[ad_1]
Each node in the Array of Things is equipped with an Nvidia graphics processing unit (or GPU) to compute images in the field and sends only processed data to the network—a form of edge computing. As an additional privacy protection, the nodes are designed to be installed temporarily. “I’d rather see edge computing overlaid on the city, where there’s a camera monitoring what you’re doing everywhere you go,” Catlett said. “This is more dystopian than I would like to see. But I think these edge devices have a place for investigation. You put that potential in for a purpose and then you take it out.
Between 2016 and 2019, the team connected 140 AoT nodes to Chicago streetlights. Through a participatory process, the team at Argonne and area universities worked with everyday Chicagoans and city departments to decide where to place the sensors.
Chicago/URBANCCD
Since then, dozens of studies have used sensor data. The crossings have been used to assess the safety of grade-level railroad crossings, monitor pedestrian crossing use, and identify flood hazards on the Chicago River. Project co-author Kathleen Cagney, who directs the Institute for Social Research at the University of Michigan, used environmental data from the sensors for a public health study and found higher rates of asthma in areas where the sensors detected air pollution.
Catlett’s team took on low-tech projects. Last year, for example, he and his colleagues teamed up with Microsoft Research to install 115 low-cost, solar-powered air quality sensors at bus shelters across the city. The data revealed unprecedented levels of pollution hot spots near industrial corridors on Chicago’s south and west sides. Environmental and community groups are now pushing the city to make policy changes. The team plans to expand to thousands of air quality nodes in the coming years.
The collection is expanding beyond Chicago with a project called SAGE. Unlike other urban sensing systems that tend to be proprietary, SAGE allows anyone to write software for its nodes, which contain high-resolution hyperspectral cameras, lidar and audio recorders.
Catlett said the team is now entering the deployment phase. By the end of the year, it plans to install 50 of the $10,000 nodes in Chicago, replacing the previous generation of Thing nodes. Several dozen are deployed nationwide to track wildfires in Southern California and analyze weather and climate change. The National Science Foundation wants 80, each to build the National Ecological Observatory Network. Oregon requires 100 to detect an earthquake. The Australian Science Agency, CSIRO, issued the order. The library of open source applications available on GitHub is constantly growing and includes programs for identifying birds by their songs and distinguishing fungal clouds from images.
“Fitness tracker for the city” has become global – just like our changing world to study.
Christian Elliott is a freelance science journalist based in Chicago, Illinois.
[ad_2]
Source link
