径向基函数网络在体感诱发电位实时监测中的应用

Application of multi-adaptive filter based on radial basis function neural network for real-time somatosensory evoked potential monitoring

目的 针对体感诱发电位（SEP）的特征,设计基于径向基函数网络的复合自适应滤波器,实现体感诱发电位的快速提取.方法通过径向基函数网络的关键参数优化选择,对基于径向基函数网络的复合自适应滤波器与以自适应信号增强器和自适应噪声消除器为基础构造的复合自适应滤波器提取体感诱发电位的性能进行比较分析.结果仿真实验表明：基于径向基函数神经网络的复合自适应滤波器拟合出的SEP信号,在波形上基本与模板信号相似,并且比已有复合自适应滤波器拟合出的波形更为平滑.结论 基于径向基函数网络的复合自适应滤波器新算法可实现从强噪声背景中快速提取体感诱发电位,能更快地识别体感诱发电位的潜伏期及幅值,实现单次提取,并且系统性能稳定.

Objective To design multi-adaptive filter based on radial basis function （MAF-RBF） for efficiently extracting somatosensory evoked potential （SEP） in real-time SEP monitoring. Methods With the optimization of important parameters that influence the performance of radial basis function neural network, the performance of extracting SEP was compared to that of a multi-adaptive filter （MAF）, which developed from the combination of well-developed adaptive noise canceller and adaptive signal enhancer. Results In this simulation study, the outputs of MAF-RBF showed a similar waveform with SEP template signals, and a smoother waveform than the .output of MAF. Conclusion With appropriate parameter values, MAF-RBFNN is able to extract the latency and amplitude of SEP from the extremely noisy background rapidly and reliably without averaging.