Abstract
Large-scale traffic data mining provides a new solution to alleviate traffic congestion and improves traffic service. As an important part of traffic data analysis, traffic multi-feature prediction is widely concerned, and several machine learning algorithms are also applied in this field. However, this is very challenging, because each traffic feature has a highly nonlinear and complex pattern, and there are great differences between multiple features. A large number of the existing traffic feature prediction methods focus on extracting a single traffic feature and lack the ability of analyzing multiple features. This paper proposes a new multi-feature based attention graph convolutional network (MFAGCN) to solve the problem of the prediction of multiple features in traffic, the proposed method has 4.53% improved to the conventional methods. The three features predicted by MFAGCN are traffic flow, occupancy rate, and vehicle speed. Each feature is modeled with three temporal attributes, namely weekly period, daily period, and nearest period. In this paper, multi-feature prediction mainly includes two parts: (1) Establish a spatiotemporal attention mechanism for capturing the dynamic spatiotemporal correlation of multiple features. (2) Different convolutional kernels and activation functions are used for each feature after splitting. The experimental results on real traffic datasets have verified the effectiveness of the MFAGCN .
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shengnan, G., Youfang, L., Ning, F., Chao, S., Huaiyu, W.: Attention based spatial-temporal graph convolutional networks for traffic flow prediction. AAAI Conf. Artif. Intell. 33(1), 922–929 (2019)
Bing, Y., Haoteng, Y., Zhanxing, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic prediction. In: International Joint Conferences on Artificial Intelligence Organization, pp. 3634–3640 (2017)
Ling, Z., et al.: T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21(9), 3848–3858 (2019)
Huaxiu, Y., Xianfeng, T., Hua, W., Guanjie, Z., Zhenhui, L.: Revisiting spatial-temporal similarity: a deep learning framework for traffic prediction. AAAI Conf. Artif. Intell. 33(1), 5668–5675 (2019)
Chuanpan, Z., Xiaoliang, F., Cheng, W., Jianzhong, Q.: GMAN: a graph multi-attention network for traffic prediction. AAAI Conf. Artif. Intell. 34(1), 1234–1241 (2020)
Yaguang, L., Rose, Y., Cyrus, S., Yan, L.: Diffusion convolutional recurrent neural network: data-driven traffic prediction, pp. 1–16 (2018)
Jiabin, Q., Xinyu, G., Lin, Z.: Improved UGRNN for short-term traffic flow prediction with multi-feature sequence inputs. In: 2018 International Conference on Information Networking (ICOIN), Chiang Mai, pp. 13–17 (2018)
Di, Y., Songjiang, L., Zhou, P., Peng, W., Junhui, W., Huamin, Y.: MF-CNN: traffic flow prediction using convolutional neural network and multi-features fusion. IEICE Trans. Inf. Syst. 102(8), 1526–1536 (2019)
Lin, Y., Wang, R., Zhu, R., Li, T., Wang, Z., Chen, M.: The short-term exit traffic prediction of a toll station based on LSTM. In: Li, G., Shen, H.T., Yuan, Ye., Wang, X., Liu, H., Zhao, X. (eds.) KSEM 2020. LNCS (LNAI), vol. 12275, pp. 462–471. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-55393-7_41
Eunjoon, C., Seth, A.M., Jure, L.: Friendship and mobility: user movement in location-based social networks. In: 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2004), San Diego, pp. 1082–1090 (2011)
Zheng, Z., Weihai, C., Xingming, W., Peter, C.Y.C., Jingmeng, L.: LSTM network: a deep learning approach for short-term traffic prediction. IET Digit. Libr. 11(2), 68–75 (2017)
Qing, G., Zhu, S., Jie, Z., Yinleng, T.: An attentional recurrent neural network for personalized next location recommendation. In: AAAI Conference on Artificial Intelligence, New York, vol. 34, pp. 83–90 (2020)
Michaël, D., Xavier, B., Pierre, V.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Neural Information Processing Systems, pp. 1–9 (2016)
Hussein, D.: An object-oriented neural network approach to short-term traffic prediction. Eur. J. Oper. Res. 131(2), 253–261 (2001)
Paulo, C., Miguel, R., Miguel, R., Pedro, S.: Multi-scale Internet traffic prediction using neural networks and time series methods. Expert. Syst. 29(2), 143–155 (2010)
Alireza, E., David, L.: Spatiotemporal traffic prediction: review and proposed directions. Transp. Rev. 38(6), 786–814 (2017)
Yuxuan, L., Songyu, K., Junbo, Z., Xiuwen, Y., Yu, Z.: GeoMAN: multi-level attention networks for geo-sensory time series prediction. In: International Joint Conferences on Artificial Intelligence Organization, pp. 3428–3434 (2018)
