A "single-trial" signal subspace approach for extracting visual evoked potential (VEP) from the ongoing 'colored' electroencephalogram (EEG) noise is proposed. The algorithm applies the generalized eigendecomposition on the covariance matrices of the VEP and noise to transform them jointly into diagonal matrices in order to avoid a pre-whitening stage. The proposed generalized subspace approach (GSA) decomposes the corrupted VEP space into a signal subspace and noise subspace. Enhancement is achieved by removing the noise subspace and estimating the clean VEPs only from the signal subspace. The validity and effectiveness of the proposed GSA scheme in estimating the latencies of P100's (used in objective assessment of visual pathways) are evaluated using real data collected from Selayang Hospital in Kuala Lumpur. The performance of GSA is compared with the recently proposed single-trial technique called the Third Order Correlation (TOC).
Human brain generates electromagnetic signals during certain activation inside the brain. The localization of the active sources which are responsible for such activation is termed as brain source localization. This process of source estimation with the help of EEG which is also known as EEG inverse problem is helpful to understand physiological, pathological, mental, functional abnormalities and cognitive behaviour of the brain. This understanding leads for the specification for diagnoses of various brain disorders such as epilepsy and tumour. Different approaches are devised to exactly localize the active sources with minimum localization error, less complexity and more validation which include minimum norm, low resolution brain electromagnetic tomography (LORETA), standardized LORETA, exact LORETA, Multiple Signal classifier, focal under determined system solution etc. This paper discusses and compares the ability of localizing the sources for two low resolution methods i.e., sLORETA and eLORETA respectively. The ERP data with visual stimulus is used for comparison at four different time instants for both methods (sLORETA and eLORETA) and then corresponding activation in terms of scalp map, slice view and cortex map is discussed.