EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Time-Domain Versus Frequency-Embedded EEG Sequences for Sensorimotor BCI Using 1D-CNN

Simanto Saha, Mathias Baumert, Alistair Mcewan

IEEE Access · 2025 · 13 · 137919-137930

DOI: 10.1109/access.2025.3595953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Simanto Saha und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposed a motor imagery (MI) classification pipeline featuring a 1−dimensional convolutional neural network (1D-CNN) with different time/frequency feature representation techniques. The objective was to classify right hand (RH) versus right foot (RF) MI tasks in both intra- and inter-subject (pairwise and pooled) BCI settings using a 1D-CNN architecture trained on time-domain bandpass filtered electroencephalography (EEG) signals, frequency-embedded power spectral density (PSD) and cross-power spectral density (CPSD) sequences. The EEG signals were bandpass filtered with 4 Hz and 32 Hz cut-off frequencies, and PSD/CPSD sequences were estimated in the same frequency range. Thus, the number of input channels for 1D-CNN wasN,NorN×Nfor EEG signals, PSD or CPSD sequences. We used datasetIVafrom BCI CompetitionIIIin 5−fold cross-validation settings to evaluate intra-subject, inter-subject (pairwise) and inter-subject (pooled) BCI classification accuracies. We compared the performance of the proposed methods with classification algorithms featuring common spatial patterns (CSP) for benchmarking. The best overall classification accuracies (%) for intra-subject, inter-subject (pairwise) and inter-subject (pooled) BCIs were 86.57±11.69, 70.80±9.21 and 76.61±12.37 using 1D−CNN with time-domain EEG signals. The average classification accuracies using 1D-CNN with frequency-embedded PSD sequences were 82.57±10.20, 69.32±7.46 and 71.32±7.96 for intra-subject, inter-subject (pairwise) and inter-subject (pooled) BCIs. The proposed time/frequency feature representation techniques with 1D-CNN outperformed CSP-based algorithms (p-value < 0.05). The comparative results suggest the utility of the proposed methods for MI classification, especially for a fully zero-training inter-subject BCI.

Zitieren

APA

Saha, S., Baumert, M., & Mcewan, A. (2025). Time-Domain Versus Frequency-Embedded EEG Sequences for Sensorimotor BCI Using 1D-CNN. IEEE Access, 13, 137919-137930. https://doi.org/10.1109/access.2025.3595953

Vancouver

Saha S, Baumert M, Mcewan A. Time-Domain Versus Frequency-Embedded EEG Sequences for Sensorimotor BCI Using 1D-CNN. IEEE Access. 2025;13:137919-137930. doi:10.1109/access.2025.3595953

BibTeX
@article{Saha2025,
  author = {Saha, Simanto and Baumert, Mathias and Mcewan, Alistair},
  title = {Time-Domain Versus Frequency-Embedded EEG Sequences for Sensorimotor BCI Using 1D-CNN},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {137919--137930},
  doi = {10.1109/access.2025.3595953}
}
Kostenlos starten →