Search Results

People and their communities are looking for transportation solutions that reduce travel time, improve well-being and accessibility, and reduce emissions and traffic congestion. Although new mobility services like ride-hailing advertise improvements in these areas, closer inspection has revealed a discrepancy between industry claims and reality. Key decision-makers, including citizens, cities and enterprise, and mobility service providers have the opportunity to leverage connected vehicle and connected device data through cloud-based APIs. We propose a GHG data analytics framework that functions on top of a cloud platform to provide unique system-level perspectives on operating transportation services, from procuring the most environmentally and people friendly vehicles to scheduling and designing the services based on data insights.

Connected vehicle data unlock compelling solutions for vehicle owners and fleet managers. In selecting machine learning algorithms for use in predicting a connected vehicle signal value, time series dependency is critical to understand. With little to no time series dependency, conventional machine learning models may be used with a feature set that has few or no lag variables. If there is a lot of time series dependency including long-term dependencies, deep learning architectures like variants of recurrent neural networks (RNN) may be a better approach. Further, at any time step, RNN features may be specified to use some number of past time steps to predict the latest value. This paper seeks to identify time series dependency of connected vehicle signals, and selection of the number of time steps to look back in the features set to minimize error.