No abstract

No abstract

The growth of ride-hailing (RH) companies over the past few years has affected urban mobility in numerous ways. Despite widespread claims about the benefits of such services, limited research has been conducted on the topic. This paper assesses the willingness of Munich transportation users to pay for RH services. Realizing the difficulty of obtaining data directly from RH companies, a stated preference survey was designed. The dataset includes responses from 500 commuters. Sociodemographic attributes, current travel behavior and transportation mode preference in an 8 km trip scenario using RH service and its similar modes (auto and transit), were collected. A multinomial logit model was used to estimate the time and cost coefficients for using RH services across income groups, which was then used to estimate the value of time (VOT) for RH. The model results indicate RH services’ popularity among those aged 18–39, larger households and households with fewer autos. Higher income groups are also willing to pay more for using RH services. To examine the impact of RH services on modal split in the city of Munich, we incorporated RH as a new mode into an existing nested logit mode choice model using an incremental logit. Travel time, travel cost and VOT were used as measures for the choice commuters make when choosing between RH and its closest mode, metro. A total of 20 scenarios were evaluated at four different congestion levels and four price levels to reflect the demand in response to acceptable costs and time tradeoffs.

No abstract

This study proposes a data fusion and deep learning (DL) framework that learns high-level traffic features from network-level images to predict large-scale, multi-route, speed and volume of connected vehicles (CVs). We present a scalable and parallel method of processing statewide CVs’ trajectory data that leads to real-time insights on the micro-scale in time and space (two-dimensional (2D) arrays) on graphics processing unit (GPUs) using the Nvidia rapids framework and dask parallel cluster, which provided a 50× speed-up in the data extraction, transform and load (ETL). A UNet model is then applied to perform feature extraction and multi-route speed and volume channels over a multi-step prediction horizon. The accuracy and robustness of the proposed model are evaluated by taking different road types, times of day and image snippets and comparing the model to benchmarks: Convolutional Long–Short-Term Memory (ConvLSTM) and a historical average (HA). The results show that the proposed model outperforms benchmarks with an average improvement of 15% over ConvLSTM and 65% over the HA. Comparing the image snippets from each prediction model to the actual image shows that image textures were highly similar in UNet to the benchmark models used. UNet’s dominance in performing image predictions was also evident in multi-step forecasting, where the increase in errors was relatively minimal over longer prediction horizons.