Pushing the P300-based brain–computer interface beyond 100 bpm: extending performance guided constraints into the temporal domain
Bibliographic record
Abstract
OBJECTIVE: A new presentation paradigm for the P300-based brain-computer interface (BCI) referred to as the 'asynchronous paradigm' (ASP) is introduced and studied. It is based on the principle of performance guided constraints (Townsend et al 2012 Neurosci. Lett. 531 63-8) extended from the spatial domain into the temporal domain. The traditional constraint of flashing targets in predefined constant epochs of time is eliminated and targets flash asynchronously with timing based instead on constraints intended to improve performance. APPROACH: We propose appropriate temporal constraints to derive the ASP and compare its performance to that of the 'checkerboard paradigm' (CBP), which has previously been shown to be superior to the standard 'row/column paradigm' introduced by Farwell and Donchin (1988 Electroencephalogr. Clin. Neurophysiol. 70 510-23). Ten participants were tested in the ASP and CBP conditions both with traditional flashing items and with flashing faces in place of the targets (see Zhang et al 2012 J. Neural Eng. 9 026018; Kaufmann and Kübler 2014 J. Neural Eng. 11 ; Chen et al 2015 J. Neurosci. Methods 239 18-27). Eleven minutes of calibration data were used as input to a stepwise linear discriminant analysis to derive classification coefficients used for online classification. MAIN RESULTS: Accuracy was consistently high for both paradigms (87% and 93%) while information transfer rate was 45% higher for the ASP than the CBP. In a free spelling task, one subject spelled a 66 character sentence (from a 72 item matrix) with 100% accuracy in 3 min and 24 s demonstrating a practical throughput of 120 bits per minute (bpm) with a theoretical upper bound of 258 bpm. The subject repeated the task three times in a row without error. SIGNIFICANCE: This work represents an advance in P300 speller technology and raises the ceiling that was being reached on P300-based BCIs. Most importantly, the research presented here is a novel and effective general strategy for organising timing for flashing items. The ASP is only one possible implementation of this work since in general it can be used to describe all previous existing presentation paradigms as well as any possible new ones. This may be especially important for people with neuromuscular disabilities.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".