Table 6.

Summary of feature extraction methods.

	Method	Properties	Applications
Dimension reduction	PCA	– Linear transformation – Set of possibly correlated observations is transformed into a set of uncorrelated variables – Optimal representation of data in terms of minimal mean-square-error – No guarantees always a good classification – Valuable noise and dimension reduction method. PCA requires that artifacts are uncorrelated with the EEG signal	[155,157,158]
	ICA	– Splits a set of mixed signals into its sources – Mutual statistical independence of underlying sources is assumed – Powerful and robust tool for artifact removal. Artifacts are required to be independent from the EEG signal – May corrupt the power spectrum	[160,161,164–168]
Space	CSP	– Spatial filter designed for 2-class problems. Multiclass extensions exist – Good result for synchronous BCIs. Less effective for asynchronous BCIs – Its performance is affected by the spatial resolution. Some electrode locations offer more discriminative information for some specific brain activities than others – Improved versions of CSP: WCSP, CSSP, CSSSP	[183–187]
Time-frequency	AR	– Spectrum model – High frequency resolution for short time segments – Not suitable for non-stationary signals – Adaptive version of AR: MVAAR	[170,172]
	MF	– Detects a specific pattern on the basis of its matches with predetermined known signals or templates – Suitable for detection of waveforms with consistent temporal characteristics	[151,173]
	CWT	– Provides both frequency and temporal information – Suitable for non-stationary signals	[179,180]
	DWT	– Provides both frequency and temporal information – Suitable for non-stationary signals – Reduces the redundancy and complexity of CWT	[181,182]