Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909469392240640 |
|---|---|
| author | Pereira, Joao Alummoottil, Michael Halatsis, Dimitrios Farina, Dario |
| author_facet | Pereira, Joao Alummoottil, Michael Halatsis, Dimitrios Farina, Dario |
| contents | Machine learning offers promising methods for processing signals recorded with wearable devices such as surface electromyography (sEMG) and electroencephalography (EEG). However, in these applications, despite high within-session performance, intersession performance is hindered by electrode shift, a known issue across modalities. Existing solutions often require large and expensive datasets and/or lack robustness and interpretability. Thus, we propose the Spatial Adaptation Layer (SAL), which can be applied to any biosignal array model and learns a parametrized affine transformation at the input between two recording sessions. We also introduce learnable baseline normalization (LBN) to reduce baseline fluctuations. Tested on two HD-sEMG gesture recognition datasets, SAL and LBN outperformed standard fine-tuning on regular arrays, achieving competitive performance even with a logistic regressor, with orders of magnitude less, physically interpretable parameters. Our ablation study showed that forearm circumferential translations account for the majority of performance improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08058 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications Pereira, Joao Alummoottil, Michael Halatsis, Dimitrios Farina, Dario Machine Learning Signal Processing Machine learning offers promising methods for processing signals recorded with wearable devices such as surface electromyography (sEMG) and electroencephalography (EEG). However, in these applications, despite high within-session performance, intersession performance is hindered by electrode shift, a known issue across modalities. Existing solutions often require large and expensive datasets and/or lack robustness and interpretability. Thus, we propose the Spatial Adaptation Layer (SAL), which can be applied to any biosignal array model and learns a parametrized affine transformation at the input between two recording sessions. We also introduce learnable baseline normalization (LBN) to reduce baseline fluctuations. Tested on two HD-sEMG gesture recognition datasets, SAL and LBN outperformed standard fine-tuning on regular arrays, achieving competitive performance even with a logistic regressor, with orders of magnitude less, physically interpretable parameters. Our ablation study showed that forearm circumferential translations account for the majority of performance improvements. |
| title | Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications |
| topic | Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2409.08058 |