Emotional EEG Classification using Upscaled Connectivity Matrices
This work addresses a limitation in EEG-based emotion recognition for applications like brain-computer interfaces, but it is incremental as it builds on existing CNN methods with a simple modification.
The paper tackled the problem of important patterns being lost in connectivity matrices during convolutional operations for emotional EEG classification, and proposed upscaling these matrices to strengthen local patterns, resulting in significantly enhanced classification performance.
In recent studies of emotional EEG classification, connectivity matrices have been successfully employed as input to convolutional neural networks (CNNs), which can effectively consider inter-regional interaction patterns in EEG. However, we find that such an approach has a limitation that important patterns in connectivity matrices may be lost during the convolutional operations in CNNs. To resolve this issue, we propose and validate an idea to upscale the connectivity matrices to strengthen the local patterns. Experimental results demonstrate that this simple idea can significantly enhance the classification performance.