[1]孙加新,惠 飞,张凯望,等.基于 CNN-BiLSTM-AM 模型的交通流量预测[J].计算机技术与发展,2023,33(02):32-37.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 005]
　SUN Jia-xin,HUI Fei,ZHANG Kai-wang,et al.Traffic Volume Prediction Based on CNN-BiLSTM-AM Model[J].,2023,33(02):32-37.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 005]
点击复制

基于 CNN-BiLSTM-AM 模型的交通流量预测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年02期
页码:
32-37
栏目:
大数据与云计算
出版日期:
2023-02-10

文章信息/Info

Title:
Traffic Volume Prediction Based on CNN-BiLSTM-AM Model
文章编号:
1673-629X(2023)02-0032-06
作者:
孙加新; 惠 飞; 张凯望; 冯 耀; 张师源
长安大学 信息工程学院,陕西 西安 710064
Author(s):
SUN Jia-xin; HUI Fei; ZHANG Kai-wang; FENG Yao; ZHANG Shi-yuan
School of Information Engineering,Chang’an University,Xi’an 710064,China
关键词:
交通流量; 深度学习; 卷积神经网络; 双向长短时记忆网络; 注意力机制
Keywords:
traffic volume; deep learning; convolutional neural network; bidirectional long short-term memory network; attention mechanism
分类号:
TP183
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 02. 005
摘要:
交通流量的准确预测可以为交通管理部门及个人提供更加可靠的宏观道路状况信息,为城市建设、道路规划、交通管制等问题的研究提供重要的参考。 针对现有模型存在的预测准确度不理想、对特征感知能力不强等问题,结合卷积神经网络( CNN) 的特征提取能力,双向长短记忆网络( BiLSTM) 对于时序数据的连续性、周期性的挖掘能力以及注意力机制(Attention Mechanism,AM)对于关键信息的捕获能力,提出了一种融合多特征的 CNN-BiLSTM-AM 组合模型,旨在提升模型在交通流量预测准确度上的表现。 采用美国明尼苏达州 I-94 号公路每小时西行交通流量数据进行预测实验,实验结果表明 CNN-BiLSTM-AM 模型具备准确预测交通流量的能力,与其他基准网络模型相比,各项误差指标均有明显下降,其中 MSE 降至 0. 002 64,RMSE 降至 0. 051 35,MAE 降至 0. 023 72,判定系数 R2 达到 0. 970 01,模型预测结果与真实值拟合度较高。 整体模型具有准确度高、稳定性好等优势。
Abstract:
Exact prediction of traffic volume enable traffic operation units and individuals to better understand roadway conditions from amacro perspective,and support important reference for the study of city construction,road planning and traffic control. Considering theproblems of unsatisfactory prediction accuracy and weak feature perception ability of existing models, with the features extractioncapabilities of CNN,the BiLSTM`s ability to mine periodically for time series and the critical information capturing ability of attentionmechanism,a CNN-BiLSTM-AM fusion model has been proposed to improve the accuracy of prediction. Hourly westbound traffic dataon Highway I-94 in Minnesota,USA,was used for predictive experiments. The experiment shows that the CNN-BiLSTM-AM modelhas the ability to accurately predict traffic volume. Compared with other network models, all evaluation indicators have significantlyreduced. MSE dropped to 0. 002 64, RMSE dropped to 0. 051 35, MAE dropped to 0. 023 72, and the coefficient of determinationreached 0. 970 01,which are well fitted to the true values. This model has better performance in terms of accuracy and stability.

相似文献/References:

[1]任环 蒋国平 胡海宏.考虑交通流量的SIR-CA病毒传播模型[J].计算机技术与发展,2011,(08):250.
　REN Huan,JIANG Guo-ping,HU Hai-hong.A SIR-CA Model for Epidemic Propagation Considering Traffic Flow[J].,2011,(02):250.
[2]黄向党,金志扬,羊秋玲.交通灯动态配时策略研究[J].计算机技术与发展,2013,(10):224.
　HUANG Xiang-dang[],JIN Zhi-yang[],YANG Qiu-ling[].Research on Traffic Light Dynamic Timing Plan[J].,2013,(02):224.
[3]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(02):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[4]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(02):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[5]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(02):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[6]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(02):19.
[7]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(02):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[8]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(02):1.
[9]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(02):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[10]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(02):1.

更新日期/Last Update: 2023-02-10