基于特征蒸馏的变分编码器交通流预测模型

欧阳毅; 汤文燕; 黎晏伶

doi:10.12263/DZXB.20230230

您当前的位置：

首页 >

文章列表页 >

基于特征蒸馏的变分编码器交通流预测模型

学术论文 | 更新时间：2025-12-11

- 基于特征蒸馏的变分编码器交通流预测模型
- Traffic Flow Prediction Model Based on Spatio-Temporal Feature Distillation Variational Autoencoder
- 电子学报 2024年52卷第6期页码：1938-1944
- 作者机构：
  
  浙江工商大学管理科学与电子商务学院，浙江杭州 310000
- 作者简介：
  
  [ "欧阳毅男，1975年10月出生于贵州省贵阳市.现为浙江工商大学管理工程与电子商务学院副教授、硕导.2005年在浙江大学计算机科学与技术学院获工学博士学位，2018年在美国Oakland大学作访问学者，获Academic EXCELLCE奖项. 在国内外发表学术论文30余篇.E-mail: oyy@mail.zjgsu.edu.cn" ]
  [ "汤文燕女，1998年7月13日出生于江苏省泰州市兴化市.浙江工商大学管理科学与电子商务学院硕士研究生.研究方向为智慧物流与智能决策.E-mail: twy15298547169@163.com" ]
- 基金信息：
  
  浙江工商大学“数字+学科建设项目”(SZJ2022C004);浙江工商大学2023年度省级及以上教学平台自主设立校级教学项目(1310XJ0521036)
- DOI：10.12263/DZXB.20230230
  中图分类号： TN911.7;U491.1
- 收稿：2023-03-10，
  
  修回：2023-12-06，
  
  纸质出版：2024-06-25
- 稿件说明：
移动端阅览
欧阳毅,汤文燕,黎晏伶.基于特征蒸馏的变分编码器交通流预测模型[J].电子学报,2024,52(06):1938-1944.

OUYANG Yi, TANG Wen-yan, LI Yan-ling.Traffic Flow Prediction Model Based on Spatio-Temporal Feature Distillation Variational Autoencoder[J].Acta Electronica Sinica, 2024, 52(06): 1938-1944.
欧阳毅,汤文燕,黎晏伶.基于特征蒸馏的变分编码器交通流预测模型[J].电子学报,2024,52(06):1938-1944. DOI：10.12263/DZXB.20230230

OUYANG Yi, TANG Wen-yan, LI Yan-ling.Traffic Flow Prediction Model Based on Spatio-Temporal Feature Distillation Variational Autoencoder[J].Acta Electronica Sinica, 2024, 52(06): 1938-1944. DOI：10.12263/DZXB.20230230

摘要

针对交通流数据高维非线性和时空依赖性复杂，本文构建了基于特征蒸馏的变分贝叶斯编码器交通流预测模型.对每段时间序列对应的时间窗口特征，构建了基于多模态时间槽和空间槽的交通流特征提取模型.以时空槽特征提取模型作为特征知识蒸馏架构的输入.通过知识蒸馏结构提取的时空特征结晶体，利用教师模型指导学生模型的学习过程，从而提高学生模型的泛化能力.变分贝叶斯编码器对交通流时空特征结晶编码获取交通流数据的隐变量，根据隐变量的生成采样，利用解码器将其解码重构成新的预测值.实验结果表明，本文提出的模型预测性能显著提升，且中长期预测中鲁棒性更优.

