In this work, we adopt an unsupervised learning approach, k-means clustering, to analyze the arterial traffic flow data over a high-dimensional spatio-temporal feature space. As part of the adaptive traffic control system deployed around the East Liberty area in Pittsburgh, high-resolution traffic occupancy and count data are available at the lane level in virtually any time resolution. The k-means clustering method is used to analyze those data to understand the traffic patterns before and after the closure and reopening of an arterial bridge. The modeling framework also holds great potentials for predicting traffic flow and detect incidents. The main findings are that clustering on high-dimensional spatio-temporal features can effectively distinguish flow patterns before and after road closure and reopening and between weekends and weekdays.

When self-driving cars get here, they'll make our commutes more efficient and allow us to get the kids to soccer practice without disrupting mom and dad's work days. They'll conserve resources, boost mobility for seniors and others who can't, and make deadly traffic accidents all but disappear. But the impact of self-driving cars will go deeper than even that, according to researchers at the Illinois Institute of Technology, who've begun to study the potential ultra-long-range impacts of self-driving cars on urban environments. Everything from sidewalks and curbs to streets, building designs, urban layouts, and living patterns will change as computers take the wheel. "We're looking at the broader urban effects--and urban opportunities--of this technology," says Illinois Tech architect Marshall Brown, one of the team members in the Chicago school's Driverless Cities Project. "It's in the news a lot, but nobody's been discussing what it will actually do to cities." Just six percent of long-range transportation plans in major US cities are factoring the impact of autonomous cars, according to a report released in the fall by the National League of Cities.

When self-driving cars get here, they'll make our commutes more efficient and allow us to get the kids to soccer practice without disrupting mom and dad's work days. They'll conserve resources, boost mobility for seniors and others who can't, and make deadly traffic accidents all but disappear. But the impact of self-driving cars will go deeper than even that, according to researchers at the Illinois Institute of Technology, who've begun to study the potential ultra-long-range impacts of self-driving cars on urban environments. Everything from sidewalks and curbs to streets, building designs, urban layouts, and living patterns will change as computers take the wheel. "We're looking at the broader urban effects--and urban opportunities--of this technology," says Illinois Tech architect Marshall Brown, one of the team members in the Chicago school's Driverless Cities Project. "It's in the news a lot, but nobody's been discussing what it will actually do to cities." Just six percent of long-range transportation plans in major US cities are factoring the impact of autonomous cars, according to a report released in the fall by the National League of Cities.