Transfer-Learning for Automated Seizure Detection Based on Electric Field Encephalography Reconstructed Signal

Building an automatic seizure onset prediction model based on multi-channel electroencephalography (EEG) signals has been a hot topic in computer science and neuroscience field for a long time. In this research, we collect EEG data from different epilepsy patients and EEG devices and reconstruct and combine the EEG signals using an innovative electric field encephalography (EFEG) method, which establishes a virtual electric field vector, enabling extraction of electric field components and increasing detection accuracy compared to the conventional method. We extract a number of important features from the reconstructed signals and pass them through an ensemble model based on support vector machine (SVM), Random Forest (RF), and deep neural network (DNN) classifiers. By applying this EFEG channel combination method, we can achieve the highest detection accuracy at 87% which is 6% to 17% higher than the conventional channel averaging combination method. Meanwhile, to reduce the potential overfitting problem caused by DNN models on a small dataset and limited training patient, we ensemble the DNN model with two “weaker” classifiers to ensure the best performance in model transferring for different patients. Based on these methods, we can achieve the highest detection accuracy at 82% on a new patient using a different EEG device. Thus, we believe our method has good potential to be applied on different commercial and clinical devices.

Multisensory mechanisms of gait and balance in Parkinson’s disease:an integrative review

Understanding the neural underpinning of human gait and balance is one of the most pertinent challenges for 21st-century translational neuroscience due to the profound impact that falls and mobility disturbances have on our aging population.Posture and gait control does not happen automatically,as previously believed,but rather requires continuous involvement of central nervous mechanisms.To effectively exert control over the body,the brain must integrate multiple streams of sensory information,including visual,vestibular,and somatosensory signals.The mechanisms which underpin the integration of these multisensory signals are the principal topic of the present work.Existing multisensory integration theories focus on how failure of cognitive processes thought to be involved in multisensory integration leads to falls in older adults.Insufficient emphasis,however,has been placed on specific contributions of individual sensory modalities to multisensory integration processes and cross-modal interactions that occur between the sensory modalities in relation to gait and balance.In the present work,we review the contributions of somatosensory,visual,and vestibular modalities,along with their multisensory intersections to gait and balance in older adults and patients with Parkinson’s disease.We also review evidence of vestibular contributions to multisensory temporal binding windows,previously shown to be highly pertinent to fall risk in older adults.Lastly,we relate multisensory vestibular mechanisms to potential neural substrates,both at the level of neurobiology(concerning positron emission tomography imaging)and at the level of electrophysiology(concerning electroencephalography).We hope that this integrative review,drawing influence across multiple subdisciplines of neuroscience,paves the way for novel research directions and therapeutic neuromodulatory approaches,to improve the lives of older adults and patients with neurodegenerative diseases.