基于径向基函数神经网络的多电极阵列信号脉冲电位的分类

通过径向基函数神经网络的分析,对神经元脉冲电位信号提出了新的分类方法。对原始信号进行峰电位检测,获得脉冲电位信号样本,以主成分进行预分类,选取与类中心方差小的典型脉冲电位集合作为径向基网络的训练样本,让神经网络进行自适应学习,以实现对原始信号的分类。仿真结果表明,在对模拟的脉冲电位信号进行分类时此方法的错误率比主成分聚类法和形状聚类法小。多电极细胞外记录的海马神经元细胞电活动信号应用此方法分类也取得了较好的效果。

Spike Sorting of Multielectrode Arrays Based on Radial Basis Function Neural Network

A new method was proposed to sort neural spikes using radial basis function manual neural network.Spikes of raw data were detected,and presorted by principle components analysis,the spikes which had the smaller square error to the center of these sorts were selected as the train set of radial basis function neural network.The manual neural network was trained and then identified the spikes of different sorts.Simulation results showed that the radial basis function neural network performed more efficiently than that of the principle components analysis cluster and the shape parameter cluster in the simulation data.And this method also perform well on the hippocampal neural network electrophysiology with extracellular recording in vitro from multielectrode arrays.