Aircraft Location Prediction using Deep Learning

Adesina, Damilola; Olutobi, Adagunodo; Dong, Xishuang; Qian, Lijun

doi:10.1109/milcom47813.2019.9020888

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Method [9] and a location prediction method [10] based on individual movement patterns using a trajectory location prediction model have been proposed. In addition, based on the flight records of aircraft, aircraft position prediction using aircraft trajectory file data was also proposed [11]. Due to the major limitations of the Markovian model, the current trend of location prediction is recognized as the most important value to obtain the predicted value of the next location from the location visited by a user.…”

Section: Related Workmentioning

confidence: 99%

Low Power Sensor Location Prediction Using Spatial Dimension Transformation and Pattern Recognition

Lee

Jeong

2022

Energies

View full text Add to dashboard Cite

A method of positioning a location on a specific object using a wireless sensor has been developed for a long time. However, due to the error of wavelengths and various interference factors occurring in three-dimensional space, accurate positioning is difficult, and predicting future locations is even more difficult. It uses IoT-based node pattern recognition technology to overcome positioning errors or inaccurate predictions in wireless sensor networks. It developed a method to improve the current positioning accuracy in a sensor network environment and a method to learn a pattern of position data directly from a wavelength receiver. The developed method consists of two steps: The first step is a method of changing location data in 3D space to location data in 2D space in order to reduce the possibility of positioning errors in 3D space. The second step is to reduce the range of the moving direction angle in which the data changed in two dimensions can be changed in the future and to predict future positions through pattern recognition of the position data. It is to calculate the expected position in the future. In conclusion, three-dimensional positioning accuracy was improved through this method, and future positioning accuracy was also improved. The core technology was able to reduce inevitable errors by changing the spatial dimension from 3D to 2D and to improve the accuracy of future location prediction by reducing the range of the movable direction angle of the location data changed to 2D. It was also possible to obtain the result that the prediction accuracy increases in proportion to the amount of data accumulated in the wavelength receiver and the learning time. In the era of the Fourth Industrial Revolution, this method is expected to be utilized in various places, such as smart cities, autonomous vehicles, and disaster prediction.

show abstract

Section: Related Workmentioning

confidence: 99%

Low Power Sensor Location Prediction Using Spatial Dimension Transformation and Pattern Recognition

Lee

Jeong

2022

Energies

View full text Add to dashboard Cite

show abstract

“…These standards have been developed to ensure safe aircraft transportation, especially for modern automatic flights. Huge investments have been made in the United States over the last decades by the Federal Aviation Administration (FAA) into "The Next-Generation of Aerial Transportation" project, with the aim of increasing the safety and reliability of flights [1].…”

Section: Introductionmentioning

confidence: 99%

New Reliability Studies of Data-Driven Aircraft Trajectory Prediction

Hashemi¹,

Botez²,

Grigorie

2020

Aerospace

View full text Add to dashboard Cite

Two main factors, including regression accuracy and adversarial attack robustness, of six trajectory prediction models are measured in this paper using the traffic flow management system (TFMS) public dataset of fixed-wing aircraft trajectories in a specific route provided by the Federal Aviation Administration. Six data-driven regressors with their desired architectures, from basic conventional to advanced deep learning, are explored in terms of the accuracy and reliability of their predicted trajectories. The main contribution of the paper is that the existence of adversarial samples was characterized for an aircraft trajectory problem, which is recast as a regression task in this paper. In other words, although data-driven algorithms are currently the best regressors, it is shown that they can be attacked by adversarial samples. Adversarial samples are similar to training samples; however, they can cause finely trained regressors to make incorrect predictions, which poses a security concern for learning-based trajectory prediction algorithms. It is shown that although deep-learning-based algorithms (e.g., long short-term memory (LSTM)) have higher regression accuracy with respect to conventional classifiers (e.g., support vector regression (SVR)), they are more sensitive to crafted states, which can be carefully manipulated even to redirect their predicted states towards incorrect states. This fact poses a real security issue for aircraft as adversarial attacks can result in intentional and purposely designed collisions of built-in systems that can include any type of learning-based trajectory predictor.

show abstract