Zhiyuan Liu

TL;DR: This paper analyzes the passenger flow from scopes on both macroscopic and microscopic levels, in order to take full advantage of the information from a variety of views and inspired by the feature engineering of decision-tree-based models, a modular convolutional neural network is designed.

TL;DR: In this article, the authors showed that the constant v/c ratio on a private toll road is still held via relaxing this assumption, and they further examined in different scenarios: the volume-capacity ratio remains constant under demand regulation, markup charge regulation, and social cost minimization scheme; it may change under the rate-of-return regulation, it may decrease under capacity regulation and increase under price-cap regulation.

TL;DR: Experimental results on city-wide online taxi-hailing demand predictions demonstrate that the proposed attention-based ensemble net is superior to the existing ensemble strategy in terms of the prediction accuracy.

TL;DR: Increased activation of the VS and significantly higher functional connectivity with the dorsal anterior cingulate cortex (dACC) were found when their outcomes were better than others, and the VS‐dACC functional connectivity was correlated with risk‐taking behavior.

TL;DR: The network capacity with second-best constraints (NCSC) is investigated to meet some specific development requirements of urban transport networks, and an exact solution method is developed for the NCSC problem, wherein, a modified improved gradient projection (MIGP) algorithm is designed for the lower-level multimodal flow equilibrium problem, and a tailored sensitivity analysis-based (SAB) method is employed for solving theNCSC problem.