Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Workshop on Learning from Time Series for Health

Subject Selection Framework to Improve Personalised Models for Motor-Imagery BCIs via Wavelets and Graph Diffusion

Konstantinos Barmpas · Yannis Panagakis · Dimitrios Adamos · Nikolaos Laskaris · Stefanos Zafeiriou

Keywords: [ Motor-Imagery ] [ Electroencephalogram ] [ Wavelets ] [ Graph Diffusion ] [ Subject Selection ] [ Brain-Computer Interface ]


Abstract:

Personalized electroencephalogram (EEG) decoders hold a distinct preference in healthcare applications, especially in the context of Motor-Imagery (MI) Brain-Computer Interfaces (BCIs), owing to their inherent capability to effectively tackle inter-subject variability. This study introduces a novel subject selection framework that blends ideas from discriminative learning (based on continuous wavelet transform) and graph-signal processing (over the sensor array). Through experimentation with a publicly available MI dataset, we showcase enhanced personalized performance for MI-BCIs. Notably, it proves particularly advantageous for subjects who initially demonstrated suboptimal personalized performance.

Chat is not available.