Optimal Time Window and Frequency Bandwidth Parameter Combination for Subject-Specific Motor Imagery EEG Classification

Read full text Summarise with VIRAT
Authors: Matthew McCartney, Liisa Anna Kivioja, Sonal Santosh Baberwal, Shirley M. Coyle
Cited by: 0
References: 28

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Motor-imagery (MI) EEG can be classified using supervisedmachine learning techniques such as Linear Discriminant Analysis applied to features extracted by Common Spatial Patterns. Performance ofthese models varies widely, possibly due to MI studies commonly utilising differing post-cue time windows and frequency bands to one another.This study aims to assess how the simultaneous optimisation of boththese parameters impact MI classification performance. This is done byiteratively training and testing a series of subject-specific models on different combinations of frequency bandwidth and time window optionsacross 109 subjects. This is followed by a statistical analysis using repeated measures ANOVA to uncover significant differences between different bandwidths and time windows in terms of accuracy across thepatient cohort. The resulting visualisations and statistical tests showthat there are, indeed, significant differences between both specific timewindows and specific bandwidths in terms of accuracy. While the comparison of classification accuracies across 23 frequency bandwidths during five different time windows demonstrates an optimal temporal andspectral scale combination of (0, 4) s at the range of (4, 12) Hz across allsubjects, the subjects demonstrate similar accuracies for other parameter combinations. These findings highlight the efficacy of personalisedmodels to detect optimal temporal and spectral parameter combinationsto best classify MI EEG signals that inherently vary across subjects.

Fields of Study & Subjects

EEG and Brain-Computer Interfaces Muscle activation and electromyography studies Stroke Rehabilitation and Recovery

Publication details

Journal / source
arXiv (Cornell University)
Publication date
23 March 2026
Language
EN
Document type
Preprint