HCMay 23, 2018
Reworked Second Order Blind Identification and Support Vector Machine technique towards imagery movement identification from EEG signalsKalogiannis Gregory, Hassapis George
During imagery motor movements tasks, the so called mu and beta event related desynchronization (ERD) and synchronization (ERS) are taking place, allowing us to determine human patient imagery movement. However, initial recordings of electroencephalography (EEG) signals contain system and environmental noise as well as interference that must be ejected in order to separate the ERS/ERD events from the rest of the signal. This paper presents a new technique based on a reworked Second Order Blind Identification (SOBI) algorithm for noise removal while imagery movement classification is implemented using Support Vector Machine (SVM) technique.
HCMay 8, 2018
A reworked SOBI algorithm based on SCHUR Decomposition for EEG data processingKalogiannis Gregory, Karampelas Nikolaos, Hassapis George
In brain machine interfaces (BMI) that are used to control motor rehabilitation devices there is the need to process the monitored brain signals with the purpose of recognizing patient's intentions to move his hands or limbs and reject artifact and noise superimposed on these signals. This kind of processing has to take place within time limits imposed by the on-line control requirements of such devices. A widely-used algorithm is the Second Order Blind Identification (SOBI) independent component analysis (ICA) algorithm. This algorithm, however, presents long processing time and therefor it not suitable for use in the brain-based control of rehabilitation devices. A rework of this algorithm that is presented in this paper and based on SCHUR decomposition results to significantly reduced processing time. This new algorithm is quite appropriate for use in brain-based control of rehabilitation devices.