Assessing the effectiveness of spatial PCA on SVM-based decoding of EEG data

• Published in: NeuroImage (Orlando, Fla.) Vol. 293; p. 120625
• Main Authors: Zhang, Guanghui, Carrasco, Carlos D., Winsler, Kurt, Bahle, Brett, Cong, Fengyu, Luck, Steven J.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.06.2024; Elsevier Limited; Elsevier
• Subjects: Adult; Brain - physiology; Dimensionality reduction; EEG; Electroencephalography; Electroencephalography - methods; Event-related potentials; Evoked Potentials - physiology; Female; Group-based PCA; Humans; Male; Mismatch negativity; MVPA; Performance evaluation; Principal Component Analysis; Principal components analysis; Signal Processing, Computer-Assisted; Subject-based PCA; Support Vector Machine; Young Adult; Dimensionality reduction; Group-based PCA; Subject-based PCA; EEG; MVPA
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2024.120625

Principal component analysis (PCA) has been widely employed for dimensionality reduction prior to multivariate pattern classification (decoding) in EEG research. The goal of the present study was to provide an evaluation of the effectiveness of PCA on decoding accuracy (using support vector machines) across a broad range of experimental paradigms. We evaluated several different PCA variations, including group-based and subject-based component decomposition and the application of Varimax rotation or no rotation. We also varied the numbers of PCs that were retained for the decoding analysis. We evaluated the resulting decoding accuracy for seven common event-related potential components (N170, mismatch negativity, N2pc, P3b, N400, lateralized readiness potential, and error-related negativity). We also examined more challenging decoding tasks, including decoding of face identity, facial expression, stimulus location, and stimulus orientation. The datasets also varied in the number and density of electrode sites. Our findings indicated that none of the PCA approaches consistently improved decoding performance related to no PCA, and the application of PCA frequently reduced decoding performance. Researchers should therefore be cautious about using PCA prior to decoding EEG data from similar experimental paradigms, populations, and recording setups. •We evaluated the impact of PCA on EEG/ERP SVM-based decoding performance.•We examined a broad set of datasets, spanning easy and difficult decoding tasks collected with different electrode densities.•We varied the numbers of principal components and tried several PCA approaches.•We found that PCA-based dimensionality reduction did not improve SVM-based decoding performance.