Artificial neural network models for airport capacity prediction

TL;DR: This study proposes a novel parallel-series model and adaptive bidirectional extreme learning machine (AB-ELM) for predicting IATA-coded flight delays and analyzing their causes, achieving 80.66% accuracy with reduced imbalanced and noisy data.

TL;DR: This study develops an Artificial Neural Network (ANN) model to predict domestic air passenger demand in emerging economies, achieving high accuracy (0.92) and outperforming conventional linear regression models with socio-economic parameters as input variables.

TL;DR: This study compares neural network models (RNN, LSTM, GRU) to traditional time series models (ARIMA, SARIMA) for short-term airport passenger flow forecasting, finding RNNs outperform SARIMA by 34% during pandemic periods, but not during normal periods.

TL;DR: This work considers the multi-airport scenario and proposes a novel spatio-temporal hybrid deep learning model to efficiently capture spatial correlations as well as temporal dependencies in a parallelized way to address the heterogeneity of airports.

TL;DR: In this paper, the authors quantify the transferability of features from the first layer to the last layer of a deep neural network and show that transferability is negatively affected by two distinct issues: (1) the specialization of higher layer neurons to their original task at the expense of performance on the target task and (2) optimization difficulties related to splitting networks between co-adapted neurons.

TL;DR: In this paper, deep recurrent neural networks (RNNs) are used to combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs.

TL;DR: It is shown that when stochastic gradient descent with momentum uses a well-designed random initialization and a particular type of slowly increasing schedule for the momentum parameter, it can train both DNNs and RNNs to levels of performance that were previously achievable only with Hessian-Free optimization.

TL;DR: This paper quantifies the generality versus specificity of neurons in each layer of a deep convolutional neural network and reports a few surprising results, including that initializing a network with transferred features from almost any number of layers can produce a boost to generalization that lingers even after fine-tuning to the target dataset.