Analysis of neuronal ensembles encoding model in invasive brain-computer interface study using Radial-Basis-Function networks

In this paper, radial basis function (RBF) network is applied to achieve the discrimination of ratpsilas behavior by encoding and decoding the ratpsilas motor cortical activity. Firstly, the brain neuronal action potentials during extending and flexing behaviors of ratspsila forearms are recorded. Secondly, the neuronal action potentials are classified based on principal component analysis (PCA) and K-means cluster methods. Thirdly, the firing frequency of each neuron during the behaviors are calculated. Lastly, the neuronal ensembles encoding model is characterized based on RBF. We use the firing frequency as the input of the RBF network, and the RBF network will give the behavior state as its output. When analyzing the encoding of ratspsila extending and flexing behaviors, we get the encoding performance of 93%. The result is better than that of back-propagate (BP) neural network and k-means cluster. Therefore, radial basis function (RBF) network is an effective tool for neuron ensembles encoding.