AIRCRAFT PATH EXTRACTION FROM NOISY TARGET DATA
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Testing of air traffic control (ATC) and air traffic management (ATM) systems benefits from the availability of realistic scenario data based on live recorded traffic. The difficulty with such data sets is the dependency on local geography and adaptation of the site where the data was collected. Scenario data is typically used in an environment different than the original, potentially with new sensor types and configuration. An example is the evaluation of the accuracy of the tracking and conflict alert functions for future systems that plan to implement data fusion of radar and automatic dependent surveillance-broadcast (ADS-B) data using a scenario based on data where only radar surveillance is available today. This paper presents an algorithm to extract “ground truth” from live recorded data such that the noiseless aircraft paths are obtained with their relative separations preserved and in a representation decoupled from the sensor types and the geographic configuration specific to the originating site. Ground truth obtained from the path extraction (PE) algorithm can be used as input to target generation software configured for a specific sensor environment as required for the system under test. The PE algorithm is basically a maneuver detector that looks for changes above noise in heading, altitude, speed and vertical velocity. The algorithm relies on identifying those segments where the relevant kinematic data (heading, altitude, horizontal and vertical speed) could be considered constant and consistent with noise. Unlike a purely statistical change detector, which is more sensitive to the correct modeling of noise, the PE algorithm is more robust because the straightforward geometric approach that it uses looks at the overall effect of a maneuver rather than trying to detect the point where the maneuver takes place. For example, a small change in heading is difficult to detect when looking for the maneuver point, but the change it produces is easily recognized by examining the entire realized track. The horizontal component of the extracted aircraft paths are expressed in stereographic coordinates on a common surveillance system plane. It is shown that, together with aircraft altitude, this choice of coordinate system lends itself to relocate the traffic easily to any region on the ellipsoidal Earth. The PE algorithm provides segmented aircraft path data, which in addition to its use to generate reference scenarios for testing, can also be used to infer aircraft intent, to obtain scenario characterization metrics, and for detection of the phase of flight. Metrics to evaluate the performance of the PE algorithm are presented and results of an evaluation are discussed.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it