“…To verify the superiority of this method, DGLSTM is compared with LSTM [25], random forest (RF) [16], BP neural network (BPNN) [20], and Markov method. LSTM only used information related to delays at the current airport.…”
Section: Experimental Results and Analysismentioning
Due to the strong propagation causality of delays between airports, this paper proposes a delay prediction model based on a deep graph neural network to study delay prediction from the perspective of an airport network. We regard airports as nodes of a graph network and use a directed graph network to construct airports’ relationship. For adjacent airports, weights of edges are measured by the spherical distance between them, while the number of flight pairs between them is utilized for airports connected by flights. On this basis, a diffusion convolution kernel is constructed to capture characteristics of delay propagation between airports, and it is further integrated into the sequence-to-sequence LSTM neural network to establish a deep learning framework for delay prediction. We name this model as deep graph-embedded LSTM (DGLSTM). To verify the model’s effectiveness and superiority, we utilize the historical delay data of 325 airports in the United States from 2015 to 2018 as the model training set and test set. The experimental results suggest that the proposed method is superior to the existing mainstream methods in terms of accuracy and robustness.
“…To verify the superiority of this method, DGLSTM is compared with LSTM [25], random forest (RF) [16], BP neural network (BPNN) [20], and Markov method. LSTM only used information related to delays at the current airport.…”
Section: Experimental Results and Analysismentioning
Due to the strong propagation causality of delays between airports, this paper proposes a delay prediction model based on a deep graph neural network to study delay prediction from the perspective of an airport network. We regard airports as nodes of a graph network and use a directed graph network to construct airports’ relationship. For adjacent airports, weights of edges are measured by the spherical distance between them, while the number of flight pairs between them is utilized for airports connected by flights. On this basis, a diffusion convolution kernel is constructed to capture characteristics of delay propagation between airports, and it is further integrated into the sequence-to-sequence LSTM neural network to establish a deep learning framework for delay prediction. We name this model as deep graph-embedded LSTM (DGLSTM). To verify the model’s effectiveness and superiority, we utilize the historical delay data of 325 airports in the United States from 2015 to 2018 as the model training set and test set. The experimental results suggest that the proposed method is superior to the existing mainstream methods in terms of accuracy and robustness.
“…In the methodology section describes the flow of work for the algorithms that were applied .The main objective is to build a model to predict the delay of the flights that meets the state of art. neural network gave an amazing performance in terms of flight delay prediction [16], [18], [24], [25], [26], [27], [11], especially RNN,LTSM [17] and DBN [29].…”
Commercial airlines and the passengers suffer from flight delay. Flight delay causes huge loss for the airlines and unsatisfied passengers. The researchers attempt to solve this problem through prediction extensively by machine learning approach and data mining tools. Accurate and robust performance is still to get through existing models. Our proposed hybrid approach is intended to use the power of machine learning as data mining tool and to predict the delay using classification algorithm of deep learning. An extensive evaluation of the proposed method is carried out by comparing the performance by using two data sets: one is local and the other is benchmark from Kaggle to obtain the best performing classifier. Three predictive models were applied on the datasets: logistic regression, decision tree and the proposed approach. The result shows that the proposed method performed well as comparing to the existing state-ofthe art.
“…e researchers [19] introduced a new type of multilevel input layer ANN capable of handling nominal variables in order to predict the delay of incoming flights at JFK airport. e authors in [20] applied decision trees, random forest, multilayer perceptron, and different sampling techniques to predict flight delays.…”
Flight delay is the most common preoccupation of aviation stakeholders around the world. Airlines, which suffer from a monetary and customer loyalty loss, are the most affected. Various studies have attempted to analyze and solve flight delays using machine learning algorithms. This research aims to predict flights’ arrival delay using Artificial Neural Network (ANN). We applied a MultiLayer Perceptron (MLP) to train and test our data. Two approaches have been adopted in our work. In the first one, we used historical flight data extracted from Bureau of Transportation Statistics (BTS). The second approach improves the efficiency of the model by applying selective-data training. It consists of selecting only most relevant instances from the training dataset which are delayed flights. According to BTS, a flight whose difference between scheduled and actual arrival times is 15 minutes or greater is considered delayed. Departure delays and flight distance proved to be very contributive to flight delays. An adjusted and optimized hyperparameters using grid search technique helped us choose the right architecture of the network and have a better accuracy and less error than the existing literature. The results of both traditional and selective training were compared. The efficiency and time complexity of the second method are compared against those of the traditional training procedure. The neural network MLP was able to predict flight arrival delay with a coefficient of determination
R
2
of 0.9048, and the selective procedure achieved a time saving and a better
R
2
score of 0.9560. To enhance the reliability of the proposed method, the performance of the MLP was compared with that of Gradient Boosting (GB) and Decision Trees (DT). The result is that the MLP outperformed all existing benchmark methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.