This article reports on an integrated modeling exercise, conducted on behalf of the US Federal Highway Administration, on the potential for frequent automated transit shuttles (‘community transit’), in conjunction with improvements to the walking and cycling environment, to overcome the last-mile problem of regional rail transit and thereby divert travelers away from car use. A set of interlocking investigations was undertaken, including development of urban visualizations, distribution of a home-based survey supporting a stated-preference model of mode choice, development of an agent-based model, and alignment of the mode-choice and agent-based models. The investigations were designed to produce best-case estimates of the impact of community transit and ancillary improvements in reducing car use. The models in combination suggested significant potential to divert drivers, especially in areas that were relatively transit-poor to begin with. 相似文献
For route planning and tracking, it is sometimes necessary to know if the user is walking or using some other mode of transport. In most cases, the GPS data can be acquired from the user device. It is possible to estimate user’s transportation mode based on a GPS trace at a sampling rate of once per minute. There has been little prior work on the selection of a set of features from a large number of proposed features, especially for sparse GPS data. This article considers characteristics of distribution, auto- and cross-correlations, and spectral features of speed and acceleration as possible features, and presents an approach to selecting the most significant, non-correlating features from among those. Both speed and acceleration are inferred from changes in location and time between data points. Using GPS traces of buses in the city of Tampere, and of walking, biking and driving from the OpenStreetMap and Microsoft GeoLife projects, spectral bins were found to be among the most significant non-correlating features for differentiating between walking, bicycle, bus and driving, and were used to train classifiers with a fair accuracy. Auto- and cross-correlations, kurtoses and skewnesses were found to be of no use in the classification task. Useful features were found to have a fairly large (>0.4) correlation with each other. 相似文献
This paper discusses the appropriateness of the “3-stage urban transport policy development cycle” hypothesis proposed by Professor Peter Jones and the importance of both local development context and motorization transport culture in transport policy. It then makes some observations on the future prospects for sustainable cities and transport through major technological innovations in connected and autonomous vehicles, that is, in “Auto Sapiens” as next generation vehicles. 相似文献
A variety of automatic data collection technologies have been used to gather road and highway system data. The majority of these automatic data collection technologies are designed to collect vehicle-based data and either do not have the capability to collect other travel mode data (e.g., bicycles and pedestrians), or may need to be deployed differently to support this capability.
One type of wireless-based data collection system that has been deployed recently is based on Bluetooth technology. A key feature of Bluetooth-based data collection systems that makes travel mode identification feasible is that the Bluetooth-enabled devices within vehicles are also present on bicyclists and pedestrians. This research explores the effectiveness of applying cluster analysis methods when processing data collected via Bluetooth technology from vehicles, bicyclists, and pedestrians to automatically identify the associated travel modes. The results of several experiments utilizing multiple Bluetooth-based data collection units arranged linearly and in relatively close proximity on a simulated intersection demonstrate the potential of cluster analysis to accurately differentiate transportation modes from the collected data. 相似文献