Character-level decoding (ERP and c-VEP)
Open
Nobody has claimed this yet.
enhancement
moabb
- Dominant language
- Python
- Stars
- 1.1k
- Forks
- 264
- Avg merge
- 1d 13m
- Merged PRs (30d)
- 23
Description
Character-level (or trial-level) decoding of ERP and c-VEP (see #366) datasets would allow to benchmark the state-of-the-art algorithms that directly exploit the trial structure instead of doing a binary target/non-target classification.
For such a trial-level decoding to be possible in MOABB, we would need to:
- #186 ;
- pass the stimulation sequence of each character to the decoding algorithms.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing issue #186 and the existing ERP and c-VEP decoding entry points. Determine how each character's stimulation sequence can reach the decoding algorithms; the work is done when both checklist items are supported for trial-level benchmarking.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100