EARtrodes: Towards a wireless in-ear custom-fitted brain computer interface
Bibliographic record
Abstract
Brain-computer interfaces (BCI) can directly translate human intentions into discrete commands, bypassing the motor system. Most non-invasive BCI systems currently in use are based on electroencephalography (EEG) recording technology. While traditional EEG-based BCIs achieve high information transfer rates, these systems are facing important limitations. First, they cannot be used in daily life as they are bulky and sensitive to movement. Second, the scalp caps used to position electrodes are inadequate for social settings. To overcome these two limitations a portable and unobtrusive ear-EEG recording system was developed and tested against a traditional laboratory EEG system. The ear-EEG system senses brain-electrical signals from in and around-the ear, using custom-fitted earpieces. The objective of the current study is to assess if ear-EEG could produce results similar to the ones obtained from conventional EEG apparatus. Miniaturized wet electrodes were installed in a SonoFit™ custom-fitted in-ear audio platform developed by EERS (Montreal, Canada). This in-ear audio platform was coupled with a behind-the-ear piece forming a 5 mini electrodes interface. Auditory steady state responses (ASSRs) were collected with this prototype setup, dubbed “EARtrodes”, and compared to those obtained with a well-established, wired laboratory EEG recording system, the Rotman MASTER research system developed at the Baycrest Centre (University of Toronto, Canada). Although EARtrodes' signals show lower amplitudes, corresponding signal-to-noise ratios were similar with both systems. As a consequence, the proposed EARtrodes seems to be a promising candidate for future small, mobile, and unobtrusive BCI platforms, but further research is needed to investigate event-related potentials obtained from an auditory oddball and a mismatch negativity paradigm to further support such statement. In the long term ear-EEG systems like EARtrodes could be merged with other audio devices, such as hearing aids and headphones, to build next-generation devices that dynamically adapt to the listener’s intentions and cognitive state changes.
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 | 0.001 |
| 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 | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".