Scholarlink

<p>Traffic congestion is getting increasingly severe, making accurate traffic flow prediction crucial for relieving traffic pressure. Existing methods have problems in extracting multidimensional features from time series, particularly in capturing long-range temporal dependencies, effectively mining frequency-domain characteristics (e.g., periodic patterns), and modeling complex inter-correlations among multivariate data, all of which limit prediction accuracy. Therefore, this study proposes an integrated model called DSTIT-TCN to address this issue. Firstly, efficient multi-dimensional feature extraction of time series is accomplished through the integration of Discrete Cosine Transform (DCT), Squeeze-and-Excitation Networks (SENet), and Temporal Convolutional Network (TCN). Furthermore, the optimized features are subsequently fed into an iTransformer network to capture multivariate inter-correlations. Finally, the parallel connection with TCN enhances temporal dependency modeling capabilities and synergistically improves the prediction performance. To validate the proposed model’s efficacy, we used the UK motorway dataset for evaluation. Experimental results demonstrate substantial performance gains, with our model achieving improvements across all key metrics: R² increased by 0.0101%–6.4204%, MAE reduced by 3.0671%–62.2520%, RMSE by 3.4064%–64.4270%, MAPE by 1.8294%–39.2713%, and MASE by 35.3543%-64.5922%. It also shows superior performance in other metrics and strong generalization ability. Parameter sensitivity analysis also confirmed its robustness to data selection, highlighting its engineering application potential.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DSTIT-TCN: research on traffic flow prediction method based on big data multi-scale information fusion

  • 期刊论文

  • 发表日期：

    2026年1月9日

查看全文
  • Jingjing Sun,
  • Zhiwen Wang,
  • Long Li,
  • Kangkang Yang,
  • Jingxiao Zeng,
  • Haoxu Wang,
  • Wei Miao

摘要

Traffic congestion is getting increasingly severe, making accurate traffic flow prediction crucial for relieving traffic pressure. Existing methods have problems in extracting multidimensional features from time series, particularly in capturing long-range temporal dependencies, effectively mining frequency-domain characteristics (e.g., periodic patterns), and modeling complex inter-correlations among multivariate data, all of which limit prediction accuracy. Therefore, this study proposes an integrated model called DSTIT-TCN to address this issue. Firstly, efficient multi-dimensional feature extraction of time series is accomplished through the integration of Discrete Cosine Transform (DCT), Squeeze-and-Excitation Networks (SENet), and Temporal Convolutional Network (TCN). Furthermore, the optimized features are subsequently fed into an iTransformer network to capture multivariate inter-correlations. Finally, the parallel connection with TCN enhances temporal dependency modeling capabilities and synergistically improves the prediction performance. To validate the proposed model’s efficacy, we used the UK motorway dataset for evaluation. Experimental results demonstrate substantial performance gains, with our model achieving improvements across all key metrics: R² increased by 0.0101%–6.4204%, MAE reduced by 3.0671%–62.2520%, RMSE by 3.4064%–64.4270%, MAPE by 1.8294%–39.2713%, and MASE by 35.3543%-64.5922%. It also shows superior performance in other metrics and strong generalization ability. Parameter sensitivity analysis also confirmed its robustness to data selection, highlighting its engineering application potential.