information of channel distribution of electroencephalogram (EEG). Similar to image convolution, SFCC begins by defining a matrix to be processed and an operation kernel, both derived from a channel projection. We then calculate the functional connectivity between the matrix elements and elements of the kernel while sliding the kernel across the matrix. The resultant brain networks provide additional spatial information for a classifier compared to conventional methods. Comparison between brain networks constructed using conventional feature vectors and connectivity matrices with those created by the proposed method showed a significant enhancement in classification performance.