Spike sorting via Multi Cluster Feature Selection
Dinparast Djadid, Azadeh
MetadataShow full item record
Having the ability to study the activity of single neurons will facilitate studies in many areas including cognitive sciences and brain computer interface applications. Due to the fact that every neuron has it’s own unique spike waveform, by applying spike-sorting methods, one can separate the neurons based on their associated spike. Spike sorting is an unsupervised learning problem in the realm of data mining and machine learning. In this study, a new method that will improve the accuracy of spike sorting in comparison to existing methods has been introduced. This method, which is named Multi Cluster Feature Selection (MCFS), will designate a reduced number of features from the original data set that will best differentiate the existing clusters by solving a Least Absolute Shrinkage and Shrinkage Operator (LASSO) optimization problem. MCFS was also applied to data obtained from a multi channel recording on a rat’s brain. In this experiment, the rat was exposed to noises with different levels of intensity for specified periods of time. With MCFS, each channel was studied and after sorting the neurons existing in the selected channel, the effect of the level of intensity of noise on individual neurons was studied. The eventual result was that, as the intensity of the noise increase the number of action potentials in the neurons increased.