Abstract

Neural spike sorting refers to the classification of electric potentials (spikes) from multi-neuron recordings, a difficult but essential pre-processing step before neural data can be analyzed for information content. In this paper, we propose a novel method of multineuronal spike sorting based on rough set theory. In the experiments, the performance of the presented system was tested at various signal-to-noise ratio levels based on synthetic data. The trained rough set classifier yields satisfactory correct ratio on synthesis data. In contrast with other methods such as artificial neural network classifiers, classification model based on rough set theory provides intelligible knowledge about sorting of neural spikes, while in the artificial neural network methods the sorting spike sorting ability is hidden in the weights and structures of networks. Neurophysiology researchers could supply physiological interpretation of the sorting knowledge.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call