MétaCan
Menu
Back to cohort
Record W3194701173 · doi:10.46932/sfjdv2n4-019

A Novel 4D Track Prediction Approach Combining Empirical Mode Decomposition with Nonlinear Correlation Coefficient

2021· article· en· W3194701173 on OpenAlex

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueSouth Florida Journal of Development · 2021
Typearticle
Languageen
FieldEngineering
TopicAir Traffic Management and Optimization
Canadian institutionsMD Precision (Canada)
FundersNanjing UniversityNanjing University of Aeronautics and AstronauticsNational Natural Science Foundation of China
KeywordsHilbert–Huang transformNonlinear systemCorrelation coefficientMode (computer interface)AlgorithmEngineeringArtificial intelligenceComputer scienceMathematicsStatisticsPhysics

Abstract

fetched live from OpenAlex

The accuracy of 4D track prediction plays an important role to solve the prominent contradiction between the rapid development of air transport industry and the limited resources of airspace. The conventional 4D track prediction based on the aerospace dynamic model is usually inaccurate since of weather influence and air traffic controller (ATC) factor. In this paper, an entirely data-driven nominal flight height profile prediction approach combing empirical mode decomposition (EMD) with nonlinear correlation coefficient (NCC) is proposed. Firstly, the historical tracks are implemented on EMD individually. Then according to a procedure similar to leave-one-out cross validation (LOOCV), the physical meanings of different intrinsic mode functions (IMFs) obtained by EMD are analyzed to corresponding to the various flight information. For a specified flight, the similarities between different dates are measured by NCC. Finally, a predicted nominal trajectory is obtained by summing a series of selected IMFs with a regression weight under least square optimization framework. It is demonstrated that the proposed method shows a higher prediction performance when comparing with the state of the art method named as nearest neighbor classification with dynamic time warping (DTW).
 
 La precisión de la predicción de la pista 4D desempeña un papel importante para resolver la importante contradicción entre el rápido desarrollo de la industria del transporte aéreo y los recursos limitados del espacio aéreo. La predicción convencional de la pista 4D basada en el modelo dinámico aeroespacial suele ser inexacta debido a la influencia de las condiciones meteorológicas y el factor del controlador de tráfico aéreo (ATC). En este trabajo, se propone un enfoque de predicción del perfil de altura de vuelo nominal totalmente basado en datos que combina la descomposición empírica de modos (EMD) con el coeficiente de correlación no lineal (NCC). En primer lugar, las pistas históricas se implementan en la EMD individualmente. A continuación, de acuerdo con un procedimiento similar al de la validación cruzada sin intervención (LOOCV), se analizan los significados físicos de las diferentes funciones de modo intrínseco (IMF) obtenidas por la EMD para que correspondan a las diversas informaciones de vuelo. Para un vuelo específico, se miden las similitudes entre las distintas fechas mediante NCC. Por último, se obtiene una trayectoria nominal predicha mediante la suma de una serie de FMI seleccionadas con un peso de regresión en el marco de la optimización de mínimos cuadrados. Se demuestra que el método propuesto muestra un mayor rendimiento de predicción en comparación con el método más avanzado denominado clasificación de vecinos más cercanos con deformación temporal dinámica (DTW).

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 imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.417
Threshold uncertainty score0.559

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.015
GPT teacher head0.250
Teacher spread0.235 · 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