research-article

A Multi-Stream Feature Fusion Approach for Traffic Prediction

Authors:

Xiang SuAuthors Info & Claims

IEEE Transactions on Intelligent Transportation Systems, Volume 23, Issue 2

Pages 1456 - 1466

https://doi.org/10.1109/TITS.2020.3026836

Published: 01 February 2022 Publication History

Abstract

Accurate and timely traffic flow prediction is crucial for intelligent transportation systems (ITS). Recent advances in graph-based neural networks have achieved promising prediction results. However, some challenges remain, especially regarding graph construction and the time complexity of models. In this paper, we propose a multi-stream feature fusion approach to extract and integrate rich features from traffic data and leverage a data-driven adjacent matrix instead of the distance-based matrix to construct graphs. We calculate the Spearman rank correlation coefficient between monitor stations to obtain the initial adjacent matrix and fine-tune it while training. As to the model, we construct a multi-stream feature fusion block (MFFB) module, which includes a three-channel network and the soft-attention mechanism. The three-channel networks are graph convolutional neural network (GCN), gated recurrent unit (GRU) and fully connected neural network (FNN), which are used to extract spatial, temporal and other features, respectively. The soft-attention mechanism is utilized to integrate the obtained features. The MFFB modules are stacked, and a fully connected layer and a convolutional layer are used to make predictions. We conduct experiments on two real-world traffic prediction tasks and verify that our proposed approach outperforms the state-of-the-art methods within an acceptable time complexity.

References

[1]

J. Zhang, F.-Y. Wang, K. Wang, W.-H. Lin, X. Xu, and C. Chen, “Data-driven intelligent transportation systems: A survey,” IEEE Trans. Intell. Transp. Syst., vol. 12, no. 4, pp. 1624–1639, Dec. 2011.

Digital Library

[2]

Y.-C. Chiu, H. Zheng, J. Villalobos, and B. Gautam, “Modeling no-notice mass evacuation using a dynamic traffic flow optimization model,” IIE Trans., vol. 39, no. 1, pp. 83–94, Jan. 2007.

[3]

G. Xiong, D. Shen, X. Dong, B. Hu, D. Fan, and F. Zhu, “Parallel transportation management and control system for subways,” IEEE Trans. Intell. Transp. Syst., vol. 18, no. 7, pp. 1974–1979, Jul. 2017.

Digital Library

[4]

Y. Lv, Y. Duan, W. Kang, Z. Li, and F.-Y. Wang, “Traffic flow prediction with big data: A deep learning approach,” IEEE Trans. Intell. Transp. Syst., vol. 16, no. 2, pp. 865–873, Apr. 2015.

Digital Library

[5]

R. Fu, Z. Zhang, and L. Li, “Using LSTM and GRU neural network methods for traffic flow prediction,” in Proc. Annu. Conf. Chin. Assoc. Autom., 2017, pp. 324–328.

[6]

P. Lopez-Garcia, E. Onieva, E. Osaba, A. D. Masegosa, and A. Perallos, “A hybrid method for short-term traffic congestion forecasting using genetic algorithms and cross entropy,” IEEE Trans. Intell. Transp. Syst., vol. 17, no. 2, pp. 557–569, Feb. 2016.

Digital Library

[7]

X. Han, Y. Chen, J. Shi, and Z. He, “An extended cell transmission model based on digraph for urban traffic road network,” in Proc. 15th Int. IEEE Conf. Intell. Transp. Syst., Sep. 2012, pp. 558–563.

[8]

U. von Luxburg, “A tutorial on spectral clustering,” Statist. Comput., vol. 17, no. 4, pp. 395–416, Dec. 2007.

Digital Library

[9]

W. Liu and L. Lü, “Link prediction based on local random walk,” EPL, vol. 89, no. 5, p. 58007, Mar. 2010.

[10]

D. I. Shuman, S. K. Narang, P. Frossard, A. Ortega, and P. Vandergheynst, “The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains,” IEEE Signal Process. Mag., vol. 30, no. 3, pp. 83–98, May 2013.

[11]

X. Genget al., “Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting,” in Proc. AAAI Conf. Artif. Intell., vol. 33, 2019, pp. 3656–3663.

[12]

L. Lin, Z. He, and S. Peeta, “Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach,” Transp. Res. C, Emerg. Technol., vol. 97, pp. 258–276, Dec. 2018.

[13]

Z. Liet al., “A hybrid deep learning approach with GCN and LSTM for traffic flow Prediction*,” in Proc. IEEE Intell. Transp. Syst. Conf. (ITSC), Oct. 2019, pp. 1929–1933.

