Optimization of air traffic management efficiency based on deep learning enriched by the long short-term memory (LSTM) and extreme learning machine (ELM)

Aghdam, Mahdi Yousefzadeh; Tabbakh, Seyed Reza Kamel; Chabok, Seyed Javad Mahdavi; Kheyrabadi, Maryam

doi:10.1186/s40537-021-00438-6

Cited by 17 publications

(4 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The confusion matrix [46] represents the iterative results of the actual and predicted data. The predicted data comprise the output after executing the model.…”

Section: Discussion Of the Algorithm Resultsmentioning

confidence: 99%

Reservoir Prediction Model via the Fusion of Optimized Long Short-Term Memory Network (LSTM) and Bidirectional Random Vector Functional Link (RVFL)

Pan

2022

Electronics

View full text Add to dashboard Cite

An accurate and stable reservoir prediction model is essential for oil location and production. We propose an predictive hybrid model ILSTM-BRVFL based on an improved long short-term memory network (IAOS-LSTM) and a bidirectional random vector functional link (Bidirectional-RVFL) for this problem. Firstly, the Atomic Orbit Search algorithm (AOS) is used to perform collective optimization of the parameters to improve the stability and accuracy of the LSTM model for high-dimensional feature extraction. At the same time, there is still room to improve the optimization capability of the AOS. Therefore, an improvement scheme to further enhance the optimization capability is proposed. Then, the LSTM-extracted high-dimensional features are fed into the random vector functional link (RVFL) to improve the prediction of high-dimensional features by the RVFL, which is modified as the bidirectional RVFL. The proposed ILSTM-BRVFL (IAOS) model achieves an average prediction accuracy of 95.28%, compared to the experimental results. The model’s accuracy, recall values, and F1 values also showed good performance, and the prediction ability achieved the expected results. The comparative analysis and the degree of improvement in the model results show that the high-dimensional extraction of the input data by LSTM is the most significant improvement in prediction accuracy. Secondly, it introduces a double-ended mechanism for IAOS to LSTM and RVFL for parameter search.

show abstract

“…The confusion matrix [46] represents the iterative results of the actual and predicted data. The predicted data comprise the output after executing the model.…”

Section: Discussion Of the Algorithm Resultsmentioning

confidence: 99%

Reservoir Prediction Model via the Fusion of Optimized Long Short-Term Memory Network (LSTM) and Bidirectional Random Vector Functional Link (RVFL)

Pan

2022

Electronics

View full text Add to dashboard Cite

show abstract

“…Machine learning techniques have been previously applied to flight planning primarily for path planning, optimization, and scheduling [8][9][10][11][12]. In this work, we use state-of-the-art machine learning (ML) technologies to enhance flight planning operations by recognizing, predicting, and incorporating plan changes due to undesirable flight routing behaviors, in-mission coordination decisions and Air Traffic Control deviations early into the planning cycle.…”

Section: Figure 1: Current Flight Planning Processmentioning

confidence: 99%

Improving flight planning efficiency through machine learning

Vaidyanathan,

Danet,

Tran

et al. 2024

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications VI

View full text Add to dashboard Cite

Flight planning in support of multi-domain operations is a complex and manpower intensive process. Multiple factors such as changing environmental conditions, navigational data and constraints, air-traffic procedures and policies, maturation of routes and coordination with all stakeholders contribute to this complexity. These changing constraints result in multiple updates and deviations to the flight plans which eventually impact mission objectives and timing. This work applies state-of-the-art machine learning technologies to automatically determine the quality of generated flight plans to enable rapid verification and approval for plan filing. It also identifies preferred routes that are input into planner that results in higher flight plan acceptance rates. We leverage voluminous sources of real operational flight planning data and filed planning data to develop the models. Supervised learning is leveraged to predict whether a generated plan will be filed or rejected. The unsupervised learning component identifies flight plan preferences for feedback to the planner system. These models could be eventually deployed in a flight planning operational environment to reduce human effort, cost, and time to generate flyable plans. The results from this work could also be used to improve planner rules and search algorithms.

show abstract

“…In other cases, some of these models take time to train, tune, and optimize before acceptable levels of performance are reached. Therefore, this may limit their application in real-time [64,65].…”

Section: A Existing Approaches To Arrival Traffic Modelingmentioning

confidence: 99%

A Comparative Analysis of Terminal Area Navigation and Conventional Standard Arrival Routes with Cellular Automata

Ogedengbe

Wong

Liem

2023

AIAA AVIATION 2023 Forum

View full text Add to dashboard Cite

Aircraft arrival at airports is limited by the physical configuration and layout of the terminal maneuvering area (TMA), which might result in a bottleneck. In a bottleneck situation, navigation is made difficult because arriving aircraft will need special considerations to manage congestion and guarantee safety. In addition, the operating cost of airline operators increases with higher fuel consumption encountered in the extra airborne time. Likewise, passengers incur more travel time with the additional arrival delays. Traditional arrival adopts conventional standard arrival route (STAR), with trajectories that are rigidly coordinated by air traffic controller (ATC). However, a more flexible approach to general navigation has also been introduced, namely the area navigation (RNAV), which makes provision for flexibility in aircraft path selection. This flexibility is enabled by abstract navigational elements, namely waypoints that are unlike conventional navigational aids (NAVAIDs). We look at a modeling framework that juxtaposes the key elements of the traditional STAR (procedure-based) navigation and RNAV (performance-based) navigation. We adopt the cellular automata (CA) framework that has the capability to model the dynamic interaction between aircraft, inherent environmental uncertainties, and arrival route as defined by waypoints. To this end, we develop a modeling environment that enables a fair comparison between these two approaches under similar conditions to determine their respective viability. The effect of the number of waypoints in the TMA under different traffic conditions is illustrated using the relationship between TMA occupancy, traffic flow, and the landing rate. Results show that RNAV navigation exhibits more sensitivity to waypoint distribution within the TMA in terms of throughput, compared to STAR navigation. STAR navigation, on the other hand, demonstrates inherent latency that allows for higher capacities, albeit at the risk of initiating abrupt jamming when a high number of waypoints are active. Consequently, we are able to establish guidelines that justify the adoption RNAV over STAR and vice versa. Furthermore, we also identify performance disparities between them, and where each approach is desirable.

show abstract

Optimization of air traffic management efficiency based on deep learning enriched by the long short-term memory (LSTM) and extreme learning machine (ELM)

Cited by 17 publications

References 55 publications

Reservoir Prediction Model via the Fusion of Optimized Long Short-Term Memory Network (LSTM) and Bidirectional Random Vector Functional Link (RVFL)

Reservoir Prediction Model via the Fusion of Optimized Long Short-Term Memory Network (LSTM) and Bidirectional Random Vector Functional Link (RVFL)

Improving flight planning efficiency through machine learning

A Comparative Analysis of Terminal Area Navigation and Conventional Standard Arrival Routes with Cellular Automata

Contact Info

Product

Resources

About