Aircraft Categorization Approach Using Machine Learning to Analyze Aircraft Behavior
Bibliographic record
Abstract
The establishment of aircraft categories is a classification technique employed in a variety of aviation disciplines, including design and development, certification, ongoing airworthiness, air traffic management, surveillance, and safety analysis. Traditional approaches rely on manual feature engineering, which can be labor-intensive and ineffective for capturing complex patterns. In this paper, an approach to aircraft categorization using unsupervised machine learning clustering is proposed. The aim of the proposed approach is to be simple in order to be useful and understandable across disciplinary domains; to be scalable to large volumes of air traffic data; and to be adaptable to changes to account for the evolving technological and operational nature of the airspace environment. The application is based on an adapted version of the [Formula: see text]-means algorithm that can group aircraft into clusters based on 3D position over time. The approach is validated using real-world, publicly available ADS-B air traffic data, and the results are compared to traditional categorization methods from the field of aircraft certification. The results showed that the model could be used to 1) identify and group aircraft sharing the same flight phase, 2) categorize aircraft with a similar general heading or direction, and 3) distinguish between local regional aircraft operations and longer flight operations. It was also shown that, depending on the use case, the model could be extended to identify more granular behaviors by increasing the [Formula: see text] value used to create the model. Overall, the findings demonstrate that leveraging machine learning techniques for aircraft categorization provides an effective, automated, and scalable solution applicable to a wide range of current applications.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 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) | 0.001 | 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".