BPE for classifying clinical EEG_Sep29.pdf (1.6 MB)
Download file

Byte-Pair Encoding for classifying routine clinical electroencephalograms in adults over the lifespan

Download (1.6 MB)
posted on 2022-10-05, 20:42 authored by Mykola KlymenkoMykola Klymenko, Sam M. Doesburg, George Medvedev, Pengcheng Xi, Urs Ribary, Vasily A. Vakorin

Our study considered the problem of classifying routine clinical EEG. We incorporated NLP tools into the workflow for time series classification. We transformed EEG signals into strings of symbols. We then applied byte-pair encoding (BPE) to split the new text into combinations of symbols or tokens, each associated with different patterns of changes in EEG amplitude. We validated the proposed workflow under the framework of predicting patients' biological age.


National Research Council (NRC) of Canada, Collaborative Research and Development Grant DHGA-116-1

Digital Research Alliance of Canada, Research Platforms and Portals (RPP) grant


Email Address of Submitting Author

ORCID of Submitting Author


Submitting Author's Institution

Simon Fraser University, BC, Canada

Submitting Author's Country

  • Ukraine