MétaCan
Menu
Back to cohort
Record W4382052297 · doi:10.4050/f-0079-2023-18094

Towards an Evaluation Process for Regime Recognition Approaches: Addressing Variability in Labeling Training Data

2023· article· en· W4382052297 on OpenAlexaff
Catherine Cheung, Emma Seabrook

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTarget Tracking and Data Fusion in Sensor Networks
Canadian institutionsNational Research Council Canada
Fundersnot available
KeywordsComputer scienceUSableProcess (computing)Task (project management)Test dataMachine learningTraining setArtificial intelligenceFlight testFlight trainingFlight simulatorPath (computing)Test (biology)Data miningSimulationEngineering

Abstract

fetched live from OpenAlex

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 imitation

Not 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.

metaresearch head score (Codex)0.060
metaresearch head score (Gemma)0.156
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.060
Threshold uncertainty score0.320

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0600.156
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0030.002
Science and technology studies0.0020.003
Scholarly communication0.0060.006
Open science0.0030.005
Research integrity0.0040.005
Insufficient payload (model declined to judge)0.0010.001

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.

Opus teacher head0.596
GPT teacher head0.415
Teacher spread0.181 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicTarget Tracking and Data Fusion in Sensor NetworksFrench-language works237,207