New approaches for EEG signal processingartifact EOG removal by ICA-RLS scheme and tracks extraction method

Resumen

Localizing the bioelectric phenomena originating from the cerebral cortex and evoked by auditory and somatosensory stimuli are clear objectives to both understand how the brain works and to recognize different pathologies. Diseases such as Parkinson’s, Alzheimer’s, schizophrenia and epilepsy are intensively studied to find a cure or accurate diagnosis. Epilepsy is considered the disease with major prevalence within disorders with neurological origin. The recurrent and sudden incidence of seizures can lead to dangerous and possibly life-threatening situations. Since disturbance of consciousness and sudden loss of motor control often occur without any warning, the ability to predict epileptic seizures would reduce patients’ anxiety, thus considerably improving quality of life and safety. The common procedure for epilepsy seizure detection is based on brain activity monitorization via electroencephalogram (EEG) data. This process consumes a lot of time, especially in the case of long recordings, but the major problem is the subjective nature of the analysis among specialists when analyzing the same record. From this perspective, the identification of hidden dynamical patterns is necessary because they could provide insight into the underlying physiological mechanisms that occur in the brain. Time-frequency distributions (TFDs) and adaptive methods have demonstrated to be good alternatives in designing systems for detecting neurodegenerative diseases. TFDs are appropriate transformations because they offer the possibility of analyzing relatively long continuous segments of EEG data even when the dynamics of the signal are rapidly changing. On the other hand, most of the detection methods proposed in the literature assume a clean EEG signal free of artifacts or noise, leaving the preprocessing problem opened to any denoising algorithm. In this thesis we have developed two proposals for EEG signal processing: the first approach consists in electrooculogram (EOG) removal method based on a combination of ICA and RLS algorithms which automatically cancels the artifacts produced by eyes movement without the use of external “ad hoc” electrode. This method, called ICA-RLS has been compared with other techniques that are in the state of the art and has shown to be a good alternative for artifacts rejection. The second approach is a novel method in EEG features extraction called tracks extraction (LFE features). This method is based on the TFDs and partial tracking. Our results in pattern extractions related to epileptic seizures have shown that tracks extraction is appropriate in EEG detection and classification tasks, being practical, easily applicable in medical environment and has acceptable computational cost.