Data Sheet for Domain-aware Domain–Class Adaptation Network for EEG Classification

Jiahuan Wang authored a research document describing a domain-aware domain–class adaptation network (DDCA Net) for cross-task transfer learning from motor execution to motor imagery EEG classification. The document reports results from experiments on a public dataset with over 100 subjects, showing a 7.71% accuracy improvement over a baseline. It was last updated on June 1, 2026.

Use Cases

• Training domain adaptation models based on the described DDCA Net architecture for EEG classification.
• Benchmarking cross-task transfer learning performance based on the reported 7.71% accuracy improvement.
• Investigating the conversion of BCI-illiterate to BCI-literate subjects based on the described methodology.
• Reproducing experiments on a public EEG dataset with over 100 subjects as referenced in the document.

Strengths

• The document is associated with a public dataset containing over 100 subjects.
• The described method achieved a 7.71% classification accuracy improvement over a within-task baseline.
• The work is licensed under CC-BY-4.0, allowing for open sharing and reuse.

Limitations

• The dataset itself is not directly provided; the file is a 876.0 KB DOCX document describing a method.
• Column-level documentation and sample data for the underlying EEG dataset are unavailable.
• Row count for the referenced public dataset is unknown, which may limit suitability assessment.

Provenance

Source

Jiahuan Wang

Collection Method

The document describes a proposed neural network architecture and its evaluation on a public dataset.

Freshness

Last updated 2026-06-01 05:23:29; freshness should be verified.