Universal EEG Encoder for Learning Diverse Intelligent Tasks
This addresses the problem of poor generalization across tasks in EEG-based BCI studies, offering a more versatile approach for researchers and practitioners, though it appears incremental as it builds on existing deep learning methods.
The paper tackles the challenge of individualistic, task-specific analysis in EEG-based brain-computer interfaces by designing a GRU-based universal deep encoding architecture that extracts meaningful features for five diverse EEG classification tasks, outperforming the state-of-the-art EEGNet architecture on most experiments.
Brain Computer Interfaces (BCI) have become very popular with Electroencephalography (EEG) being one of the most commonly used signal acquisition techniques. A major challenge in BCI studies is the individualistic analysis required for each task. Thus, task-specific feature extraction and classification are performed, which fails to generalize to other tasks with similar time-series EEG input data. To this end, we design a GRU-based universal deep encoding architecture to extract meaningful features from publicly available datasets for five diverse EEG-based classification tasks. Our network can generate task and format-independent data representation and outperform the state of the art EEGNet architecture on most experiments. We also compare our results with CNN-based, and Autoencoder networks, in turn performing local, spatial, temporal and unsupervised analysis on the data.