What Causes Performance Degradation in Cross-Subject EEG Classification?
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_ | 1866917414513410048 |
|---|---|
| author | Wang, Yihe Li, Taida Yan, Yujun Song, Wenzhan Zhang, Xiang |
| author_facet | Wang, Yihe Li, Taida Yan, Yujun Song, Wenzhan Zhang, Xiang |
| contents | Cross-subject EEG classification typically achieves significantly lower performance than subject-dependent settings. Although this phenomenon has been widely observed in the literature, the underlying causes have not been systematically studied. In this paper, we design a series of controlled experiments to investigate the mechanisms behind the performance drop in cross-subject EEG classification across different EEG tasks. We show that the performance degradation can generally be attributed to two factors: inter-subject variability and shortcut learning. Specifically, multi-class-per-subject EEG classification tasks, such as motor imagery, emotion recognition, and ERP stimulus classification, are mainly affected by inter-subject variability, whereas single-class-per-subject EEG classification tasks, such as brain disease detection, are primarily influenced by shortcut learning based on subject-specific features. These findings provide new insights into the challenges of cross-subject EEG classification and emphasize the importance of appropriate evaluation protocols in EEG research. The code is available at https://github.com/DL4mHealth/EEG-Cross-Subject. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03057 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | What Causes Performance Degradation in Cross-Subject EEG Classification? Wang, Yihe Li, Taida Yan, Yujun Song, Wenzhan Zhang, Xiang Computational Engineering, Finance, and Science Cross-subject EEG classification typically achieves significantly lower performance than subject-dependent settings. Although this phenomenon has been widely observed in the literature, the underlying causes have not been systematically studied. In this paper, we design a series of controlled experiments to investigate the mechanisms behind the performance drop in cross-subject EEG classification across different EEG tasks. We show that the performance degradation can generally be attributed to two factors: inter-subject variability and shortcut learning. Specifically, multi-class-per-subject EEG classification tasks, such as motor imagery, emotion recognition, and ERP stimulus classification, are mainly affected by inter-subject variability, whereas single-class-per-subject EEG classification tasks, such as brain disease detection, are primarily influenced by shortcut learning based on subject-specific features. These findings provide new insights into the challenges of cross-subject EEG classification and emphasize the importance of appropriate evaluation protocols in EEG research. The code is available at https://github.com/DL4mHealth/EEG-Cross-Subject. |
| title | What Causes Performance Degradation in Cross-Subject EEG Classification? |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2410.03057 |