College of Electrical Engineering, Xinjiang University, Ürümqi, China.
PLoS One. 2024 Jul 15;19(7):e0306892. doi: 10.1371/journal.pone.0306892. eCollection 2024.
Accurately predicting traffic flow is crucial for optimizing traffic conditions, reducing congestion, and improving travel efficiency. To explore spatiotemporal characteristics of traffic flow in depth, this study proposes the MFSTBiSGAT model. The MFSTBiSGAT model leverages graph attention networks to extract dynamic spatial features from complex road networks, and utilizes bidirectional long short-term memory networks to capture temporal correlations from both past and future time perspectives. Additionally, spatial and temporal information enhancement layers are employed to comprehensively capture traffic flow patterns. The model aims to directly extract original temporal features from traffic flow data, and utilizes the Spearman function to extract hidden spatial matrices of road networks for deeper insights into spatiotemporal characteristics. Historical traffic speed and lane occupancy data are integrated into the prediction model to reduce forecasting errors and enhance robustness. Experimental results on two real-world traffic datasets demonstrate that MFSTBiSGAT successfully extracts and captures spatiotemporal correlations in traffic networks, significantly improving prediction accuracy.
准确预测交通流量对于优化交通状况、减少拥堵和提高出行效率至关重要。为了深入探索交通流量的时空特征，本研究提出了 MFSTBiSGAT 模型。该模型利用图注意力网络从复杂的道路网络中提取动态空间特征，并利用双向长短期记忆网络从过去和未来的时间角度捕捉时间相关性。此外，还采用了空间和时间信息增强层来全面捕捉交通流模式。该模型旨在直接从交通流量数据中提取原始时间特征，并利用 Spearman 函数提取路网的隐藏空间矩阵，以更深入地了解时空特征。历史交通速度和车道占有率数据被整合到预测模型中，以减少预测误差并提高鲁棒性。在两个真实交通数据集上的实验结果表明，MFSTBiSGAT 成功地提取和捕捉了交通网络中的时空相关性，显著提高了预测精度。
