Fake Spike Removal Based on the Reconstruction Error of the KPCA

The effective detection of neuron spikes plays an important role in the brain-computer interface (BCI). In order to improve the reliability of spikes, the method based on the reconstruction error of Kernel principal component analysis (KPCA) is used to remove the fake spikes mixed in the detected spikes. Simulation experiments with different noise levels and different fake spikes ratios are carried out to verify the performance of the reconstruction error of KPCA. The results show that the KPCA method outperforms the traditional template matching method in removing fake spikes.

[1]  Kunal J. Paralikar,et al.  New approaches to eliminating common-noise artifacts in recordings from intracortical microelectrode arrays: Inter-electrode correlation and virtual referencing , 2009, Journal of Neuroscience Methods.

[2]  R. Quian Quiroga,et al.  Unsupervised Spike Detection and Sorting with Wavelets and Superparamagnetic Clustering , 2004, Neural Computation.

[3]  Kunal J. Paralikar,et al.  Collagenase-Aided Intracortical Microelectrode Array Insertion: Effects on Insertion Force and Recording Performance , 2008, IEEE Transactions on Biomedical Engineering.

[4]  Heiko Hoffmann,et al.  Kernel PCA for novelty detection , 2007, Pattern Recognit..

[5]  Andrew Jackson,et al.  Minimum requirements for accurate and efficient real-time on-chip spike sorting , 2014, Journal of Neuroscience Methods.

[6]  Rodrigo Quian Quiroga,et al.  Past, present and future of spike sorting techniques , 2015, Brain Research Bulletin.

[7]  Zhigang Shang,et al.  Automatic extracellular spike denoising using wavelet neighbor coefficients and level dependency , 2015, Neurocomputing.

[8]  Matias J. Ison,et al.  Realistic simulation of extracellular recordings , 2009, Journal of Neuroscience Methods.

[9]  Wenli Xu,et al.  Model selection of Gaussian kernel PCA for novelty detection , 2014 .

[10]  Lei Xie,et al.  Cross-validatory framework for optimal parameter estimation of KPCA and KPLS models , 2017 .

[11]  Jean-Michel Poggi,et al.  Multivariate denoising using wavelets and principal component analysis , 2006, Comput. Stat. Data Anal..