Abstract

To improve the accuracy of traffic flow prediction and to solve the problems of high-dimensional nonlinearity and spatio-temporal dependence of traffic flow

a combined feature distillation and variational Bayes encoders traffic flow forecasting model (ST-DVBE) is proposed. First

to extract the time window characteristics corresponding to each time series

the multi-modal time slots and spatial slots are constructed. Second

with spatio-temporal slot feature extraction model as the input of feature knowledge distillation architecture

and space-time feature crystallization extracted by knowledge distillation structure

the learning process of student model is guided by teacher model

so as to improve the generalization ability of student model. Finally

the variational Bayesian encoder is employed to capture the latent variables of traffic flow data by encoding the crystallization of spatiotemporal features. Utilizing the generated latent variables

the decoder reconstructs them into new predicted values. Experimental results demonstrate a significant enhancement in predictive performance with the proposed model

especially with better robustness in mid- and long-term forecasting.

关键词

Keywords

references

马君 , 刘小冬 , 孟颖 . 基于神经网络的城市交通流预测研究‍ [J ] . 电子学报 , 2009 , 37 ( 5 ): 1092 - 1094 .

MA J , LIU X D , MENG Y . Research of urban traffic flow forecasting based on neural network [J ] . Acta Electronica Sinica , 2009 , 37 ( 5 ): 1092 - 1094 . (in Chinese)

MAKRIDAKIS S , HIBON M . ARMA models and the box-Jenkins methodology [J ] . Journal of Forecasting , 1997 , 16 ( 3 ): 147 - 163 .

MIRCHANDANI P , HEAD L . A real-time traffic signal control system: Architecture, algorithms, and analysis [J ] . Transportation Research Part C: Emerging Technologies , 2001 , 9 ( 6 ): 415 - 432 .

LESHEM G , RITOV Y . Traffic flow prediction using adaboost algorithm with random forests as a weak learner [J ] . International Journal of Mathematical, Computational, Physical, Electrical and Computer Engineering , 2007 , 1 ( 1 ): 1 - 6 .

TANG J , CHEN X , HU Z , et al . Traffic flow prediction based on combination of support vector machine and data denoising schemes [J ] . Physica A: Statistical Mechanics and Its Applications , 2019 , 534 : 120642 .

金苍宏 , 董腾然 , 陈天翼 , 等 . 融合序列分解与时空卷积的时序预测算法 [J ] . 电子学报 , 2021 , 49 ( 2 ): 233 - 238 .

JIN C H , DONG T R , CHEN T Y , et al . Spatio-temporal convolutional forecasting based on time-series decomposition strategy [J ] . Acta Electronica Sinica , 2021 , 49 ( 2 ): 233 - 238 . (in Chinese)

徐兴荣 , 刘聪 , 李婷 , 等 . 基于双向准循环神经网络和注意力机制的业务流程剩余时间预测方法 [J ] . 电子学报 , 2022 , 50 ( 8 ): 1975 - 1984 .

XU X R , LIU C , LI T , et al . Business process remaining time prediction: An approach based on bidirectional quasi recurrent neural network with attention [J ] . Acta Electronica Sinica , 2022 , 50 ( 8 ): 1975 - 1984 . (in Chinese)

LU H , GE Z , SONG Y , et al . A temporal-aware LSTM enhanced by loss-switch mechanism for traffic flow forecasting [J ] . Neurocomputing , 2021 , 427 : 169 - 178 .

HUSSAIN B , AFZAL M K , AHMAD S , et al . Intelligent traffic flow prediction using optimized GRU model [J ] . IEEE Access , 2021 , 9 : 100736 - 100746 .

HINTON G , VINYALS O , DEAN J . Distilling the knowledge in a neural network [EB/OL ] . [2023 ] . http://arxiv.org/abs/1503.02531.pdf http://arxiv.org/abs/1503.02531.pdf .

钱亚冠 , 马骏 , 何念念 , 等 . 面向边缘智能的两阶段对抗知识迁移方法 [J ] . 软件学报 , 2022 , 33 ( 12 ): 4504 - 4516 .

QIAN Y G , MA J , HE N N , et al . Two-stage adversarial knowledge transfer method for edge intelligence [J ] . Journal of Software , 2022 , 33 ( 12 ): 4504 - 4516 . (in Chinese)

LIU Y , ZHANG W , WANG J . Adaptive multi-teacher multi-level knowledge distillation [J ] . Neurocomputing , 2020 , 415 : 106 - 113 .

