基于深度残差长短记忆网络交通流量预测算法

doi:10.11772/j.issn.1001-9081.2020121928

计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1566-1572.DOI: 10.11772/j.issn.1001-9081.2020121928

所属专题： 2020年全国开放式分布与并行计算学术年会（DPCS 2020）

• 2020年全国开放式分布与并行计算学术年会（DPCS 2020） • 上一篇下一篇

基于深度残差长短记忆网络交通流量预测算法

刘世泽¹, 秦艳君², 王晨星², 苏琳³, 柯其学², 罗海勇⁴, 孙艺³, 王宝会¹

1. 北京航空航天大学软件学院, 北京 100191;
2. 北京邮电大学计算机学院, 北京 100876;
3. 首都师范大学信息工程学院, 北京 100048;
4. 中国科学院计算技术研究所, 北京 100190

收稿日期:2020-11-04 修回日期:2021-04-02 出版日期:2021-06-10 发布日期:2021-06-21
通讯作者: 刘世泽
作者简介:刘世泽(1988-),男,辽宁抚顺人,硕士,主要研究方向:大数据挖掘、智能感知;秦艳君(1991-),女,山西长治人,博士研究生,CCF会员,主要研究方向:城市计算、交通模式识别;王晨星(1997-),男,河北衡水人,硕士研究生,主要研究方向:城市计算、交通模式识别、交通流预测;苏琳(2000-),女,天津人,CCF会员,主要研究方向:城市计算、交通模式识别;柯其学(1997-),男,湖北鄂州人,硕士研究生,主要研究方向:城市计算、交通模式识别;罗海勇(1967-),男,湖北麻城人,副研究员,博士,CCF会员,主要研究方向:移动智能、普适计算;孙艺(1988-),男,山东菏泽人,高级工程师,硕士,主要研究方向:数据分析、人工智能、数据通信;王宝会(1973-),男,江苏滨海人,教授级高级工程师,硕士,主要研究方向:软件工程。
基金资助:
国家自然基金资助项目（61872046）；北京邮电大学提升科技创新能力行动计划项目（2019XD-A06）。

Traffic flow prediction algorithm based on deep residual long short-term memory network

LIU Shize¹, QIN Yanjun², WANG Chenxing², SU Lin³, KE Qixue², LUO Haiyong⁴, SUN Yi³, WANG Baohui¹

1. College of Software, Beihang University, Beijing 100191, China;
2. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China;
3. College of Information Engineering, Capital Normal University, Beijing 100048, China;
4. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China

Received:2020-11-04 Revised:2021-04-02 Online:2021-06-10 Published:2021-06-21
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61872046), the Scientific and Technological Innovation Ability Improvement Action Program of Beijing University of Posts and Telecommunications (2019XD-A06).

摘要/Abstract

摘要： 针对多步交通流量预测任务中时间空间特征提取效果不佳和预测未来时间交通流量精度低的问题，提出一种基于长短时记忆（LSTM）网络、卷积残差网络和注意力机制的融合模型。首先，利用一种基于编解码器的架构，通过在编解码器中加入LSTM网络来挖掘不同尺度的时间域特征；其次，构建基于注意力机制挤压激励（SE）模块的卷积残差网络嵌入到LSTM网络结构中，从而挖掘交通流量数据中的空间域特征；最后，将编码器中获得的隐状态下的信息输入到解码器中，实现高精度多步交通流量的预测。基于真实交通数据进行实验测试和分析，实验结果表明，相较于原始的基于图卷积的模型，所提模型在北京和纽约两个交通流量公开数据集上的均方根误差（RMSE）分别获得了1.622和0.08的下降。所提模型能够高效且精确地对交通流量作出预测。

关键词: 时空数据挖掘, 编解码器, 长短期记忆, 挤压-激励模块, 空间注意力

Abstract: In the multi-step traffic flow prediction task, the spatial-temporal feature extraction effect is not good and the prediction accuracy of future traffic flow is low. In order to solve these problems, a fusion model combining Long-Short Term Memory (LSTM) network, convolutional residual network and attention mechanism was proposed. Firstly, an encoder-decoder-based architecture was used to mine the temporal domain features of different scales by adding LSTM network into the encoder-decoder. Secondly, a convolutional residual network based on the Squeeze-and-Excitation (SE) block of attention mechanism was constructed and embedded into the LSTM network structure to mine the spatial domain features of traffic flow data. Finally, the implicit state information obtained from the encoder was input into the decoder to realize the prediction of high-precision multi-step traffic flow. The real traffic data was used for the experimental testing and analysis. The results show that, compared with the original graph convolution-based model, the proposed model achieves the decrease of 1.622 and 0.08 on the Root Mean Square Error (RMSE) for Beijing and New York traffic flow public datasets, respectively. The proposed model can predict the traffic flow efficiently and accurately.

