Shan'an Zhu

Learn More
Holes in the skull and the scalp are associated with intracranial monitoring procedures. The purpose of the present study is to evaluate the effects of holes on extracranial electroencephalogram (EEG) and intracranial electrocorticogram (ECoG) recordings. The finite difference method (FDM) was used to model the head volume conductor with a hole of varying(More)
The question of how many channels should be sed for classification remains a key issue in the study of Brain-Computer Interface. Several studies have shown that a reduced number of channels can achieve the optimal classification accuracy in the offline analysis of motor imagery paradigm, which does not have real-time feedback as in the online control.(More)
We have applied the magnetic resonance electrical impedance imaging (MREIT) technique to image the three-dimensional (3D) conductivity distribution of the human head. Computer simulations were carried out on a tradition four-sphere head model to test the feasibility of imaging conductivity distribution of the human head. The present results show that the 3D(More)
BACKGROUND For sensorimotor rhythms based brain-computer interface (BCI) systems, classification of different motor imageries (MIs) remains a crucial problem. An important aspect is how many scalp electrodes (channels) should be used in order to reach optimal performance classifying motor imaginations. While the previous researches on channel selection(More)
EEG source localization can be considered as a nonlinear optimization process. In the present study, a hybrid genetic algorithm (HGA) is introduced, which combines genetic and local search strategies to overcome the disadvantages of conventional genetic algorithm and local optimization methods. This HGA algorithm was used to localize two dipoles from scalp(More)
A finite difference method (FDM) has been implemented to solve the electroencephalogram (EEG) forward problem. This method has been evaluated by means of computer simulations, by comparing with analytic solutions in a three-sphere concentric head model. The effects of dipole eccentricity, spacing of finite difference model and number of grid nodes on(More)
Magnetoacoustic tomography with magnetic induction (MAT-MI) is a noninvasive imaging modality for generating electrical conductivity images of biological tissues with high spatial resolution. In this paper, we create a numerical model, including a permanent magnet, a coil, and a two-layer coaxial cylinder with anisotropic electrical conductivities, for the(More)
AbstrAct Input selection is an important step in nonlinear regression modeling. By input selection, an inter-pretable model can be built with less computational cost. Input selection thus has drawn great attention in recent years. However, most available input selection methods are model-based. In this case, the input data selection is insensitive to(More)
A new method based on convolution kernel compensation (CKC) for decomposing multi-channel surface electromyogram (sEMG) signals is proposed in this paper. Unsupervised learning and clustering function of self-organizing map (SOM) neural network are employed in this method. An initial innervations pulse train (IPT) is firstly estimated, some time instants(More)