ATFMTraj: Aircraft Trajectory Time Series Data for Air Traffic Management

Citation Author(s):
Thaweerath
Phisannupawong
Korea Advanced Institute of Science and Technology (KAIST)
Joshua Julian
Damanik
Korea Advanced Institute of Science and Technology (KAIST)
Han-Lim
Choi
Korea Advanced Institute of Science and Technology (KAIST)
Submitted by:
Thaweerath Phis...
Last updated:
Sun, 10/27/2024 - 09:31
DOI:
10.21227/f77f-b640
Links:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

Since the aircraft trajectory data in the field of air traffic management typically lacks labels, it limits the community's ability to explore classification models. Consequently, evaluations of clustering models often focus on the correctness of cluster assignment rather than merely the closeness within the cluster. To address this, we labeled the dataset for both classification and clustering tasks by referring to aeronautical publications. The process of obtaining the ATFM trajectory dataset consists of data sourcing, preprocessing, and annotation.

Instructions: 

This data can also be accessed through Hugging Face at the link: https://huggingface.co/datasets/petchthwr/ATFMTraj. Use the function in Example_usage.py. There is a Python function designed to load ATFMTraj datasets from TSV files, manage missing values, and return both data and labels. The function assumes that the dataset is split into separate files based on a base name, mode, and coordinate variable (X, Y, Z).

Funding Agency: 
Korea Agency for Infrastructure Technology Advancement (KAIA)
Grant Number: 
Grant 22DATM-C163373-02

Comments

 

 

Submitted by linda zakhama on Sat, 11/30/2024 - 16:24