Skip to main navigation Skip to search Skip to main content

LMU-EEG: A Legendre Memory Unit Framework for Accurate Seizure Detection from EEG Signals

  • Danial Baharlouei
  • , Alireza Ahrar
  • , Maher Assaad
  • , Mostafa Rahimi Azghadi
  • , Amirali Amirsoleimani
  • York University Toronto
  • James Cook University Queensland

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents an energy-efficient seizure detection framework leveraging Legendre Memory Unit (LMU)based models, designed to address the challenges of long-range temporal modeling in EEG time-series data. LMUs offer a hardware-friendly alternative to conventional recurrent architectures by employing a fixed, linear time-invariant (LTI) memory system based on orthogonal Legendre polynomials, enabling precise temporal representation with minimal computational overhead. Our pipeline integrates signal preprocessing, frequency domain feature extraction, Random Forest-based EEG channel selection, class balancing via SMOTE, and LMU-based classification. Evaluated on the CHB-MIT Scalp EEG dataset, the proposed system achieves high sensitivity (average 97.26%) and low false detection rates (average 0.0329) across multiple subjects. These results demonstrate that LMUs not only outperform traditional models like LSTMs in detection accuracy and temporal capacity, but also maintain advantages critical for real-time, lowpower neurotechnologies.

Original languageEnglish
Title of host publicationProceedings - 21st IEEE Biomedical Circuits and Systems, BioCAS 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages249-253
Number of pages5
ISBN (Electronic)9798331573362
DOIs
StatePublished - 2025
Event21st IEEE Biomedical Circuits and Systems, BioCAS 2025 - Abu Dhabi, United Arab Emirates
Duration: 16 Oct 202518 Oct 2025

Publication series

NameProceedings - 21st IEEE Biomedical Circuits and Systems, BioCAS 2025

Conference

Conference21st IEEE Biomedical Circuits and Systems, BioCAS 2025
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period16/10/2518/10/25

Keywords

  • LSTM
  • Legendre Memory Unit
  • Linear Time-Invariant
  • Random Forest
  • SMOTE

Fingerprint

Dive into the research topics of 'LMU-EEG: A Legendre Memory Unit Framework for Accurate Seizure Detection from EEG Signals'. Together they form a unique fingerprint.

Cite this