Applicability of Hyperdimensional Computing for Seizure Prediction Using LBP and PSD Features from iEEG

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Hyperdimensional computing (HDC) has been assumed to be attractive for time-series classification. These classifiers are ideal for one or few-shot learning and require fewer resources. These classifiers have been demonstrated to be useful in seizure detection. This paper investigates subject-specific seizure prediction using HDC from intracranial elec-troencephalogram (iEEG) from the publicly available Kaggle dataset. In comparison to seizure detection (interictal vs. ictal), seizure prediction (interictal vs. preictal) is a more challenging problem. Two HDC-based encoding strategies are explored: local binary pattern (LBP) and power spectral density (PSD). The average performance of HDC classifiers using the two encoding approaches is computed using the leave-one-seizure-out cross-validation method. Experimental results show that the PSD method using a small number of features selected by the minimum redundancy maximum relevance (mRMR) achieves better seizure prediction performance than the LBP method on the trairring and validation data.

Original languageEnglish (US)
Title of host publication2023 IEEE 66th International Midwest Symposium on Circuits and Systems, MWSCAS 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1065-1069
Number of pages5
ISBN (Electronic)9798350302103
DOIs
StatePublished - 2023
Externally publishedYes
Event2023 IEEE 66th International Midwest Symposium on Circuits and Systems, MWSCAS 2023 - Tempe, United States
Duration: Aug 6 2023Aug 9 2023

Publication series

NameMidwest Symposium on Circuits and Systems
ISSN (Print)1548-3746

Conference

Conference2023 IEEE 66th International Midwest Symposium on Circuits and Systems, MWSCAS 2023
Country/TerritoryUnited States
CityTempe
Period8/6/238/9/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

  • Hyperdimensional computing (HDC)
  • local binary pattern (LBP)
  • minimum redundancy maximum relevance (mRMR)
  • power spectral density (PSD)
  • seizure prediction

Fingerprint

Dive into the research topics of 'Applicability of Hyperdimensional Computing for Seizure Prediction Using LBP and PSD Features from iEEG'. Together they form a unique fingerprint.

Cite this