Key words: spatial-temporal data mining, encoder-decoder, Long Short-Term Memory (LSTM), Squeeze-and-Excitation (SE) block, spatial attention

中图分类号:

TP183

刘世泽, 秦艳君, 王晨星, 苏琳, 柯其学, 罗海勇, 孙艺, 王宝会. 基于深度残差长短记忆网络交通流量预测算法[J]. 计算机应用, 2021, 41(6): 1566-1572.

LIU Shize, QIN Yanjun, WANG Chenxing, SU Lin, KE Qixue, LUO Haiyong, SUN Yi, WANG Baohui. Traffic flow prediction algorithm based on deep residual long short-term memory network[J]. Journal of Computer Applications, 2021, 41(6): 1566-1572.

参考文献

[1] WILLIAS B M,HOEL L A. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process:theoretical basis and empirical results[J]. Journal of Transportation Engineering,2003, 129(6):664-672.
[2] CHAN K Y,DILLON T S,SINGH J,et al. Neural-network-based models for short-term traffic flow forecasting using a hybrid exponential smoothing and Levenberg-Marquardt algorithm[J]. IEEE Transactions on Intelligent Transportation Systems,2012,13(2):644-654.
[3] DU B,PENG H,WANG S,et al. Deep Irregular convolutional residual LSTM for urban traffic passenger flows prediction[J]. IEEE Transactions on Intelligent Transportation Systems,2020,21(3):972-985.
[4] ZHENG M,LI T,ZHU R,et al. Traffic accident's severity prediction:a deep learning approach-based CNN network[J]. IEEE Access,2019,7:39897-39910.
[5] YU H, WU Z, WANG S, et al. Spatiotemporal recurrent convolutional networks for traffic prediction in transportation networks[J]. Sensors,2017,17(7):Article No. 1501.
[6] ZANG D, WANG D, CHENG J, et al. Traffic parameters prediction using a three-channel convolutional neural network[C]//Proceedings of the 2017 International Conference on Intelligence Science,IFIPAICT 510. Cham:Springer,2017:363-371.
[7] MA X,DAI Z,HE Z,et al. Learning traffic as images:a deep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors,2017,17(4):Article No. 818.
[8] KIM Y,WANG P,MIHAYLOVA L. Structural recurrent neural network for traffic speed prediction[C]//Proceedings of the 2019 IEEE International Conference on Acoustics,Speech and Signal Processing. Piscataway:IEEE,2019:5207-5211.
[9] ZHAO J,QU H,ZHAO J,et al. Towards traffic matrix prediction with LSTM recurrent neural networks[J]. Electronics Letters, 2018,54(9):566-568.
[10] CHEN H, HUANG S, CHIANG D, et al. Improved neural machine translation with a syntax-aware encoder and decoder[C]//Proceedings of the 2017 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg:ACL,2017:1936-1945.
[11] ZHANG J,ZHENG Y,QI D,et al. DNN-based prediction model for spatio-temporal data[C]//Proceedings of the 2016 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York:ACM,2016:Article No. 92.
[12] ZHANG,J,ZHENG Y,QI D. Deep spatio-temporal residual networks for citywide crowd flows prediction[C]//Proceedings of the 201731st AAAI Conference on Artificial Intelligence. Palo Alto:AAAI Press,2017:1655-1661
[13] MA X, YU H, WANG Y, et al. Large-scale transportation network congestion evolution prediction using deep learning theory[J]. PLoS ONE,2015,10(3):No. e0119044.
[14] 贾兴无. 基于网约车数据的居民出行需求特征分析及需求预测[J]. 交通工程, 2018, 18(5):39-45.(JIA X W. Characteristics analysis and demand prediction of travel demand based on online car-hailing data[J]. Journal of Transportation Engineering, 2018,18(5):39-45.)
[15] 李会云. 基于Geotagged Photo数据集的行为识别研究与应用[D]. 沈阳:东北大学, 2015:31-39.(LI H Y. Research and application of behavior recognition based on Geotagged Photo dataset[D]. Shenyang:Northeastern University,2015:31-39.)
[16] 冯宁. 基于时空图卷积网络的高速公路流量预测方法研究[D]. 北京:北京交通大学, 2019:44-51.(FENG N. Research on highway traffic forecasting based on spatial-temporal graph convolutional network[D]. Beijing:Beijing Jiaotong University, 2019:44-51.)
[17] NIE Y,HAN Y,HUANG J,et al. Attention-based encoderdecoder model for answer selection in question answering[J]. Frontiers of Information Technology and Electronic Engineering, 2017,18(4):535-544.
[18] WANG Y,VAN DE WEIJER J,HERRANZ L. Mix and match networks:encoder-decoder alignment for zero-pair image translation[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:5467-5476.
[19] LIPPI M,BERTINI M,FRASCONI P. Short-term traffic flow forecasting:an experimental comparison of time-series analysis and supervised learning[J]. IEEE Transactions on Intelligent Transportation Systems,2013,14(2):871-882.
[20] OKUTANI I,STEPHANEDES Y J. Dynamic prediction of traffic volume through Kalman filtering theory[J]. Transportation Research Part B:Methodological,1984,18(1):1-11.
[21] VAN DER VOORT M, DOUGHERTY M, WATSON S. Combining Kohonen maps with ARIMA time series models to forecast traffic flow[J]. Transportation Research Part C:Emerging Technologies,1996,4(5):307-318.
[22] KIM E Y. MRF model based real-time traffic flow prediction with support vector regression[J]. Electronics Letters,2017,53(4):243-245.
[23] YAO H,WU F,KE J,et al. Deep multi-view spatial-temporal network for taxi demand prediction[C]//Proceedings of the 201832nd AAAI Conference on Artificial Intelligence. Palo Alto:AAAI Press,2018:2588-2595.

