RESUMO
Motor Imagery (MI) promotes motor learning in activities, like developing professional motor skills, sports gestures, and patient rehabilitation. However, up to 30% of users may not develop enough coordination skills after training sessions because of inter and intra-subject variability. Here, we develop a data-driven estimator, termed Deep Regression Network (DRN), which jointly extracts and performs the regression analysis in order to assess the efficiency of the individual brain networks in practicing MI tasks. The proposed double-stage estimator initially learns a pool of deep patterns, extracted from the input data, in order to feed a neural regression model, allowing for infering the distinctiveness between subject assemblies having similar variability. The results, which were obtained on real-world MI data, prove that the DRN estimator fosters pre-training neural desynchronization and initial training synchronization to predict the bi-class accuracy response, thus providing a better understanding of the Brain-Computer Interface inefficiency of subjects.
RESUMO
The sensorimotor rhythm (SMR) is an electroencephalographic rhythm associated with motor and cognitive development observed in the central brain regions during wakefulness in the absence of movement, and it reacts contralaterally to generalized and hemibody movements. The purpose of this work was to characterize the SMR of 4-month-old infants, born either healthy at term or prematurely with periventricular leukomalacia (PVL). Two groups of infants were formed: healthy and premature with PVL. Their electroencephalograms (EEGs) were recorded in four conditions: rest, free movement, right-hand grasping and left-hand grasping, in order to explore general reactivity to free movement and contralateral reactivity in hand-grasping conditions. Associations between SMR, and cognitive and motor performance were analyzed. The healthy infants showed a SMR between 5.47 and 7.03 Hz, with clear contralateral reactivity to free movement and right-hand grasping. However, the premature infants with PVL did not show enough electroencephalographic characteristics to evidence the presence of SMR. Poor performance, characteristic of children with PVL, was related to low-frequency SMR, while good performance was associated with a higher frequency rhythm in the left hemisphere. The presence of SMR in the group of healthy infants could be considered a sign of health at this age. Thus, poor SMR evidence in the EEG of infants with PVL is probably a sign of brain immaturity or brain dysfunction. Our results provide data on infant SMR development that is needed to design neurofeedback protocols for infants with PVL.