A Reference-based Source Extraction Algorithm to Extract Movement Related Cortical Potentials for Brain-Computer Interface Applications
Bibliographic record
Abstract
Brain-Computer Interface (BCI) systems aim at providing a channel through electroencephalogram (EEG) to control external devices. Movement-Related Cortical Potential (MRCP) is a low-frequency and low-amplitude EEG component that has been recently introduced to control real-time BCI systems. The performance of BCI systems based on MRCP highly depends on the accuracy of single trial MRCP detection, which is a challenging task due to high amount of EEG background noise and various types of artifacts. In this paper, a semi-blind source extraction algorithm based on second order statistics and a reference signal, designed according to the BCI paradigm, is presented to extract MRCP. The performance of the method is investigated during a complex motor task, gait initiation. The reference signal utilizes the temporal information from the training set to extract MRCP. The proposed method is compared with two commonly used spatial filtering techniques as well as two source extraction methods based on second order statistics. Two different training sets including only ankle dorsiflexion data (AD) and ankle dorsiflexion plus gait initiation (GI) data was used to train the proposed algorithm and the methods that require training. The performance of the proposed algorithm and other extraction methods on the extracted MRCP was evaluated by a performance index (PI) quantifying the signal-to-noise ratio of the extracted MRCP. The PI obtained with the proposed algorithm trained with AD only training set (2.43 ± 1.23) was greater than all other investigated methods. When trained with both AD and GI trials, the performance of the method was the second best among all methods (2.52 ± 0.83). The results from this study show that the proposed method is robust against differences between training and testing sets and provides high quality MRCP extraction.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".