Subject Selection on a Riemannian Manifold for Unsupervised Cross-subject Seizure Detection
This work addresses the challenge of cross-subject seizure detection in EEG analysis, offering an incremental improvement over existing methods.
The paper tackled the problem of inter-subject variability in brain signal analysis by proposing a subject-selection algorithm based on clustering covariance matrices on a Riemannian manifold, resulting in increased accuracy from 86.83% to 89.84% and reduced false positive rate from 0.8/hour to 0.77/hour for seizure detection.
Inter-subject variability between individuals poses a challenge in inter-subject brain signal analysis problems. A new algorithm for subject-selection based on clustering covariance matrices on a Riemannian manifold is proposed. After unsupervised selection of the subsets of relevant subjects, data in a cluster is mapped to a tangent space at the mean point of covariance matrices in that cluster and an SVM classifier on labeled data from relevant subjects is trained. Experiment on an EEG seizure database shows that the proposed method increases the accuracy over state-of-the-art from 86.83% to 89.84% and specificity from 87.38% to 89.64% while reducing the false positive rate/hour from 0.8/hour to 0.77/hour.