当前位置: X-MOL 学术Comput. Aided Civ. Infrastruct. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Dynamic origin‐destination flow estimation using automatic vehicle identification data: A 3D convolutional neural network approach
Computer-Aided Civil and Infrastructure Engineering ( IF 8.5 ) Pub Date : 2020-05-27 , DOI: 10.1111/mice.12559
Keshuang Tang 1 , Yumin Cao 1 , Can Chen 1 , Jiarong Yao 1 , Chaopeng Tan 1 , Jian Sun 1
Affiliation  

Dynamic origin‐destination (OD) flow estimation is one of the most fundamental problems in traffic engineering. Despite numerous existing studies, the OD flow estimation problem remains challenging, as there is large dimensional difference between the unknown values to be estimated and the known traffic observations. To meet the needs of active traffic management and control, accurate time‐dependent OD flows are required to understand time‐of‐day traffic flow patterns. In this work, we propose a three‐dimensional (3D) convolution‐based deep neural network, “Res3D,” to learn the high‐dimensional correlations between local traffic patterns presented by automatic vehicle identification observations and OD flows. In this paper, a practical framework combining simulation‐based model training and few‐shot transfer learning is introduced to enhance the applicability of the proposed model, as continuously observing OD flows could be expensive. The proposed model is extensively tested based on a realistic road network, and the results show that for significant OD flows, the relative errors are stable around 5%, outperforming several other models, including prevalent neural networks as well as existing estimation models. Meanwhile, corrupted and out‐of‐distribution samples are generated as real‐world samples to validate Res3D's transferability, and the results indicated a 60% improvement with few‐shot transfer learning. Therefore, this proposed framework could help to bridge the gaps between traffic simulations and empirical cases.

中文翻译:

使用自动车辆识别数据的动态起点流估计:3D卷积神经网络方法

动态原始目的地(OD)流量估计是交通工程中最基本的问题之一。尽管进行了大量现有研究,但是由于要估计的未知值与已知的流量观测值之间存在较大的尺寸差异,因此OD流量估计问题仍然具有挑战性。为了满足主动流量管理和控制的需求,需要准确的与时间相关的OD流量,以了解每日时间流量的流量模式。在这项工作中,我们提出了一个基于三维(3D)卷积的深度神经网络“ Res3D”,以学习由自动车辆识别观测和OD流呈现的本地交通模式之间的高维相关性。在本文中,引入了一个结合了基于仿真的模型训练和少量触发学习的实用框架,以增强所提出模型的适用性,因为持续观察OD流可能很昂贵。该模型基于现实的道路网络进行了广泛测试,结果表明,对于大量的OD流量,相对误差稳定在5%左右,优于其他模型,包括流行的神经网络和现有的估计模型。同时,将损坏的和分布失调的样本作为真实样本生成,以验证Res3D的可移植性,结果表明,只需很少的转移学习就可以提高60%。因此,提出的框架可以帮助弥合交通模拟和经验案例之间的差距。因为持续观察OD流量可能很昂贵。所提出的模型在现实的道路网络的基础上进行了广泛的测试,结果表明,对于大量的OD流量,相对误差稳定在5%左右,优于其他模型,包括流行的神经网络和现有的估计模型。同时,将损坏和分布不均的样本作为真实样本生成,以验证Res3D的可移植性,结果表明,只需很少的转移学习就可以提高60%。因此,提出的框架可以帮助弥合交通模拟和经验案例之间的差距。因为持续观察OD流量可能很昂贵。所提出的模型基于现实的道路网络进行了广泛测试,结果表明,对于大量的OD流量,相对误差稳定在5%左右,优于其他模型,包括流行的神经网络和现有的估计模型。同时,将损坏的和分布失调的样本作为真实样本生成,以验证Res3D的可移植性,结果表明,只需很少的转移学习就可以提高60%。因此,提出的框架可以帮助弥合交通模拟和经验案例之间的差距。相对误差稳定在5%左右,优于其他几种模型,包括流行的神经网络以及现有的估计模型。同时,将损坏和分布不均的样本作为真实样本生成,以验证Res3D的可移植性,结果表明,只需很少的转移学习就可以提高60%。因此,提出的框架可以帮助弥合交通模拟和经验案例之间的差距。相对误差稳定在5%左右,优于其他几种模型,包括流行的神经网络以及现有的估计模型。同时,将损坏和分布不均的样本作为真实样本生成,以验证Res3D的可移植性,结果表明,只需很少的转移学习就可以提高60%。因此,提出的框架可以帮助弥合交通模拟和经验案例之间的差距。
更新日期:2020-05-27
down
wechat
bug