A Deep Graph-Embedded LSTM Neural Network Approach for Airport Delay Prediction

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.

Mathematic modeling of a new inlay buoyancy artefact

The novel buoyancy artefact concept for the use in mass metrology enables the determination and correction of systematic air buoyancy effects caused by measurements outside a vacuum. In contrast to other buoyancy artefacts with a nominal mass of 1 kg, the new artefact, called inlay artefact, has a smaller volume resulting from an enclosed tungsten core. The theoretical design of the new artefact consists of dismountable discs with spherical distance pieces and a cylinder. This work focuses on the design and mathematical model considering limiting factors caused by the handling and the geometry of the comparators used.

THE SPHERICAL DISTANCE FOR INTUITIONISTIC FUZZY SETS AND ITS APPLICATION IN DECISION ANALYSIS

Different from traditional distances between Intuitionistic Fuzzy Sets (IFS), the spherical distance between two IFSs relies not only on their relative differences but also their absolute values. In this paper, we generalize the properties of spherical distance measures between IFSs, and investigate the applications of spherical distance measures in group decision making, pattern recognition and medical diagnosis. We develop an optimization spherical distance model with IFS preference in group decision making, and demonstrate that this model is feasible and practical with an evaluation model of drought risk. By using comparative analysis method, we show that this new spherical distance can also be applied in other fields such as pattern recognition and medical diagnosis.