Emotion Recognition from EEG Network Connectivity Using Low-Dimensional Discriminant Analysis on Riemannian Manifolds

Emotion recognition from electroencephalogram (EEG) is key in developing affective brain-computer interfaces (BCIs).The functional interaction of brain networks encodes emotion.Using functional EEG network connectivity for emotion recognition is promising but remains difficult because of three challenges.First, EEG network connectivity is typically quantified by symmetric positive definite matrices represented on Riemannian manifolds, making existing Euclidean recognition methods not directly applicable.Second, the large EEG channel number leads to high-dimensional and noisy connectivity matrices that are difficult to classify.Third, aggregating EEG phase and spectral information on Riemannian manifolds remains elusive.Here, we develop a new Riemannian discriminant analysis (RDA) method for emotion recognition from high-dimensional EEG covariance, coherence, and cross-power spectrum density matrices.RDA projects connectivity matrices onto a low-dimensional Riemannian manifold and uses k-nearest neighbor classification on the low-dimensional manifold for emotion recognition.RDA further extends to the complex Fourier domain to incorporate phase information and uses Bayesian-based frequency fusion to aggregate spectral information.We demonstrate that RDA outperforms state-of-the-art methods on three representative EEG-emotion datasets (SEED, DEAP, and MAHNOB-HCI) and reveals the importance of frontal EEG connectivity in emotion recognition.Our results hold promise to effectively use brain network connectivity for emotion recognition in affective BCIs.