Brain EEG Time Series Selection: A Novel Graph-Based Approach for Classification
This addresses EEG classification accuracy for brain disease diagnosis, representing a domain-specific incremental improvement.
The paper tackles the problem of noisy EEG signals degrading brain disease diagnosis by proposing a novel graph-based EEG selection method called mwcEEGs, which improves classification performance compared to state-of-the-art time series selection algorithms on real-world EEG datasets.
Brain Electroencephalography (EEG) classification is widely applied to analyze cerebral diseases in recent years. Unfortunately, invalid/noisy EEGs degrade the diagnosis performance and most previously developed methods ignore the necessity of EEG selection for classification. To this end, this paper proposes a novel maximum weight clique-based EEG selection approach, named mwcEEGs, to map EEG selection to searching maximum similarity-weighted cliques from an improved Fréchet distance-weighted undirected EEG graph simultaneously considering edge weights and vertex weights. Our mwcEEGs improves the classification performance by selecting intra-clique pairwise similar and inter-clique discriminative EEGs with similarity threshold $δ$. Experimental results demonstrate the algorithm effectiveness compared with the state-of-the-art time series selection algorithms on real-world EEG datasets.