Application of cross-correlated delay shift rule in spiking neural networks for interictal spike detection

Lilin Guo; Zhenzhong Wang; Mercedes Cabrerizo; Malek Adjouadi

doi:10.1109/EMBC.2016.7590821

Application of cross-correlated delay shift rule in spiking neural networks for interictal spike detection

Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug:2016:796-799. doi: 10.1109/EMBC.2016.7590821.

Authors

Lilin Guo, Zhenzhong Wang, Mercedes Cabrerizo, Malek Adjouadi

PMID: 28268446
DOI: 10.1109/EMBC.2016.7590821

Abstract

This study proposes a Cross-Correlated Delay Shift (CCDS) supervised learning rule to train neurons with associated spatiotemporal patterns to classify spike patterns. The objective of this study was to evaluate the feasibility of using the CCDS rule to automate the detection of interictal spikes in electroencephalogram (EEG) data on patients with epilepsy. Encoding is the initial yet essential step for spiking neurons to process EEG patterns. A new encoding method is utilized to convert the EEG signal into spike patterns. The simulation results show that the proposed algorithm identified 69 spikes out of 82 spikes, or 84% detection rate, which is quite high considering the subtleties of interictal spikes and the tediousness of monitoring long EEG records. This CCDS rule is also benchmarked by ReSuMe on the same task.

MeSH terms

Action Potentials
Algorithms
Electroencephalography*
Epilepsy / diagnosis*
Humans
Machine Learning
Models, Theoretical
Neural Networks, Computer*
Neurons / physiology