The increasing population in cities induces a high travel demand. Unfortunately, due to the limited capacity of urban transport networks, this increasing demand for travel raises various problems a...
Abstract To identify time-space locations where public transit infrastructure fails to provide a reliable and timely alternative to private vehicles, this paper proposes a new travel demand-independent persistent homology-based method to locate and rank the severity of modal travel desert. Persistent homology, which is a tool from algebraic topology, is incorporated and the severity of a transit desert is measured as a trade-off between its proximity to existing transit infrastructure and the travel time required to travel through it. The proposed method highlights entire regions of cities that are bereft of suitable public transit, providing reasonable estimates even in the absence of travel demand data. This paper presents the techniques and software tools used to study the Stockholm public transit network. The proposed method is potentially useful for city planners to consider the trade-off between how severe a bottleneck is and how difficult the bottleneck is to fix.
With the growth of a city’s economy, neighboring cities are gradually integrated to form an urban agglomeration. As travel activities driven by various travel demands frequently take place within an urban agglomeration, it is essential to understand the travel demand between cities and improve the intercity transportation system, which promotes the coordinated development of cities in an urban agglomeration. This paper presents our investigation of the travel demand characteristics of urban agglomeration cities. The Beijing-Tianjin-Hebei area and its passenger flows between transportation hubs in the different cities, which are part of a typical urban agglomeration in China and representative travel demand, are taken as the empirical study objects. First, we introduce a method to extract trip data using mobile phone call detail record (CDR) data, which carry rich geographical information on travelers and has been extensively used in recent transportation research. Based on trip data, directed weighted travel demand networks were constructed, with the nodes representing the transportation hubs and the edges representing passenger flows. The results showed that edge weights can be characterized by power-law distribution, which reveals the phenomenon that most passenger flows are concentrated among a few hubs, implying unbalanced travel demand in the urban agglomeration. Our empirical findings contribute to a method for applying large-scale location-based data to extract human mobility information and to understanding the nature of travel demand on the scale of an urban agglomeration. They also provide guidance to government agencies in developing appropriate transportation policies and enhancing infrastructure in the urban agglomeration.
Identifying travelers’ transportation modes is a fundamental step for various transportation applications. With the popularization of ubiquitous GPS-enabled devices, leveraging travelers’ GPS trajectories to infer transportation modes becomes a cost-effective and appealing approach. The existing two-stage framework models usually suffer from the inevitable segmentation errors in the first stage, and can hardly realize real-time inferring. To overcome the drawbacks, this paper introduces a novel one-stage framework to directly predict the transportation mode of each GPS point without trip segmentation. A PointNet architecture from the 3D point cloud processing is designed to execute the pointwise classification task. By adding 1D convolution and pointwise pyramid pooling structure, the new network can extract local features, and significantly improve its performance. A post-processing algorithm is proposed to refine the pointwise classification. To compare with other two-stage studies, we comprehensively reproduced their results. Experimental results on the benchmark dataset of GeoLife show that the proposed framework can achieve accuracy up to 0.849 when distinguishing the following five modes: walk, bike, bus, car, and train. In addition, our model can accept trips of various lengths and benefit real-time applications greatly.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