Filmon, G.H., Mecit, C.: Short-term traffic flow rate prediction based on identifying similar traffic patterns. Transp. Res. Part C Emerg. Technol. 66, 61–78 (2016)
AbuShaaban, M., Brazil, T.J., Scanlan, J.O.: Recursive causal convolution [passive distributed circuits]. In: IEEE MTT-S International Microwave Symposium Digest, Denver, pp. 8–13 (1997)
Sepp, H., Jürgen, S.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Zhao, A., Li, J., Ahmed, M.: SpiderNet: a spiderweb graph neural network for multi-view gait recognition. Knowl. Based Syst. 206, 106273 (2020)
Shifen, C., Feng, L., Peng, P., Sheng, W.: Short-term traffic prediction: an adaptive ST-KNN model that considers spatial heterogeneity. Comput. Environ. Urban Syst. 71, 186–198 (2018)
Weiqi, C., Ling, C., Yu, X., Wei, C., Yusong, G., Xiaojie, F.: Multi-range attentive bicomponent graph convolutional network for traffic prediction. In: AAAI Conference on Artificial Intelligence, New York, pp. 3529–3536 (2020)
Yang, Y.: Spatiotemporal traffic-flow dependency and short-term traffic prediction. Environ. Plan. B Urban Anal. City Sci. 35(5), 762–771 (2008)
Bin, S., Wei, C., Prashant, G., Guohua, B.: Short-term traffic prediction using self-adjusting k-nearest neighbours. IET Digit. Libr. 12(1), 41–48 (2018)
Zhao, A., Li, J., Dong, J.: Multimodal gait recognition for neurodegenerative diseases, pp. 1–15 (2021)
Michael, G., Konrad, D., Ulrich, B., André, G., Bernhard, S.: Pedestrian's trajectory prediction in public traffic with artificial neural networks. In: 22nd International Conference on Pattern Recognition, Stockholm, pp. 4110–4115 (2014)
Huakang, L., Dongmin, H., Youyi, S., Dazhi, J., Teng, Z., Jing, Q.: ST-TrafficNet: a spatial-temporal deep learning network for traffic prediction. Electronics 9(9), 1–17 (2020)
Weiwei, J., Lin, Z.: Geospatial data to images: a deep-learning framework for traffic prediction. TUP 24(1), 52–64 (2018)
Haider, K.J., Rafiqul, Z.K.: Methods to avoid over-fitting and under-fitting in supervised machine learning (comparative study). In: Communication and Instrumentation Devices, Aligarh, pp. 163–172 (2015)
Zulong, D., Xin, W., Dafang, Z., Yingru, L., Kun, X., Shaoyao, H.: Dynamic spatial-temporal graph convolutional neural networks for traffic prediction. In: AAAI Conference on Artificial Intelligence, California, pp. 890–897 (2019)
Toon, B., Antonio, D.M., Juan, S.A., Enrique, O., Peter, H.: A graph CNN-LSTM neural network for short and long-term traffic prediction based on trajectory data. Transp. Res. Part C Emerg. Technol. 112, 62–77 (2020)
Zhao, A., Dong, J., Li. J.: Associated spatio-temporal capsule network for gait recognition, pp. 1–14 (2021)
Jiawei, Z., Yujiao, S., Ling, Z., Haifeng, L.: A3T-GCN: attention temporal graph convolutional network for traffic prediction, pp. 1–9 (2020)
Leung, F.H.F., Lam, H.K., Ling, S.H., Tam, P.K.S.: Tuning of the structure and parameters of a neural network using an improved genetic algorithm. IEEE Trans. Neural Netw. 14(1), 79–88 (2003)
Florin, S., Xuan, V.N., James, B., Chris, L., Hai, V., Rao, K.: Traffic prediction in complex urban networks: Leveraging big data and machine learning. In: 2015 IEEE International Conference on Big Data, Santa Clara, pp. 1019–1024 (2015)
Chenhan, Z., James, J.Q.Y., Yi, L.: Spatial-temporal graph attention networks: a deep learning approach for traffic prediction. Artifi. Intell. (AI)-Empowered Intell. Transp. Syst. 7, 166246–166256 (2019)
Zhiqiang, L., Jianbo, L., Chuanhao, D., Wei, Z.: A deep spatial-temporal network for vehicle trajectory prediction. In: International Conference on Wireless Algorithms, Systems, and Applications, Qingdao, pp. 359–369 (2020)
Acknowledgments
This research was supported in part by Shandong Province colleges and universities youth innovation technology plan innovation team project under Grant No. 2020KJN011, Shandong Provincial Natural Science Foundation under Grant No. ZR2020MF060, Program for Innovative Postdoctoral Talents in Shandong Province under Grant No. 40618030001, National Natural Science Foundation of China under Grant No. 61802216, and Postdoctoral Science Foundation of China under Grant No.2018M642613.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, H., Li, J., Lv, Z., Xu, Z. (2021). MFAGCN: Multi-Feature Based Attention Graph Convolutional Network for Traffic Prediction. In: Liu, Z., Wu, F., Das, S.K. (eds) Wireless Algorithms, Systems, and Applications. WASA 2021. Lecture Notes in Computer Science(), vol 12937. Springer, Cham. https://doi.org/10.1007/978-3-030-85928-2_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-85928-2_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85927-5
Online ISBN: 978-3-030-85928-2
eBook Packages: Computer ScienceComputer Science (R0)