PSO-based dimension reduction of EEG recordings: Implications for subject transfer in BCI

摘要: Subject transfer is a growing area of research in EEG aiming to address the lack having enough samples required for BCI by using originating from individuals or groups subjects that previously performed similar tasks. This paper investigates feasibility two frameworks enhancing subject through 90%+ reduction features and electrodes Particle Swarm Optimization (PSO). In first framework, selected PSO individual are combined into single ''meta-mask'' be applied new subject. second preprocessed multiple concatenated ''super subject'', which selects use on The study focused finding optimal mixture either proposed addition investigating impact various electrode selections. results indicate important role an expertise subjects' data.