Spatiotemporal Forecasting of Traffic Flow Using Wavelet-Based Temporal Attention

被引:0
作者
Jakhmola, Yash [1 ]
Panja, Madhurima [2 ,4 ]
Mishra, Nitish Kumar [1 ]
Ghosh, Kripabandhu [3 ]
Kumar, Uttam [2 ]
Chakraborty, Tanujit [4 ,5 ]
机构
[1] Indian Inst Sci Educ & Res, Dept Math & Stat, Kolkata 741246, India
[2] Int Inst Informat Technol, Ctr Data Sci, Bengaluru 560100, India
[3] Indian Inst Sci Educ & Res, Dept Computat & Data Sci, Kolkata 741246, India
[4] Sorbonne Univ Abu Dhabi, SAFIR, Abu Dhabi, U Arab Emirates
[5] Sorbonne Univ, Sorbonne Ctr Artificial Intelligence, F-75006 Paris, France
来源
IEEE ACCESS | 2024年 / 12卷
关键词
Forecasting; Spatiotemporal phenomena; Predictive models; Data models; Time series analysis; Correlation; Urban areas; Roads; Proposals; Deep learning; Traffic forecasting; wavelet transformation; temporal attention; spatiotemporal data; computational complexity; PREDICTION; DEEP; TRANSFORM; NETWORKS; SVR;
D O I
10.1109/ACCESS.2024.3516195
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Spatiotemporal forecasting of traffic flow data represents a typical problem for urban traffic management, involving complex interactions, nonlinearities, and long-range dependencies due to the interwoven nature of the temporal and spatial dimensions. Traditional statistical and machine learning methods struggle to handle both temporal and spatial dependencies in such datasets. While graph convolutional networks and multi-head attention mechanisms have been widely adopted in this field, they often fail to accurately model dynamic temporal patterns and effectively differentiate noise from signals in traffic datasets, leading to potential overfitting. This paper proposes a wavelet-based temporal attention model, namely a wavelet dynamic spatiotemporal aware graph neural network (W-DSTAGNN), for tackling the traffic forecasting problem. A key feature of W-DSTAGNN is the use of wavelets that can effectively separate noise and capture multi-resolution temporal patterns. Wavelet decomposition can help by decomposing the signal into components that can be analyzed independently, reducing the impact of non-stationarity and handling long-range dependencies of traffic flow datasets. These enable our proposal to generate more robust and accurate forecasts of complex and dynamic traffic dependencies than commonly used spatiotemporal deep learning models. Benchmark experiments using three popularly used statistical metrics confirm that our proposal efficiently captures spatiotemporal correlations and outperforms eleven state-of-the-art models (including both temporal and spatiotemporal benchmarks) on three publicly available traffic datasets. Our proposed approach can better handle dynamic temporal and spatial dependencies, delivering reliable long-term forecasts, and generating interval forecasts to enhance probabilistic forecasting of traffic datasets.
引用
收藏
页码:188797 / 188812
页数:16
相关论文
共 70 条
[51]  
Liu T., Wei H., Zhang C., Zhang K., Time series forecasting based on wavelet decomposition and feature extraction, Neural Comput. Appl., 28, S1, pp. 183-195, (2017)
[52]  
Panja M., Chakraborty T., Nadim S.S., Ghosh I., Kumar U., Liu N., An ensemble neural network approach to forecast dengue outbreak based on climatic condition, Chaos, Solitons Fractals, 167, (2023)
[53]  
Sengupta S., Chakraborty T., Singh S.K., Forecasting CPI inflation under economic policy and geopolitical uncertainties, Int. J. Forecasting, pp. 1-29, (2024)
[54]  
Borah J., Chakraborty T., Nadzir M.S.M., Cayetano M.G., Majumdar S., WaveCatBoost for probabilistic forecasting of regional air quality data, (2024)
[55]  
Grinsted A., Moore J.C., Jevrejeva S., Application of the cross wavelet transform and wavelet coherence to geophysical time series, Nonlinear Processes Geophys., 11, 5-6, pp. 561-566, (2004)
[56]  
Jiang X., Adeli H., Dynamic wavelet neural network model for traffic flow forecasting, J. Transp. Eng., 131, 10, pp. 771-779, (2005)
[57]  
Xie Y., Zhang Y., Ye Z., Short-term traffic volume forecasting using Kalman filter with discrete wavelet decomposition, Comput.-Aided Civil Infrastruct. Eng., 22, 5, pp. 326-334, (2007)
[58]  
Xiao H., Sun H., Ran B., Oh Y., Fuzzy-neural network traffic prediction framework with wavelet decomposition, Transp. Res. Rec., J. Transp. Res. Board, 1836, 1, pp. 16-20, (2003)
[59]  
Sun Y., Leng B., Guan W., A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system, Neurocomputing, 166, pp. 109-121, (2015)
[60]  
Zhang N., Guan X., Cao J., Wang X., Wu H., Wavelet-HST: A wavelet-based higher-order spatio-temporal framework for urban traffic speed prediction, IEEE Access, 7, pp. 118446-118458, (2019)