Leveraging Transfer Learning and User-Specific Updates for Rapid Training of BCI Decoders

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Ziheng, Wang, Po T., Ibrahim, Mina, Baveja, Shivali, Mu, Rong, Do, An H., Nenadic, Zoran
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911008982827008
author Chen, Ziheng
Wang, Po T.
Ibrahim, Mina
Baveja, Shivali
Mu, Rong
Do, An H.
Nenadic, Zoran
author_facet Chen, Ziheng
Wang, Po T.
Ibrahim, Mina
Baveja, Shivali
Mu, Rong
Do, An H.
Nenadic, Zoran
contents Lengthy subject- or session-specific data acquisition and calibration remain a key barrier to deploying electroencephalography (EEG)-based brain-computer interfaces (BCIs) outside the laboratory. Previous work has shown that cross subject, cross-session invariant features exist in EEG. We propose a transfer learning pipeline based on a two-layer convolutional neural network (CNN) that leverages these invariants to reduce the burden of data acquisition and calibration. A baseline model is trained on EEG data from five able-bodied individuals and then rapidly updated with a small amount of data from a sixth, holdout subject. The remaining holdout data were used to test the performance of both the baseline and updated models. We repeated this procedure via a leave-one-subject out (LOSO) validation framework. Averaged over six LOSO folds, the updated model improved classification accuracy upon the baseline by 10.0, 18.8, and 22.1 percentage points on two binary and one ternary classification tasks, respectively. These results demonstrate that decoding accuracy can be substantially improved with minimal subject-specific data. They also indicate that a CNN-based decoder can be personalized rapidly, enabling near plug-and-play BCI functionality for neurorehabilitation and other time-critical EEG applications.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Transfer Learning and User-Specific Updates for Rapid Training of BCI Decoders
Chen, Ziheng
Wang, Po T.
Ibrahim, Mina
Baveja, Shivali
Mu, Rong
Do, An H.
Nenadic, Zoran
Quantitative Methods
Lengthy subject- or session-specific data acquisition and calibration remain a key barrier to deploying electroencephalography (EEG)-based brain-computer interfaces (BCIs) outside the laboratory. Previous work has shown that cross subject, cross-session invariant features exist in EEG. We propose a transfer learning pipeline based on a two-layer convolutional neural network (CNN) that leverages these invariants to reduce the burden of data acquisition and calibration. A baseline model is trained on EEG data from five able-bodied individuals and then rapidly updated with a small amount of data from a sixth, holdout subject. The remaining holdout data were used to test the performance of both the baseline and updated models. We repeated this procedure via a leave-one-subject out (LOSO) validation framework. Averaged over six LOSO folds, the updated model improved classification accuracy upon the baseline by 10.0, 18.8, and 22.1 percentage points on two binary and one ternary classification tasks, respectively. These results demonstrate that decoding accuracy can be substantially improved with minimal subject-specific data. They also indicate that a CNN-based decoder can be personalized rapidly, enabling near plug-and-play BCI functionality for neurorehabilitation and other time-critical EEG applications.
title Leveraging Transfer Learning and User-Specific Updates for Rapid Training of BCI Decoders
topic Quantitative Methods
url https://arxiv.org/abs/2506.14120