Name
Abstract | ||
|---|---|---|
Spike sorting is the essential step in analyzing recording spike signals for studying information processing mechanisms within the nervous system. Overlapping is one of the most serious problems in the spike sorting for multi-channel recordings. In this paper, a modified radial basis function (RBF) network is proposed to decompose the overlapping signals and separate spikes within the same RBF network. A modified radial basis function based on the Gaussian function is employed in the method to improve the accuracy of overlap decomposition. In addition, the improved constructing algorithm reduces the calculation cost by taking advantage of the symmetry of the RBF network. The performance of the presented method is tested at various signal-to-noise ratio levels based on simulated data coming from the University of Leicester and Wave-clus software. Experiment results show that our method successfully solves the fully overlapping problem and has higher accuracy comparing with the Gaussian function. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICNC.2010.5582921 | Computers & Mathematics with Applications |
Keywords | Field | DocType |
modified radial basis function,radial basis function network,overlapping problem,overlapping signal,separate spike,wave-clus software,recording spike signal,gaussian function,modified radial basis,higher accuracy,rbf network,radial basis function,information processing,signal processing,signal to noise ratio,classification algorithms,shape,nervous system,accuracy,sorting,gaussian processes | Radial basis function network,Radial basis function,Pattern recognition,Spike sorting,Computer science,Signal-to-noise ratio,Sorting,Gaussian process,Artificial intelligence,Statistical classification,Gaussian function,Machine learning | Journal |
Volume | Issue | ISSN |
62 | 7 | 0898-1221 |
Citations | PageRank | References |
1 | 0.39 | 3 |
Authors | ||
2 | ||