Abstract In data-driven travel-time prediction, previous studies have mainly used speed as the input. However, from a traffic engineering perspective, given that varies little in free-flow regime, density, which can accurately represent conditions regime to congested-flow is preferable an this study, we compared accuracy of densities spatially interpolated using spatial statistical and machine ...

Travel time prediction is one of the most important parameters to forecast network-wide traffic conditions. Travelers can access roadway networks and arrive in their destinations at lowest costs guided by accurate travel estimation on alternative routes. In this study, we propose a long short-term memory (LSTM)-based deep learning model, spatiotemporal features with Convolution Neural Network (...

The application domain of intelligent transportation is plagued by a shortage of data sources that adequately assess traffic situations. Currently, to provide routing and navigation solutions an unreliable travel time database that consists of static weights as derived from road categories and speed limits is used for road networks. With the advent of Floating Car Data (FCD) and specifically th...

At its core, genetics is a historical discipline. Mutations are passed on from generation to generation and accumulate as a result of chance as well as of selection within and between populations and species. However, until recently, geneticists were confined to the study of present-day genetic variation and could only indirectly make inferences about the historical processes that resulted in t...

For example, if someone is in the central business district of a large city, it might be cheapest to walk to a given destination. However, if the traveler has a particularly high value of travel time, the person might elect to pay for a ride to get to his or her destination faster. Similarly, a person driving a car might be faced with the choice between sitting in congestion or electing to pay ...

We describe a system called Olive that freezes and precisely reproduces the environment necessary to execute software long after its creation. It uses virtual machine (VM) technology to encapsulate legacy software, complete with all its software dependencies. This legacy world can be completely closed-source: there is no requirement for availability of source code, nor a requirement for recompi...