Ben Dayan Rubin D D, Baselli G, Inbar G F, Cerutti S
Department of Biomedical Engineering, Politecnico di Milano, 20133 Milano, Italy.
Biol Cybern. 2004 Aug;91(2):63-75. doi: 10.1007/s00422-004-0500-8. Epub 2004 Aug 21.
This study aims to recover transient, trial-varying evoked potentials (EPs), in particular the movement-related potentials (MRPs), embedded within the background cerebral activity at very low signal-to-noise ratios (SNRs). A new adaptive neuro-fuzzy technique will attempt to estimate movement-related potentials within multi-channel EEG recordings, enabling this method to completely adapt to each input sweep without system training procedures. We assume that one of the sensors is corrupted by noise deriving from other sensors via an unknown function that will be estimated. We will approach this problem by: (1) spatially decorrelating the sensors in the preprocessing phase, (2) choosing the most informative of the filtered channels that will permit the best MRP estimation (input-selection phase) and (3) training the neuro-fuzzy model to fit the noise over the chosen sensor and therefore estimating the buried MRP. We tested this framework with simulations to validate the analytical results before applying them to the real biological data. Whenever it is applied to biological data, this method improves the SNR by more than 12 dB, even to very low SNRs. The processing method proposed here is likely to complement other estimation techniques and can be useful to process, enhance and analyse single-trial MRPs.
本研究旨在恢复瞬态、随试验变化的诱发电位（EPs），特别是嵌入极低信噪比（SNR）背景脑电活动中的运动相关电位（MRPs）。一种新的自适应神经模糊技术将尝试在多通道脑电图记录中估计运动相关电位，使该方法无需系统训练程序就能完全适应每个输入扫描。我们假设其中一个传感器被通过未知函数从其他传感器衍生而来的噪声所干扰，该未知函数将被估计。我们将通过以下方式解决这个问题：（1）在预处理阶段对传感器进行空间去相关，（2）选择最具信息性的滤波通道以实现最佳的MRP估计（输入选择阶段），以及（3）训练神经模糊模型以拟合所选传感器上的噪声，从而估计被掩埋的MRP。在将这些结果应用于真实生物数据之前，我们通过模拟测试了这个框架以验证分析结果。每当将该方法应用于生物数据时，即使对于非常低的SNR，它也能将SNR提高超过12 dB。这里提出的处理方法可能会补充其他估计技术，并且对于处理、增强和分析单次试验的MRPs可能是有用的。
