Neuroplasticity, also known as brain plasticity, is an inclusive term that covers the permanent changes in the brain during the course of an individual's life, and neuroplasticity can be broadly defined as the changes in function or structure of the brain in response to the external and/or internal influences. Long-term potentiation (LTP), a well-characterized form of functional synaptic plasticity, could be influenced by rapid-frequency stimulation (or “tetanus”) within in vivo human sensory pathways. Also, stochastic resonance (SR) has brought new insight into the field of visual processing for the study of neuroplasticity. In the present study, a brain-computer interface (BCI) intervention based on rapid and repetitive motion-reversal visual stimulation (i.e., a “tetanizing” stimulation) associated with spatiotemporal visual noise was implemented. The goal was to explore the possibility that the induction of LTP-like plasticity in the visual cortex may be enhanced by the SR formalism via changes in the amplitude of visual evoked potentials (VEPs) measured non-invasively from the scalp of healthy subjects. Changes in the absolute amplitude of P1 and N1 components of the transient VEPs during the initial presentation of the steady-state stimulation were used to evaluate the LTP-like plasticity between the non-noise and noise-tagged BCI interventions. We have shown that after adding a moderate visual noise to the rapid-frequency visual stimulation, the degree of the N1 negativity was potentiated following an ~40-min noise-tagged visual tetani. This finding demonstrated that the SR mechanism could enhance the plasticity-like changes in the human visual cortex.

No abstract

No abstract

Signal processing is one of the key points in brain computer interface (BCI) application. The common methods in BCI signal classification include canonical correlation analysis (CCA), support vector machine (SVM) and so on. However, because BCI signals are very complex and valid signals often come with confounded background noise, many current classification methods would lose meaningful information embedded in human EEGs. Otherwise, due to the huge inter-subject variability with respect to characteristics and patterns of BCI signals, there often exists large difference of classification accuracy among different subjects. Since BCI signals have high dimensionality and multi-channel properties, this paper proposes a novel structure of deep belief neural (DBN) network stacked by restricted boltsman machine (RBM) to extract efficient features from steady-state motion visual evoked potential signals and implement further classification. Here DBN extracts local feature from BCI data of each channel separately and fuses the local features, and then input the fused features to the output classifier which is consist of softmax units. Results proved that the proposed algorithm could achieve higher accuracy and lower inter-subject variability in short response time when compared to conventional CCA method.

No abstract