An Implementation of �-Divergence for Blind Source Separation
Bibliographic record
Abstract
Life sustaining biomedical signal processing demands a guarantee that the results produced are accurate and precise. The separation of sources (e.g., demixing two heart signals, one from a mother, and one from a fetus) based only on observations of those mixtures, known as the blind source separation problem, is seen by researchers and scientists as a necessary preprocessing step in order to obtain uncontaminated data for analysis. A method from the field of intelligent signal processing called independent component analysis (ICA) is a promising solution to this problem. However, ICA algorithms and their implementation must be robust to interference, including outliers. Unfortunately, contamination of biomedical recordings by outliers is an unavoidable aspect in signal processing. Mihoko and Eguchi developed an outlier robust ICA algorithm, but code for this algorithm is unavailable. This paper presents a Matlab implementation of their beta-divergence for blind source separation algorithm. The implementation uses a quasi-Newton Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimization, combined with an Armijo conditioned line-search, to minimize the beta-divergence between the density of the source estimates and the product of its hypothesized marginal densities to separate a mixture of statistically independent sources. The implementation is verified by repeating the source separation simulations published by Mihoko and Eguchi. In each simulation the separation results match visually to those published by Mihoko and Eguchi
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 | 0.003 |
| 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 | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".