Leveraging Transfer Learning and User-Specific Updates for Rapid Training of BCI Decoders
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| 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 |