Synthesizing EEG Signals from Event-Related Potential Paradigms with Conditional Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913569980809216 |
|---|---|
| author | Klein, Guido Guetschel, Pierre Silvestri, Gianluigi Tangermann, Michael |
| author_facet | Klein, Guido Guetschel, Pierre Silvestri, Gianluigi Tangermann, Michael |
| contents | Data scarcity in the brain-computer interface field can be alleviated through the use of generative models, specifically diffusion models. While diffusion models have previously been successfully applied to electroencephalogram (EEG) data, existing models lack flexibility w.r.t.~sampling or require alternative representations of the EEG data. To overcome these limitations, we introduce a novel approach to conditional diffusion models that utilizes classifier-free guidance to directly generate subject-, session-, and class-specific EEG data. In addition to commonly used metrics, domain-specific metrics are employed to evaluate the specificity of the generated samples. The results indicate that the proposed model can generate EEG data that resembles real data for each subject, session, and class. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18486 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Synthesizing EEG Signals from Event-Related Potential Paradigms with Conditional Diffusion Models Klein, Guido Guetschel, Pierre Silvestri, Gianluigi Tangermann, Michael Machine Learning Artificial Intelligence Signal Processing I.2.6; G.3; I.5.4; J.3 Data scarcity in the brain-computer interface field can be alleviated through the use of generative models, specifically diffusion models. While diffusion models have previously been successfully applied to electroencephalogram (EEG) data, existing models lack flexibility w.r.t.~sampling or require alternative representations of the EEG data. To overcome these limitations, we introduce a novel approach to conditional diffusion models that utilizes classifier-free guidance to directly generate subject-, session-, and class-specific EEG data. In addition to commonly used metrics, domain-specific metrics are employed to evaluate the specificity of the generated samples. The results indicate that the proposed model can generate EEG data that resembles real data for each subject, session, and class. |
| title | Synthesizing EEG Signals from Event-Related Potential Paradigms with Conditional Diffusion Models |
| topic | Machine Learning Artificial Intelligence Signal Processing I.2.6; G.3; I.5.4; J.3 |
| url | https://arxiv.org/abs/2403.18486 |