Towards an Evaluation Process for Regime Recognition Approaches: Addressing Variability in Labeling Training Data
Bibliographic record
Abstract
Regime recognition is an important tool for monitoring aircraft usage. Algorithms for this task are normally trained and tested on flight load survey data. In many instances, significant portions of the flight data are not used because of labeling uncertainties. Flight test data is expensive to generate, but machine learning-based solutions rely on copious amounts of training data, so the idea of discarding data is unappealing. This paper presents a process to consistently and systematically label flight data with common helicopter regimes that would reduce the amount of unlabeled flight test data. The approach makes use of regime descriptions and parameter time histories to assign labels, which are then verified using flight path and flight test card information. Although the implementation of the approach is challenging, the initial results from Bell 206 test flights demonstrate that this approach can significantly reduce the amount of unlabeled flight data, enabling much more usable data for training algorithms.
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 | 0.060 | 0.156 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.001 | 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".