基于深度残差长短记忆网络交通流量预测算法

Traffic flow prediction algorithm based on deep residual long short-term memory network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[2]	党伟超, 李涛, 白尚旺, 高改梅, 刘春霞. 基于自注意力长短期记忆网络的Web软件系统实时剩余寿命预测方法[J]. 计算机应用, 2021, 41(8): 2346-2351.
[3]	武国亮, 徐继宁. 基于命名实体识别任务反馈增强的中文突发事件抽取方法[J]. 计算机应用, 2021, 41(7): 1891-1896.
[4]	谭道强, 曾诚, 乔金霞, 张俊. 基于混合注意力模型的阴影检测方法[J]. 计算机应用, 2021, 41(7): 2076-2081.
[5]	张元钧, 张曦煌. 基于图卷积与长短期记忆网络的动态网络表示学习模型[J]. 计算机应用, 2021, 41(7): 1857-1864.
[6]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.
[7]	徐萌, 王亚锟. 基于双向长短期记忆网络的DA40飞机碳刹车片剩余寿命预测[J]. 计算机应用, 2021, 41(5): 1527-1532.
[8]	李文惠, 曾上游, 王金金. 基于改进注意力机制的图像描述生成算法[J]. 计算机应用, 2021, 41(5): 1262-1267.
[9]	倪水平, 李慧芳. 基于一维卷积神经网络与长短期记忆网络结合的电池荷电状态预测方法[J]. 计算机应用, 2021, 41(5): 1514-1521.
[10]	张欣环, 刘宏杰, 施俊庆, 毛程远, 孟国连. 基于时空特征向量的长短期记忆人工神经网络的城市公交旅行时间预测[J]. 计算机应用, 2021, 41(3): 875-880.
[11]	许力, 李建华. 基于句法依存分析的图网络生物医学命名实体识别[J]. 计算机应用, 2021, 41(2): 357-362.
[12]	郭可心, 张宇翔. 基于多层次空间注意力的图文评论情感分析方法[J]. 计算机应用, 2021, 41(10): 2835-2841.
[13]	钱斌, 郑楷洪, 陈子鹏, 肖勇, 李森, 叶纯壮, 马千里. 基于残差连接长短期记忆网络的时间序列修复模型[J]. 计算机应用, 2021, 41(1): 243-248.
[14]	肖勇, 郑楷洪, 郑镇境, 钱斌, 李森, 马千里. 基于多尺度跳跃深度长短期记忆网络的短期多变量负荷预测[J]. 计算机应用, 2021, 41(1): 231-236.
[15]	张晓晗, 冯爱民. 基于经验模态分解和长短期记忆神经网络的短期交通流量预测[J]. 计算机应用, 2021, 41(1): 225-230.