[14]

A. Howardet al., “Searching for MobileNetV3,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2019, pp. 1314–1324.

[15]

L. Li, X. Su, Y. Wang, Y. Lin, Z. Li, and Y. Li, “Robust causal dependence mining in big data network and its application to traffic flow predictions,” Transp. Res. C, Emerg. Technol., vol. 58, pp. 292–307, Sep. 2015.

[16]

Z. Li, M. N. Janardhanan, Q. Tang, and P. Nielsen, “Mathematical model and metaheuristics for simultaneous balancing and sequencing of a robotic mixed-model assembly line,” Eng. Optim., vol. 50, no. 5, pp. 877–893, May 2018.

[17]

P. Nie, Y. Zhi, and H. Zhao-Cheng, “Constrained Kalman filter combined predictor for short-term traffic flow,” J. Traffic Transp. Eng., vol. 8, no. 5, pp. 86–90, 2008.

[18]

M. Van Der Voort, M. Dougherty, and S. Watson, “Combining Kohonen maps with ARIMA time series models to forecast traffic flow,” Transp. Res. C, Emerg. Technol., vol. 4, no. 5, pp. 307–318, Oct. 1996.

[19]

M. Castro-Neto, Y.-S. Jeong, M.-K. Jeong, and L. D. Han, “Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions,” Expert Syst. Appl., vol. 36, no. 3, pp. 6164–6173, Apr. 2009.

Digital Library

[20]

Y. Kamarianakis, W. Shen, and L. Wynter, “Rejoinder: Real-time road traffic forecasting using regime-switching space–time models and adaptive lasso,” Appl. Stochastic Models Bus. Ind., vol. 28, no. 4, pp. 322–323, 2012.

Digital Library

[21]

L. Li, X. Chen, and L. Zhang, “Multimodel ensemble for freeway traffic state estimations,” IEEE Trans. Intell. Transp. Syst., vol. 15, no. 3, pp. 1323–1336, Jun. 2014.

[22]

X. Daiet al., “DeepTrend 2.0: A light-weighted multi-scale traffic prediction model using detrending,” Transp. Res. C, Emerg. Technol., vol. 103, pp. 142–157, Jun. 2019.

[23]

Z. Mei, F. Xiang, and L. Zhen-hui, “Short-term traffic flow prediction based on combination model of xgboost-lightgbm,” in Proc. Int. Conf. Sensor Netw. Signal Process. (SNSP), Oct. 2018, pp. 322–327.

[24]

Y. Lv, Y. Chen, L. Li, and F.-Y. Wang, “Generative adversarial networks for parallel transportation systems,” IEEE Intell. Transp. Syst. Mag., vol. 10, no. 3, pp. 4–10, 2018.

[25]

J. Gehring, M. Auli, D. Grangier, D. Yarats, and Y. N. Dauphin, “Convolutional sequence to sequence learning,” in Proc. 34th Int. Conf. Mach. Learn., vol. 70. Sydney, NSW, Australia: International Convention Centre, Aug. 2017, pp. 1243–1252.

[26]

B. Yu, H. Yin, and Z. Zhu, “Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting,” in Proc. 27th Int. Joint Conf. Artif. Intell., Jul. 2018, pp. 3634–3640.

[27]

L. Zhaoet al., “T-GCN: A temporal graph convolutional network for traffic prediction,” IEEE Trans. Intell. Transp. Syst., vol. 21, no. 9, pp. 3848–3858, Sep. 2020.

[28]

B. Liaoet al., “Deep sequence learning with auxiliary information for traffic prediction,” in Proc. 24th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Jul. 2018, pp. 537–546.

[29]

L. Getoor and C. P. Diehl, “Link mining: A survey,” Acm Sigkdd Explorations Newslett., vol. 7, no. 2, pp. 3–12, 2005.

Digital Library

[30]

J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl, “Neural message passing for quantum chemistry,” in Proc. 34th Int. Conf. Mach. Learn., vol. 70, 2017, pp. 1263–1272.

[31]

M. Defferrard, X. Bresson, and P. Vandergheynst, “Convolutional neural networks on graphs with fast localized spectral filtering,” in Proc. Adv. Neural Inf. Progression Syst., 2016, pp. 3844–3852.

[32]

T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” CoRR, vol. abs/1609.02907, 2016. [Online]. Available: http://arxiv.org/abs/1609.02907

[33]

F. P. Suchet al., “Robust spatial filtering with graph convolutional neural networks,” IEEE J. Sel. Topics Signal Process., vol. 11, no. 6, pp. 884–896, Sep. 2017.

