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.

[1]  Joydeep Ghosh,et al.  An overview of radial basis function networks , 2001 .

[2]  R. Kass,et al.  Multiple neural spike train data analysis: state-of-the-art and future challenges , 2004, Nature Neuroscience.

[3]  Li Yan,et al.  Dynamically structured radial basis function neural networks for robust aircraft flight control , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[4]  S P Levine,et al.  A direct brain interface based on event-related potentials. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[5]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[6]  K. Horch,et al.  Classification of action potentials in multi-unit intrafascicular recordings using neural network pattern-recognition techniques , 1994, IEEE Transactions on Biomedical Engineering.

[7]  Michael J. Black,et al.  Modeling and decoding motor cortical activity using a switching Kalman filter , 2004, IEEE Transactions on Biomedical Engineering.

[8]  A P Georgopoulos,et al.  On the relations between the direction of two-dimensional arm movements and cell discharge in primate motor cortex , 1982, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[9]  Dawn M. Taylor,et al.  Direct Cortical Control of 3D Neuroprosthetic Devices , 2002, Science.

[10]  Chein-I Chang,et al.  Robust radial basis function neural networks , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[11]  T.G. McNaughton,et al.  Action potential classification with dual channel intrafascicular electrodes , 1994, IEEE Transactions on Biomedical Engineering.

[12]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[13]  E. Schmidt,et al.  Fine control of operantly conditioned firing patterns of cortical neurons , 1978, Experimental Neurology.

[14]  Andrew R. Webb.  An approach to non-linear principal components analysis using radially symmetric kernel functions , 1996, Stat. Comput..

[15]  M S Lewicki,et al.  A review of methods for spike sorting: the detection and classification of neural action potentials. , 1998, Network.

[16]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[17]  Miguel A. L. Nicolelis,et al.  Brain–machine interfaces: past, present and future , 2006, Trends in Neurosciences.

[18]  Mita Nasipuri,et al.  Improved k-means algorithm in the design of RBF neural networks , 2003, TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region.

[19]  J. T. Massey,et al.  Mental rotation of the neuronal population vector. , 1989, Science.

[20]  Bernie Mulgrew,et al.  Applying radial basis functions , 1996, IEEE Signal Process. Mag..