Unified Spatial-Temporal Neighbor Attention Network for Dynamic Traffic Prediction

Long, Wangchen; Xiao, Zhu; Jiang, Hongbo; Chen, Jie; Li, You; Alazab, Mamoun

doi:10.1109/tvt.2022.3209242

Cited by 67 publications

(14 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning-based approaches utilize either traditional machine learning ( e.g ., random forest, support vector machines) or deep learning ( e.g ., artificial neural networks (ANN), convolutional neural networks (CNN), recurrent neural networks (RNN)) for modeling by learning from historical data ( Nora & El-Gohary, 2018 ; Tian et al, 2019 ). These machine learning-based approaches usually exhibit better performance compared to other methods, especially in event detection ( Wang et al, 2023 ; Sun et al, 2023c ; Ren et al, 2022 ) and other applications using time-series data ( Sun et al, 2023a , 2023b ; Long et al, 2023 ). To predict perennial energy use, Azadeh, Ghaderi & Sohrabkhani (2008) suggested using ANN in combination with an analysis of variance.…”

Section: Introductionmentioning

confidence: 99%

Predicting energy use in construction using Extreme Gradient Boosting

Han,

Shu,

Wang

2023

PeerJ Computer Science

View full text Add to dashboard Cite

Annual increases in global energy consumption are an unavoidable consequence of a growing global economy and population. Among different sectors, the construction industry consumes an average of 20.1% of the world’s total energy. Therefore, exploring methods for estimating the amount of energy used is critical. There are several approaches that have been developed to address this issue. The proposed methods are expected to contribute to energy savings as well as reduce the risks of global warming. There are diverse types of computational approaches to predicting energy use. These existing approaches belong to the statistics-based, engineering-based, and machine learning-based categories. Machine learning-based frameworks showed better performance compared to these other approaches. In our study, we proposed using Extreme Gradient Boosting (XGB), a tree-based ensemble learning algorithm, to tackle the issue. We used a dataset containing energy consumption hourly recorded in an office building in Shanghai, China, from January 1, 2015, to December 31, 2016. The experimental results demonstrated that the XGB model developed using both historical and date features worked better than those developed using only one type of feature. The best-performing model achieved RMSE and MAPE values of 109.00 and 0.24, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting energy use in construction using Extreme Gradient Boosting

Han,

Shu,

Wang

2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Thus, the automatic flight plan generation (FPG) has become an urgent topic for air transport field. Some novel initiatives are widely discussed in both academia and industry, such as coded departure routes (CDRs) [2], dynamic weather routes (DWR) [3,4], collaborative trajectory options program (CTOP) [5], and other transportation areas [6][7][8][9]. Note that, the flight plan is generated via solving the optimization program to meet a set of operational metrics.…”

Section: Introductionmentioning

confidence: 99%

Sequence‐to‐sequence transfer transformer network for automatic flight plan generation

Yang,

Qian,

Zhang

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

In this work, a machine translation framework is proposed to tackle the flight plan generation in the air transport field. Diverging from the traditional human expert‐based way, a novel sequence‐to‐sequence transfer transformer network to automatic flight plan generation with enhanced operational acceptability is presented. It allows the user to translate the departure and arrival airport pairs denoted as test sentences, into the flyable waypoint sequences denoted as the corresponding source sentences. The approach leverages deep neural networks to autonomously learn air transport specialized knowledge and human expert insights from industry legacy data. Moreover, a multi‐head attention mechanism is adopted to model the complex correlation between airport pairs. Besides, we introduce an innovative waypoint embedding layer to learn effective embeddings for waypoint sequences. Additionally, an extensive flight plan dataset is constructed utilizing real‐world data in China spanning from July to September 2019. Employing the proposed model, rigorous training and testing procedures are conducted on this dataset, yielding remarkably favourable outcomes based on automatic evaluation metrics that are BLEU and METEOR, which outperform other popular approaches. More importantly, the proposed approach achieves high performance in the operational validation and visualization, showing its application potential for real‐world air traffic operation.

show abstract

“…Meanwhile, it also offers opportunities to extract travel behavior and spatial-temporal characteristics from private car trajectories, enabling the analysis of complex intersections, the study of car aggregation effects, and the assessment of urban attractiveness for human travel behavior and city planning. Furthermore, scholars have also utilized vehicle trajectory big data in the fields of intelligent transportation and smart city planning, thereby providing valuable insights for private car route selection, urban traffic network construction, and traffic flow prediction [10][11][12]. Particularly, by understanding private car travel behavior and capturing the spatiotemporal evolution of urban hotspots, these data-driven approaches offer new perspectives for addressing urban challenges, mitigating traffic congestion, and improving transportation services [13,14].…”

Section: Introductionmentioning

confidence: 99%

Impact of Built Environment on Carbon Emissions from Cross-District Mobility: A Social Network Analysis Based on Private Vehicle Trajectory Big Data

Chen

Xiao

2023

Sustainability

Self Cite

View full text Add to dashboard Cite

The realization of the “double carbon” goals and the development of green transportation require a focused approach to reducing carbon emissions from private cars. Starting from the perspective of social network analysis, this paper constructs the carbon emission network of private car cross-district mobility based on vehicle trajectory big data in Guangzhou and Foshan and analyzes its spatial network characteristics. Next, the MRQAP model is constructed to examine the impact of built environment factors on carbon emissions from private cars. Furthermore, the paper explores the moderating effect of private car mobility in the central urban area. The results indicate the following: (1) Private vehicle cross-district mobility in the Guangzhou and Foshan region are closely interconnected and exhibit a phenomenon of central clustering. (2) Both population density and the number of road intersections have a positive relationship with private car carbon emissions, and after a series of robustness tests, the results are still valid. (3) Private vehicle mobility in central urban areas contributes to an increase in carbon emissions, and the positive impact is reinforced by population density, while road intersections and private car mobility in central urban areas have a substitutive effect on private car carbon emissions.

show abstract

Unified Spatial-Temporal Neighbor Attention Network for Dynamic Traffic Prediction

Cited by 67 publications

References 43 publications

Predicting energy use in construction using Extreme Gradient Boosting

Predicting energy use in construction using Extreme Gradient Boosting

Sequence‐to‐sequence transfer transformer network for automatic flight plan generation

Impact of Built Environment on Carbon Emissions from Cross-District Mobility: A Social Network Analysis Based on Private Vehicle Trajectory Big Data

Contact Info

Product

Resources

About