Emotional EEG Classification using Connectivity Features and Convolutional Neural Networks
This work addresses the challenge of accurately recognizing emotional states from EEG data for applications in brain-computer interfaces and affective computing, representing an incremental improvement by integrating connectivity measures into existing CNN frameworks.
The paper tackled the problem of classifying emotional states from EEG signals by introducing a system that incorporates brain connectivity features with convolutional neural networks, achieving improved classification performance validated on emotional video classification tasks.
Convolutional neural networks (CNNs) are widely used to recognize the user's state through electroencephalography (EEG) signals. In the previous studies, the EEG signals are usually fed into the CNNs in the form of high-dimensional raw data. However, this approach makes it difficult to exploit the brain connectivity information that can be effective in describing the functional brain network and estimating the perceptual state of the user. We introduce a new classification system that utilizes brain connectivity with a CNN and validate its effectiveness via the emotional video classification by using three different types of connectivity measures. Furthermore, two data-driven methods to construct the connectivity matrix are proposed to maximize classification performance. Further analysis reveals that the level of concentration of the brain connectivity related to the emotional property of the target video is correlated with classification performance.