[34]

P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, “Graph attention networks,” 2018, arXiv:1710.10903. [Online]. Available: https://arxiv.org/abs/1710.10903

[35]

J. Atwood and D. Towsley, “Diffusion-convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst., 2016, pp. 1993–2001.

[36]

Y. Seo, M. Defferrard, P. Vandergheynst, and X. Bresson, “Structured sequence modeling with graph convolutional recurrent networks,” in Proc. Adv. Neural Inf. Progression Syst., 2017, pp. 362–373.

[37]

Y. Li, R. Yu, C. Shahabi, and Y. Liu, “Diffusion convolutional recurrent neural network: Data-driven traffic forecasting,” in Proc. Int. Conf. Learn. Represent., 2018. [Online]. Available: https://openreview.net/forum?id=SJiHXGWAZ

[38]

B. Singh, T. K. Marks, M. Jones, O. Tuzel, and M. Shao, “A multi-stream bi-directional recurrent neural network for fine-grained action detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 1961–1970.

[39]

Z. Tuet al., “Multi-stream CNN: Learning representations based on human-related regions for action recognition,” Pattern Recognit., vol. 79, pp. 32–43, Jul. 2018.

[40]

W. Wei, Y. Wong, Y. Du, Y. Hu, M. Kankanhalli, and W. Geng, “A multi-stream convolutional neural network for sEMG-based gesture recognition in muscle-computer interface,” Pattern Recognit. Lett., vol. 119, pp. 131–138, Mar. 2019.

Digital Library

[41]

G. Sistu, S. Chennupati, and S. Yogamani, “Multi-stream cnn based video semantic segmentation for automated driving,” in Proc. Int. Joint Conf. Comput. Vis. Imag. Comput. Graph. Theory Appl., 2019, pp. 173–180.

[42]

D. K. Hammond, P. Vandergheynst, and R. Gribonval, “Wavelets on graphs via spectral graph theory,” Appl. Comput. Harmon. Anal., vol. 30, no. 2, pp. 129–150, Mar. 2011.

[43]

K. Cho, B. van Merrienboer, Ç. Gülçehre, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” CoRR, vol. abs/1406.1078, 2014. [Online]. Available: http://arxiv.org/abs/1406.1078

[44]

M. M. Prieto, E. Montañés, and O. Menéndez, “Power plant condenser performance forecasting using a non-fully connected artificial neural network,” Energy, vol. 26, no. 1, pp. 65–79, Jan. 2001.

[45]

S. Li, H. Jiang, and W. Pang, “Joint multiple fully connected convolutional neural network with extreme learning machine for hepatocellular carcinoma nuclei grading,” Comput. Biol. Med., vol. 84, pp. 156–167, May 2017.

Digital Library

[46]

H. Li, M. R. Min, Y. Ge, and A. Kadav, “A context-aware attention network for interactive question answering,” CoRR, vol. abs/1612.07411, 2016. [Online]. Available: http://arxiv.org/abs/1612.07411

[47]

A. Vaswaniet al., “Attention is all you need,” in Proc. Adv. Neural Inf. Process. Syst., 2017, pp. 5998–6008.

[48]

D.-A. Clevert, T. Unterthiner, and S. Hochreiter, “Fast and accurate deep network learning by exponential linear units (ELUs),” 2015, arXiv:1511.07289. [Online]. Available: http://arxiv.org/abs/1511.07289

[49]

(2016). PeMS, Caltrans Performance Measurement System. [Online]. Available: http://pems.dot.ca.gov/

[50]

J. Bergstra, B. Komer, C. Eliasmith, D. Yamins, and D. D. Cox, “Hyperopt: A Python library for model selection and hyperparameter optimization,” Comput. Sci. Discovery, vol. 8, no. 1, Jul. 2015, Art. no.

[51]

I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to sequence learning with neural networks,” in Proc. Adv. Neural Inf. Progression Syst., 2014, pp. 3104–3112.

Cited By

Seo DSon JKim NShin WKim SSerra ESpezzano F(2024)Empowering Traffic Speed Prediction with Auxiliary Feature-Aided Dependency LearningProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679909(4031-4035)Online publication date: 21-Oct-2024
https://dl.acm.org/doi/10.1145/3627673.3679909
Angkan PBehinaein BMahmud ZBhatti ARodenburg DHungler PEtemad A(2024)Multimodal Brain–Computer Interface for In-Vehicle Driver Cognitive Load Measurement: Dataset and BaselinesIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2023.334584625:6(5949-5964)Online publication date: 5-Jan-2024
https://dl.acm.org/doi/10.1109/TITS.2023.3345846
Du WChen SLi ZCao XLv Y(2024)A Spatial-Temporal Approach for Multi-Airport Traffic Flow Prediction Through Causality GraphsIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2023.330890325:1(532-544)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TITS.2023.3308903
Show More Cited By

Index Terms

A Multi-Stream Feature Fusion Approach for Traffic Prediction
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
    2. Machine learning approaches
      1. Neural networks
2. Information systems
  1. Information systems applications
    1. Data mining

Index terms have been assigned to the content through auto-classification.

