Intelligent Transportation Systems

This paper demonstrates the power and value of connecting satisfaction surveys from public transportation passengers to smartphone tracking data and automatic vehicle location (AVL) data. The high resolution of the smartphone location data allows travel times to be dissected into their individual components, and the connection with AVL data provides objective information on personal-level experiences of the respondents. Analyses show how these data can provide a quantitative understanding of the relationship between planned and provisioned service, and customer satisfaction. In-vehicle...

We apply virtual machine abstractions to networked vehicles, enabling what we call cloud computing in space to create performance isolation between customers. In analogy to conventional system virtualization and cloud computing, there are customer-operated virtual vehicles that essentially perform like real vehicles, although they are in reality hosted by fewer, shared, provider-operated real vehicles. The motion of the virtual vehicles and real vehicles creates migration gain. As a result, cloud computing in space can do better than conventional cloud computing in the sense of realizing...

This brief describes findings from a research effort to understand the changing impacts of the pandemic upon households from different places and backgrounds living in the United States. We investigated the effects of the pandemic along with pandemic-based restrictions and rules on people’s behavior along with their mental and emotional health, social relations, and livelihoods. Unlike other research efforts, as far as we are aware this effort is the only one to join passive data from cell phones with survey information collected from the same individuals over time. We combined these data...

Large-scale highway traffic forecasting approaches are critical for intelligent transportation systems. Recently, deep- learning-based traffic forecasting methods have emerged as promising approaches for a wide range of traffic forecasting tasks. These methods are specific to a given traffic network, however, and consequently they cannot be used for forecasting traffic on an unseen traffic network. Previous work has identified diffusion convolutional recurrent neural networks, (DCRNN), as a state-of- the-art method for highway traffic forecasting. It models the complex spatial and temporal...