Automatic subject-specific spatiotemporal feature selection for subject-independent affective BCI

• Published in: PloS one Vol. 16; no. 8; p. e0253383
• Main Authors: Almarri, Badar, Rajasekaran, Sanguthevar, Huang, Chun-Hsi
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 26.08.2021; Public Library of Science (PLoS)
• Subjects: Algorithms; Analysis; Arousal; Benchmarks; Biology and Life Sciences; Brain research; Channels; Cognition & reasoning; Communication; Computer and Information Sciences; Computer science; Data mining; Datasets; EEG; Electrodes; Electroencephalography; Emotion recognition; Emotions; Engineering and Technology; Feature extraction; Feature selection; Human-computer interface; Information management; Interfaces; Learning; Machine learning; Medicine and Health Sciences; Neurophysiology; Outliers (statistics); Physical Sciences; Physiology; Research and Analysis Methods; Social Sciences; Support vector machines; Temporal resolution; Time series; United States; United States > US

The dimensionality of the spatially distributed channels and the temporal resolution of electroencephalogram (EEG) based brain-computer interfaces (BCI) undermine emotion recognition models. Thus, prior to modeling such data, as the final stage of the learning pipeline, adequate preprocessing, trans...