Recommendations

Deep Feature Fusion over Multi-field Categorical Data for Rating Prediction
AICCC '18: Proceedings of the 2018 Artificial Intelligence and Cloud Computing Conference

Many predictive tasks in recommender systems model from categorical variables. Different from continuous features extracted from images and videos, categorical data is discrete and of multi-field while their dependencies are little known, which brings ...
Multi-feature fusion deep networks

In this paper, we propose a novel deep networks, multi-feature fusion deep networks (MFFDN), based on denoising autoencoder. MFFDN significantly reduces the classification error while giving the interpretability of the hidden-layer feature ...
QoS Prediction via Multi-scale Feature Fusion Based on Convolutional Neural Network
Service-Oriented Computing
Abstract
Quality of Service (QoS) prediction is a crucial aspect in service management. However, the existing QoS prediction methods face several limitations, such as loss of information during encoding, incomplete feature extraction and neglect of the ...

Comments

Information & Contributors

Information

Published In

cover image IEEE Transactions on Intelligent Transportation Systems

IEEE Transactions on Intelligent Transportation Systems Volume 23, Issue 2

Feb. 2022

1019 pages

ISSN:1524-9050

Issue’s Table of Contents

1558-0016 © 2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

Publisher

IEEE Press

Publication History

Published: 01 February 2022

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 09 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Seo DSon JKim NShin WKim SSerra ESpezzano F(2024)Empowering Traffic Speed Prediction with Auxiliary Feature-Aided Dependency LearningProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679909(4031-4035)Online publication date: 21-Oct-2024
https://dl.acm.org/doi/10.1145/3627673.3679909
Angkan PBehinaein BMahmud ZBhatti ARodenburg DHungler PEtemad A(2024)Multimodal Brain–Computer Interface for In-Vehicle Driver Cognitive Load Measurement: Dataset and BaselinesIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2023.334584625:6(5949-5964)Online publication date: 5-Jan-2024
https://dl.acm.org/doi/10.1109/TITS.2023.3345846
Du WChen SLi ZCao XLv Y(2024)A Spatial-Temporal Approach for Multi-Airport Traffic Flow Prediction Through Causality GraphsIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2023.330890325:1(532-544)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TITS.2023.3308903
Gui HLiu JMa CLi M(2024)Industrial-oriented machine learning big data framework for temporal-spatial error prediction and control with DTSMGCN modelJournal of Intelligent Manufacturing10.1007/s10845-023-02095-335:3(1173-1196)Online publication date: 1-Mar-2024
https://dl.acm.org/doi/10.1007/s10845-023-02095-3
Zhao CWang XLv YTian YLin YWang F(2023)Parallel Transportation in TransVerse: From Foundation Models to DeCASTIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2023.331158524:12(15310-15327)Online publication date: 1-Dec-2023
https://dl.acm.org/doi/10.1109/TITS.2023.3311585
Rahmani SBaghbani ABouguila NPatterson Z(2023)Graph Neural Networks for Intelligent Transportation Systems: A SurveyIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2023.325775924:8(8846-8885)Online publication date: 1-Aug-2023
https://dl.acm.org/doi/10.1109/TITS.2023.3257759
Liu TZhang J(2023)An adaptive traffic flow prediction model based on spatiotemporal graph neural networkThe Journal of Supercomputing10.1007/s11227-023-05261-979:14(15245-15269)Online publication date: 16-Apr-2023
https://dl.acm.org/doi/10.1007/s11227-023-05261-9
He RLi LHua BTong JTan C(2023)ST-MAN: Spatio-Temporal Multimodal Attention Network for Traffic PredictionKnowledge Science, Engineering and Management10.1007/978-3-031-40286-9_12(137-152)Online publication date: 16-Aug-2023
https://dl.acm.org/doi/10.1007/978-3-031-40286-9_12
Yu J(2022)Graph Construction for Traffic Prediction: A Data-Driven ApproachIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2021.313616123:9(15015-15027)Online publication date: 1-Sep-2022
https://dl.acm.org/doi/10.1109/TITS.2021.3136161
Zhang CZhu FLv YYe PWang F(2022)MLRNN: Taxi Demand Prediction Based on Multi-Level Deep Learning and Regional Heterogeneity AnalysisIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2021.308051123:7(8412-8422)Online publication date: 1-Jul-2022
https://dl.acm.org/doi/10.1109/TITS.2021.3080511
Show More Cited By

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents