Algorithmic clustering based on string compression to extract P300 structure in EEG signals

• Published in: Computer methods and programs in biomedicine Vol. 176; pp. 225 - 235
• Main Authors: Sarasa, Guillermo, Granados, Ana, Rodriguez, Francisco B.
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.07.2019
• Subjects: Algorithms; Brain - physiology; Brain computer interface; Brain-Computer Interfaces; Cluster Analysis; Clustering by compression; Computer Simulation; Data Compression - methods; Data mining; Dendrogram; Electrodes; Electroencephalography; Event-Related Potentials, P300; Humans; Kolmogorov complexity; Multidimensional projections; Normalized compression distance; Silhouette coefficient; Similarity; Clustering by compression; Multidimensional projections; Normalized compression distance; Similarity; Kolmogorov complexity; Silhouette coefficient; Brain computer interface; Data mining; Dendrogram

•String-based approach to convert EEG signals into suitable objects for NCD analysis.•Methodology for structural P300-ERP identification through clustering by compression.•Normalized Compression Distance (NCD) extracts the main structure of P300-ERP on EEG signals.•Two distinct NCD-driven clustering...