|
|
基于大语言模型的缺失数据交通流预测
|
Abstract:
交通流预测在智能交通系统中具有重要意义。近年来，交通预测模型多基于复杂的深度学习架构，然而，这些模型往往缺乏对输入到输出过程及其结果的直观解释。由于交通数据本身的复杂性、模型不透明性以及数据收集过程中常见的缺失问题，缺失数据的处理和预测结果的可解释性仍然面临重大挑战。针对这一问题，我们提出了一种基于大语言模型(LLM-MTFP)的可解释性缺失数据交通预测模型。具体而言，该模型通过将多模式交通数据转换为自然语言描述，利用大语言模型捕捉复杂的时空特征和外部因素，并基于语言指令进行微调。我们在加利福尼亚州多模态数据集上进行了实验验证。结果表明，本文提出的方法在预测准确性方面优于基线模型，并且能够提供可靠的解释，验证了大语言模型在交通流预测中的应用潜力。
Traffic flow prediction holds significant importance in intelligent transportation systems. In recent years, traffic prediction models have largely been based on complex deep learning architectures. However, these models often lack intuitive explanations of the input-output processes and their results. Due to the inherent complexity of traffic data, model opacity, and common data missing issues during the data collection process, handling missing data and ensuring the interpretability of prediction results remain major challenges. To address this problem, we propose an explainable missing data traffic prediction model based on large language models (LLM-MTFP). Specifically, the model converts multimodal traffic data into natural language descriptions, leverages large language models to capture complex spatiotemporal features and external factors, and fine-tunes the model based on linguistic instructions. We conducted experimental validations on the California multimodal dataset. The results demonstrate that the proposed method outperforms baseline models in prediction accuracy and can provide reliable explanations, verifying the application potential of large language models in traffic flow prediction.
| [1] | 姚俊峰, 何瑞, 史童童, 等. 基于机器学习的交通流预测方法综述[J]. 交通运输工程学报, 2023, 23(3): 44-67. |
| [2] | Mehdipour Ghazi, M., Ramezani, A., Siahi, M. and Mehdipour Ghazi, M. (2022) Learning Spatiotemporal Features from Incomplete Data for Traffic Flow Prediction Using Hybrid Deep Neural Networks. Transport Research Part C: Emerging Technologies, 134, Article 102514. |
| [3] | Luo, Y., Wan, Z., Chen, Y., Mai, G., Chung, F. and Larson, K. (2024) TransFlower: An Explainable Transformer-Based Model with Flow-to-Flow Attention for Commuting Flow Prediction. Transportation Research Part C: Emerging Technologies, 144, Article 103895. |
| [4] | Wang, R., Xin, Y., Zhang, Y., Perez-Cruz, F. and Raubal, M. (2024) Counterfactual Explanations for Deep Learning-Based Traffic Forecasting. IEEE Transactions on Intelligent Transportation Systems, 25, 768-778. |
| [5] | 崔建勋, 要甲, 赵泊媛. 基于深度学习的短期交通流预测方法综述[J]. 交通运输工程学报, 2024, 24(2): 50-64. |
| [6] | Gunning, D. and Aha, D.W. (2019) DARPA’s Explainable Artificial Intelligence Program. AI Magazine, 40, 44-58. https://doi.org/10.1609/aimag.v40i2.2850 |
| [7] | Mei, H., Li, J., Liang, Z., Zheng, G., Shi, B. and Wei, H. (2023) Uncertainty-Aware Traffic Prediction under Missing Data. Neurocomputing, 522, 451-462. |
| [8] | He, Z., Chow, C. Y. and Zhang, J.D. (2019) STCNN: A Spatio-Temporal Convolutional Neural Network for Long-Term Traffic Prediction. 2019 20th IEEE International Conference on Mobile Data Management (MDM), Hong Kong SAR, 10-13 June 2019, 226-233. https://doi.org/10.1109/MDM.2019.00-53 |
| [9] | Nie, T., Qin, G., Wang, Y. and Sun, J. (2023) Correlating Sparse Sensing for Large-Scale Traffic Speed Estimation: A Laplacian-Enhanced Low-Rank Tensor Kriging Approach. Transportation Research Part C: Emerging Technologies, 152, Article 104190. https://doi.org/10.1016/j.trc.2023.104190 |
| [10] | Wang, L., Ren, Y., Jiang, H., Cai, P., Fu, D., Wang, T., et al. (2023) AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-Modal Large Model. arXiv: 2312.13156. https://doi.org/10.48550/arXiv.2312.13156 |
| [11] | Ren, Y., Chen, Y., Liu, S., Wang, B., Yu, H. and Cui, Z. (2024) TPLLM: A Traffic Prediction Framework Based on Pre-trained Large Language Models. arXiv: 2403.02221. https://doi.org/10.48550/arXiv.2403.02221 |
| [12] | Wang, P., Wei, X., Hu, F. and Han, W. (2024) TransGPT: Multi-Modal Generative Pre-Trained Transformer for Transportation. 2024 International Conference on Computational Linguistics and Natural Language Processing (CLNLP), Yinchuan, 19-21 July 2024, 96-100. https://doi.org/10.1109/clnlp64123.2024.00026 |
| [13] | Qu, J., Ma, X. and Li, J. (2024) TrafficGPT: Breaking the Token Barrier for Efficient Long Traffic Analysis and Generation. arXiv: 2403.05822. https://doi.org/10.48550/arXiv.2403.05822 |
| [14] | Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735 |
| [15] | Li, Y., Yu, R., Shahabi, C. and Liu, Y. (2018) Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. Proceedings of the 2018 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, 19-23 August 2018, 934-943. |
| [16] | Yu, B., Yin, H. and Zhu, Z. (2018) Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, 13-19 July 2018, 3634-3640. https://doi.org/10.24963/ijcai.2018/505 |
| [17] | Zheng, Y., Li, Q. and Zhang, W. (2018) ASTGCN: Attention-Based Spatio-Temporal Graph Convolutional Networks for Traffic Flow Forecasting. Proceedings of the 2018 IEEE International Conference on Data Mining (ICDM), Singapore, 17-20 November 2018, 59-68. |
| [18] | Wu, Z., Pan, S., Long, G., Jiang, J. and Zhang, C. (2019) Graph Wavenet for Deep Spatial-Temporal Graph Modeling. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, Macao SAR, 10-16 August 2019, 1907-1913. https://doi.org/10.24963/ijcai.2019/264 |
| [19] | Li, X. and Liu, Y. (2020) Attention-Based Graph Convolutional Recurrent Network for Spatiotemporal Forecasting. Proceedings of the 2020 IEEE International Conference on Data Mining (ICDM), Sorrento, 17-20 November 2020, 118-128. |
| [20] | Song, J. and Zha, Z. J. (2020) STTN: A Spatio-Temporal Traffic Network for City-Wide Traffic Forecasting. Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 4579-4588. |
| [21] | Yu, R. and Li, Q. (2021) Deep Spatio-Temporal Attention Graph Neural Network for Traffic Flow Prediction. Proceedings of the 2021 IEEE International Conference on Data Mining (ICDM), Auckland, 7-10 December 2021, 203-212. |
