Advancing Temporal Multimodal Learning with Physics Informed Regularization
Advancing Temporal Multimodal Learning with Physics Informed Regularization
复制标题
DOI：
10.1109/ciss56502.2023.10089632
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Niharika Deshpande;Hyoshin Park;Venktesh Pandey;Gyugeun Yoon
中科院分区：
文献类型：
--
作者：
Niharika Deshpande;Hyoshin Park;Venktesh Pandey;Gyugeun Yoon
从真实世界的数据中估计出行时间的多模式分布对于理解和管理拥堵至关重要。混合模型可以估计概率密度函数中存在明显峰值时的总体分布，但在认知不确定性下，没有考虑混合信息在不同时空尺度上的传递，以捕获未观测到的异质性。在本文中，开发了一个物理信息和正则化的预测模型，该模型可以跨时间和空间的相似分布网络段共享观测结果。通过对相似的混合模型进行分组，该模型在遥远的非连续未开发位置使用特定的样本分布，提高了TT预测。与没有这些更新的传统预测相比，该模型的19%的性能显示了间接学习的好处。与传统的出行时间预测工具不同，所开发的模型可以被交通和规划机构用来了解历史上的时间，以及历史数据的样本量对当前预测有用。
Estimating multimodal distributions of travel times from real-world data is critical for understanding and managing congestion. Mixture models can estimate the overall distribution when distinct peaks exist in the probability density function, but no transfer of mixture information under epistemic uncertainty across different spatiotemporal scales has been considered for capturing unobserved heterogeneity. In this paper, a physics-informed and -regularized prediction model is developed that shares observations across similarly distributed network segments across time and space. By grouping similar mixture models, the model uses a particular sample distribution at distant non-contiguous unexplored locations and improves TT prediction. Compared to traditional prediction without those updates, the proposed model's 19% of performance show the benefit of indirect learning. Different from traditional travel time prediction tools, the developed model can be used by traffic and planning agencies in knowing how far back in history and what sample size of historic data would be useful for current prediction.