Tracing the spatial‐temporal evolution dynamics of air traffic systems using graph theories

Hu, Cui-E; Xiao, S.; Gao, Luyao; Li, Mingyang

doi:10.1002/int.22927

Cited by 4 publications

(6 citation statements)

References 42 publications

(87 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A smooth, flexible, and robust air traffic network should be efficient and economic, but not easily disrupted when there are issues. Graph theory models prove to be efficient tools to provide guidance on how to manage air traffic networks optimally as seen in many applications (Dunn, S., & Wilkinson, S. M., 2016;Farrahi, A. H., et al, 2017;Ren, P., & Li, L., 2018;Hu, C., et al, 2022). Water distribution systems are essential, as many regions face clean water crises and costs can be so high that they hinder local economic development.…”

Section: Literaturementioning

confidence: 99%

Cost Accounting in Multiple-Source and Multiple-Sink Logistics Management From Network Flow Perspectives

2022

JABE

View full text Add to dashboard Cite

Transportation and logistics costs are becoming a large portion of the operating expenses for many businesses. Recently, supply chain disruptions caused by the COVID-19 pandemic and inflation crisis have brought challenges, especially, to many small-and medium-sized companies. Not only are companies struggling with logistics costs, but logistics bottlenecks are often preventing businesses from growing, expanding, and obtaining additional market shares. According to both academics and practitioners, there must be more literature and studies to address these logistics management challenges from cost accounting perspectives. This study focuses on multiple-source and multiple-sink scenarios, in which products are delivered from various production units to various stores. Optimized solutions to these cases may suggest optimal logistics strategies in terms of the minimized costs, as well as provide insights for later profitability analysis through common cost allocations and segment income statement reports. This paper can contribute to the practical examples in logistics management for businesses and is an addition to the current literature on cost accounting issues.

show abstract

Section: Literaturementioning

confidence: 99%

Cost Accounting in Multiple-Source and Multiple-Sink Logistics Management From Network Flow Perspectives

2022

JABE

View full text Add to dashboard Cite

show abstract

“…Graphs can abstractly describe the relationships between objects and have received much attention from researchers [1,2]. Graph neural networks (GNNs) combine node features and graph structure with learning better representations and have achieved signifcant performance in many tasks, e.g., graph classifcation [3], node classifcation [4], and link prediction [5,6].…”

Section: Introductionmentioning

confidence: 99%

“…Te GNNs that train the backdoor dataset are called backdoor GNNs, and the clean GNNs are trained on the clean dataset [14]. Te output of backdoor GNNs has two characteristics: (1) the output on the clean data is similar to that of clean GNNs; (2) the output on the poisoned data is predefned by the adversary.…”

Section: Introductionmentioning

confidence: 99%

Feature-Based Graph Backdoor Attack in the Node Classification Task

Chen

Zhao

et al. 2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

Graph neural networks (GNNs) have shown significant performance in various practical applications due to their strong learning capabilities. Backdoor attacks are a type of attack that can produce hidden attacks on machine learning models. GNNs take backdoor datasets as input to produce an adversary-specified output on poisoned data but perform normally on clean data, which can have grave implications for applications. Backdoor attacks are under-researched in the graph domain, and almost existing graph backdoor attacks focus on the graph-level classification task. To close this gap, we propose a novel graph backdoor attack that uses node features as triggers and does not need knowledge of the GNNs parameters. In the experiments, we find that feature triggers can destroy the feature spaces of the original datasets, resulting in GNNs inability to identify poisoned data and clean data well. An adaptive method is proposed to improve the performance of the backdoor model by adjusting the graph structure. We conducted extensive experiments to validate the effectiveness of our model on three benchmark datasets.

show abstract

“…Trafc fow prediction is a prominent example of the spatiotemporal prediction [1,2] problem and is an important section of the intelligent transportation system (ITS) [3][4][5]. Te study of spatiotemporal prediction involves the analysis of historical data across both spatial and temporal dimensions to extract underlying patterns of change and facilitate the generation of prediction.…”

Section: Introductionmentioning

confidence: 99%

“…Te GDESolver can help the model obtain higher accuracy with lower memory occupancy. (3) We conduct experiments on real-world datasets to evaluate the efectiveness of our proposed approach. Our experimental results corroborate the efcacy of the GDENet model, demonstrating higher computational efciency and a greater practical value than the current state-of-the-art methods for trafc fow prediction.…”

Section: Introductionmentioning

confidence: 99%

GDENet: Graph Differential Equation Network for Traffic Flow Prediction

Miao,

Tang,

Wang

et al. 2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

The accurate prediction of traffic flow is paramount for the advancement of intelligent transportation systems. Despite this, current prediction models only account for either temporal or spatial features in isolation, without considering their interaction, impeding the model’s ability to express itself. In light of this, we propose the graph differential equations network (GDENet), an approach that can effectively mine spatiotemporal correlation. Specifically, we propose a spatiotemporal feature integrator (STFI), which alleviates the error caused by the deviation of the sampling distribution from the overall distribution. By incorporating temporal information into the model for training and combining it with spatial features, we thoroughly explore the spatiotemporal intrinsic association. When compared to state-of-the-art methods, our proposed algorithm reduces memory consumption and elevates computational efficiency and the practical value. We conduct experiments with real-world datasets, and our proposed model outperformed advanced prediction models.

show abstract

Tracing the spatial‐temporal evolution dynamics of air traffic systems using graph theories

Cited by 4 publications

References 42 publications

Cost Accounting in Multiple-Source and Multiple-Sink Logistics Management From Network Flow Perspectives

Cost Accounting in Multiple-Source and Multiple-Sink Logistics Management From Network Flow Perspectives

Feature-Based Graph Backdoor Attack in the Node Classification Task

GDENet: Graph Differential Equation Network for Traffic Flow Prediction

Contact Info

Product

Resources

About