Talk · International Winter Conference on Brain-Computer Interface · February 22, 2021
Deep Transfer Learning for Subject-Independent ERP-based BCIs
Kassymzhomart Kunanbayev, Dias Azhigulov, Berdakh Abibullaev, Amin Zollanvari
Abstract
Designing subject-independent Brain-Computer Interfaces remains to be an open question for developing systems that can capture the inter-subject intrinsic brain features and classify them with reasonable accuracy. This paper presents the application of the state-of-the-art deep transfer learning architectures on classifying ERP signals. We report 66.87%, 67.64%, 65.58%, and 71.93% test classification accuracy for DenseNet121, DenseNet201, Xception, and VGG-16 models, respectively. The experimental results demonstrate the viability of our approach in subject independent ERP-signals classification and suggest the better performance of models with fewer layers in classifying ERP signals.
More by Berdakh Abibullaev
- Onset Review: traceable analysis of high-frequency oscillations and seizure onset in intracranial EEGZenodo · 2026
- Multi-scale EEG feature decoding with Swin Transformers for subject independent motor imagery BCIsScientific Reports · 2026 · Citations: 12
- Generative data augmentation for machine learning-based quantitative cancer cell detection using optical fiber biosensorsEPJ Web of Conferences · 2026
- Deep learning in intracranial EEG for seizure detection: advances, challenges, and clinical applicationsFrontiers in Neuroscience · 2025 · Citations: 13