University of Hertfordshire

From the same journal

By the same authors

HMIAN: a Hierarchical Mapping and Interactive Attention Data Fusion Network for Traffic Forecasting

Research output: Contribution to journalArticlepeer-review

Standard

HMIAN: a Hierarchical Mapping and Interactive Attention Data Fusion Network for Traffic Forecasting. / Sun, Jingru; Peng, Mu; Jiang, Hongbo ; Hong , Qinghui; Sun, Yichuang.

In: IEEE Internet of Things Journal, 19.08.2022.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{8e39303121c3419583145722cc24156f,
title = "HMIAN: a Hierarchical Mapping and Interactive Attention Data Fusion Network for Traffic Forecasting",
abstract = "With the development of intelligent transportation system (ITS), the vital technology of ITS, short-term traffic forecasting, gains increasing attention. However, the existing prediction models ignore the impact of urban functional zones on traffic data, resulting in inaccurate extractions of dynamic spatial relationships from network. Furthermore, how to calculate the influence of external factors such as weather and holidays on traffic is an unsolved problem. This paper proposes a spatio-temporal hierarchical mapping and interactive attention network (HMIAN), which extracts the spatial features from traffic network by constructing functional zones, and designs an effective external factors fusion method. HMIAN uses the hierarchical mapping structure to aggregate the roads into functional zones, calculate the interaction between functional zones and feed this information back to the spatial features. And the interactive attention mechanism is utilized to fuse the traffic data with external factors effectively, and extracts temporal features. In addition, some experiments were carried out on three real traffic data sets. First, experiment results show that the proposed model better prediction performance compared with other existing approaches in more complex traffic network. Second, the longitudinal comparison experiment verifies that the hierarchical mapping structure is effective in extracting spatial features in complex road network. Finally, the influence of different external factors and fusion methods on traffic prediction are compared, which provides a consult for subsequent research on the influence of external factors.",
author = "Jingru Sun and Mu Peng and Hongbo Jiang and Qinghui Hong and Yichuang Sun",
note = "{\textcopyright} 2022 IEEE. This is the accepted manuscript version of an article which has been published in final form at https://doi.org/10.1109/JIOT.2022.3196461",
year = "2022",
month = aug,
day = "19",
doi = "10.1109/JIOT.2022.3196461",
language = "English",
journal = "IEEE Internet of Things Journal",
issn = "2327-4662",
publisher = "IEEE",

}

RIS

TY - JOUR

T1 - HMIAN: a Hierarchical Mapping and Interactive Attention Data Fusion Network for Traffic Forecasting

AU - Sun, Jingru

AU - Peng, Mu

AU - Jiang, Hongbo

AU - Hong , Qinghui

AU - Sun, Yichuang

N1 - © 2022 IEEE. This is the accepted manuscript version of an article which has been published in final form at https://doi.org/10.1109/JIOT.2022.3196461

PY - 2022/8/19

Y1 - 2022/8/19

N2 - With the development of intelligent transportation system (ITS), the vital technology of ITS, short-term traffic forecasting, gains increasing attention. However, the existing prediction models ignore the impact of urban functional zones on traffic data, resulting in inaccurate extractions of dynamic spatial relationships from network. Furthermore, how to calculate the influence of external factors such as weather and holidays on traffic is an unsolved problem. This paper proposes a spatio-temporal hierarchical mapping and interactive attention network (HMIAN), which extracts the spatial features from traffic network by constructing functional zones, and designs an effective external factors fusion method. HMIAN uses the hierarchical mapping structure to aggregate the roads into functional zones, calculate the interaction between functional zones and feed this information back to the spatial features. And the interactive attention mechanism is utilized to fuse the traffic data with external factors effectively, and extracts temporal features. In addition, some experiments were carried out on three real traffic data sets. First, experiment results show that the proposed model better prediction performance compared with other existing approaches in more complex traffic network. Second, the longitudinal comparison experiment verifies that the hierarchical mapping structure is effective in extracting spatial features in complex road network. Finally, the influence of different external factors and fusion methods on traffic prediction are compared, which provides a consult for subsequent research on the influence of external factors.

AB - With the development of intelligent transportation system (ITS), the vital technology of ITS, short-term traffic forecasting, gains increasing attention. However, the existing prediction models ignore the impact of urban functional zones on traffic data, resulting in inaccurate extractions of dynamic spatial relationships from network. Furthermore, how to calculate the influence of external factors such as weather and holidays on traffic is an unsolved problem. This paper proposes a spatio-temporal hierarchical mapping and interactive attention network (HMIAN), which extracts the spatial features from traffic network by constructing functional zones, and designs an effective external factors fusion method. HMIAN uses the hierarchical mapping structure to aggregate the roads into functional zones, calculate the interaction between functional zones and feed this information back to the spatial features. And the interactive attention mechanism is utilized to fuse the traffic data with external factors effectively, and extracts temporal features. In addition, some experiments were carried out on three real traffic data sets. First, experiment results show that the proposed model better prediction performance compared with other existing approaches in more complex traffic network. Second, the longitudinal comparison experiment verifies that the hierarchical mapping structure is effective in extracting spatial features in complex road network. Finally, the influence of different external factors and fusion methods on traffic prediction are compared, which provides a consult for subsequent research on the influence of external factors.

U2 - 10.1109/JIOT.2022.3196461

DO - 10.1109/JIOT.2022.3196461

M3 - Article

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

ER -