Aircraft Trajectory Prediction Enhanced through Resilient Generative Adversarial Networks Secured by Blockchain: Application to UAS-S4 Ehécatl

Hashemi, Seyed Mohammad; Hashemi, Seyed Ali; Botez, Ruxandra Mihaela; Ghazi, Georges

doi:10.3390/app13179503

Cited by 9 publications

(5 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If more than 51% of nodes confirm the conflict, then the smart contract must rearrange allocated airspaces. Otherwise, the report is assumed to be invalid due to an adversarial attack [56]. Algorithm 1 explains the consensus procedure in detail.…”

Section: Methodsmentioning

confidence: 99%

Blockchain PoS and PoW Consensus Algorithms for Airspace Management Application to the UAS-S4 Ehécatl

Hashemi,

Botez,

Ghazi

2023

Algorithms

Self Cite

View full text Add to dashboard Cite

This paper introduces an innovative consensus algorithm for managing Unmanned Aircraft System Traffic (UTM) through blockchain technology, a highly secure consensus protocol, to allocate airspace. A smart contract was developed on the Ethereum blockchain for allocating airspace. This technique enables the division of the swarm flight zone into smaller sectors to decrease the computational complexity of the algorithm. A decentralized voting system was established within these segmented flight zones, utilizing two primary methodologies: Proof of Work (PoW) and Proof of Stake (PoS). By employing 1000 UAS-S4s across various locations and heading angles, a swarm flight zone was generated. The efficiency of the devised decentralized consensus system was assessed based on error rate and validation time. Despite PoS displaying greater efficiency in cumulative probability for block execution, the comparative analysis indicated PoW outperformed PoS concerning the potential for conflicts among UASs.

show abstract

Section: Methodsmentioning

confidence: 99%

Blockchain PoS and PoW Consensus Algorithms for Airspace Management Application to the UAS-S4 Ehécatl

Hashemi,

Botez,

Ghazi

2023

Algorithms

Self Cite

View full text Add to dashboard Cite

show abstract

“…The robust data-driven method for Aircraft Trajectory Prediction using a Neural Network based on the Generative Adversarial Network framework is presented in [11]. Enhanced with Blockchain Ledger Technology for secure storage of predictions, the system effectively resists adversarial attacks, as demonstrated by performance evaluations using proposed simulation.…”

Section: Ai In Air Traffic Managementmentioning

confidence: 99%

Artificial Intelligence in Aviation: New Professionals for New Technologies

Kabashkin,

Misnevs,

Zervina

2023

Applied Sciences

View full text Add to dashboard Cite

Major aviation organizations have highlighted the need to adopt artificial intelligence (AI) to transform operations and improve efficiency and safety. However, the aviation industry requires qualified graduates with relevant AI competencies to meet this demand. This study analyzed aviation engineering bachelor’s programs at European universities to determine if they are preparing students for AI integration in aviation by incorporating AI-related topics. The analysis focused on program descriptions and syllabi using semantic annotation. The results showed a limited focus on AI and machine learning competencies, with more emphasis on foundational digital skills. Reasons include the newness of aviation AI, its specialized nature, and implementation challenges. As the industry evolves, dedicated AI programs may emerge. But currently, curricula appear misaligned with stated industry goals for AI adoption. The study provides an analytical methodology and competency framework to help educators address this gap. Producing graduates equipped with AI literacy and collaboration skills will be key to aviation’s intelligent future.

show abstract

“…Commonly used loss functions such as L1 and L2 norms can guide the optimization of models, but may overlook the distribution underlying predicted data and real data. To cope with this problem, generative frameworks such as generative adversarial networks (GANs) and auto-encoders are applied in traffic prediction [40,41]. These methods can be defined as unsupervised models that integrate supervised loss as a part of learning process of STGNNs.…”

Section: Learning Paradigmsmentioning

confidence: 99%

Self-Supervised Spatiotemporal Masking Strategy-Based Models for Traffic Flow Forecasting

Liu,

He,

Han

et al. 2023

Symmetry

View full text Add to dashboard Cite

Traffic flow forecasting is an important function of intelligent transportation systems. With the rise of deep learning, building traffic flow prediction models based on deep neural networks has become a current research hotspot. Most of the current traffic flow prediction methods are designed from the perspective of model architectures, using only the traffic features of future moments as supervision signals to guide the models to learn the spatiotemporal dependence in traffic flow. However, traffic flow data themselves contain rich spatiotemporal features, and it is feasible to obtain additional self-supervised signals from the data to assist the model to further explore the underlying spatiotemporal dependence. Therefore, we propose a self-supervised traffic flow prediction method based on a spatiotemporal masking strategy. A framework consisting of symmetric backbone models with asymmetric task heads were applied to learn both prediction and spatiotemporal context features. Specifically, a spatiotemporal context mask reconstruction task was designed to force the model to reconstruct the masked features via spatiotemporal context information, so as to assist the model to better understand the spatiotemporal contextual associations in the data. In order to avoid the model simply making inferences based on the local smoothness in the data without truly learning the spatiotemporal dependence, we performed a temporal shift operation on the features to be reconstructed. The experimental results showed that the model based on the spatiotemporal context masking strategy achieved an average prediction performance improvement of 1.56% and a maximum of 7.72% for longer prediction horizons of more than 30 min compared with the backbone models.

show abstract

Aircraft Trajectory Prediction Enhanced through Resilient Generative Adversarial Networks Secured by Blockchain: Application to UAS-S4 Ehécatl

Cited by 9 publications

References 51 publications

Blockchain PoS and PoW Consensus Algorithms for Airspace Management Application to the UAS-S4 Ehécatl

Blockchain PoS and PoW Consensus Algorithms for Airspace Management Application to the UAS-S4 Ehécatl

Artificial Intelligence in Aviation: New Professionals for New Technologies

Self-Supervised Spatiotemporal Masking Strategy-Based Models for Traffic Flow Forecasting

Contact Info

Product

Resources

About