DAI W , HOU L , SHANG L , et al . Enabling multimodal generation on CLIP via vision-language knowledge distillation [C ] // Findings of the Association for Computational Linguistics: ACL 2022 . Stroudsburg : ACL , 2022 : 2383 - 2395 .

HUANG Y , HAO Y , XU J , et al . Compressing speaker extraction model with ultra-low precision quantization and knowledge distillation [J ] . Neural Networks , 2022 , 154 : 13 - 21 .

KINGMA D P , WELLING M . Auto-encoding variational Bayes [C ] // International Conference on Learning Representations (ICLR2014) . Canada : ICLR . 2014 : 1 - 14 .

YU B , YIN H , ZHU Z . Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting [C ] // Proceedings of the 27th International Joint Conference on Artificial Intelligence . New York : ACM , 2018 : 3634 - 3640 .

LI Y , YU R , SHAHABI C , et al . Diffusion convolutional recurrent neural network: Data-driven traffic forecasting ‍ [EB/OL ] . [2023 ] . http://arxiv.org/abs/1707.01926.pdf http://arxiv.org/abs/1707.01926.pdf .

ZHENG C , FAN X , WANG C , et al . GMAN: A graph multi-attention network for traffic prediction [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 1 ): 1234 - 1241 .

YOO B , LEE J , JU J , et al . Conditional temporal neural processes with covariance loss [C ] // International Conference on Machine Learning . PMLR , 2021 : 12051 - 12061 .

XU M , DAI W , LIU C , et al . Spatial-temporal transformer networks for traffic flow forecasting [EB/OL ] . [2023 ] . http://arxiv.org/abs/2001.02908.pdf http://arxiv.org/abs/2001.02908.pdf .

LI Z , LI W , HWANG K . Adaptive graph convolution networks for traffic flow forecasting [EB/OL ] . [2023 ] . http://arxiv.org/abs/2307.05517.pdf http://arxiv.org/abs/2307.05517.pdf .

FENG A , TASSIULAS L . Adaptive graph spatial-temporal transformer network for traffic flow forecasting [EB/OL ] . [2023 ] . http://arxiv.org/abs/2207.05064.pdf http://arxiv.org/abs/2207.05064.pdf .

WILLIAMS B M , DURVASULA P K , BROWN D E . Urban freeway traffic flow prediction: Application of seasonal autoregressive integrated moving average and exponential smoothing models [J ] . Transportation Research Record , 1998 , 1644 ( 1 ): 132 - 141 .

LIU B , TANG X , et al . Traffic flow combination forecasting method based on improved LSTM and ARIMA [J ] . International Journal of Embedded Systems , 2020 , 12 ( 1 ): 22 - 30 .

BAI L , YAO L , KANHERE S , et al . Stg2seq: Spatial-temporal graph to sequence model for multi-step passenger demand forecasting [C ] // Proceedings of the 28th International Joint Conference on Artificial Intelligence . New York : ACM , 2019 : 1981 - 1987 .

BAI L , YAO L , LI C , et al . Adaptive graph convolutional recurrent network for traffic forecasting [J ] . Advances in Neural Information Processing Systems , 2020 , 33 ( 1 ): 17804 - 17815 .

WU Z , PAN S , LONG G , et al . Graph wavenet for deep spatial-temporal graph modeling [C ] // Proceedings of the 28th International Joint Conference on Artificial Intelligence . New York : ACM , 2019 : 1907 - 1913 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于物理可解释自编码模型的雷达目标方位稳健识别算法

基于条件变分推断与内省对抗学习的多样化图像描述生成

基于变分贝叶斯的分布式融合目标跟踪

MU-MIMO-OFDM上行频偏与信道联合跟踪

有限贝塔刘维尔混合模型的变分学习及其应用