Smart Data Revolution
Sep 13, 2017 — Atlanta, GA
Most cities are grappling with becoming truly smart, but they're making exciting progress. Testbeds and innovation districts have popped up across the country, and on a larger scale, cities are deploying sensors and cameras to collect information about our daily lives. They’re also tapping into the power of universities by working together on research projects that explore how data, technology, and policy changes can address urban challenges.
Georgia Tech recently expanded its smart cities efforts by joining the national MetroLab Network in 2016 and assembling a 20-plus member interdisciplinary faculty council co-chaired by Gisele Bennett, Georgia Tech’s associate vice president for research, Faculty Interaction, and Beth Mynatt, executive director of the Institute for People and Technology (IPaT).
"Creating smart cities is a true interdisciplinary challenge on an exponential scale," said Mynatt. "It's important that we pull together the breadth and depth of Georgia Tech's expertise in this area to meet local, national and international needs."
The Institute is pairing the council with a number of key partnerships, including the City of Atlanta, and a three-year strategic partnership with the German American Chamber of Commerce of the Southern U.S. (GACC South) which will help connect organizations that work on sustainable mobility issues in the U.S. and abroad. A new Smart Cities and Inclusive Innovation website provides a comprehensive summary of these key partnerships, projects, and data sets.
"Smart cities remains an evolving area with unexplored technical and social frontier," said Debra Lam, managing director for Smart Cities and Inclusive Innovation at Georgia Tech. "It can't be successfully deployed by any single entity and it is vital that partnerships are pursued and developed to further the research applications and broaden the impact, to ensure that the beneficiaries are the people and communities at large. The research at Georgia Tech reflects that wider reach."
Georgia Tech’s smart cities initiative extends to research projects from diverse disciplines across campus. Faculty researchers are gathering data about safety, how people travel, and even how taxpayer money is spent, all in an effort to improve the quality of life for residents.
Late last year, Yao Xie, assistant professor in the School of Industrial and Systems Engineering, began working with the Atlanta Police Department to test an algorithm that finds connections between crime incidents. The algorithm examines both structured data captured by 911 operators — the type of crime, and when and where it happened — and unstructured, or free text data. This type of data is gathered by police officers at the scene of the crime and includes detailed, narrative descriptions from the officer, victims, and witnesses.
The tricky part for police investigators is manually analyzing thousands upon thousands of reports — including new reports that are coming in every day — to find patterns between cases, which could help solve serial crimes. It’s an impossible task. Xie’s algorithm automates this process by dissecting incident reports and learning the similarities between words and common patterns in how crimes occurred. It has to be smart enough to recognize that two or more crimes could be related.
“This is an artificial intelligence way of processing police reports,” said Xie. “It’s a way of investigating cases much faster, and more effectively.”
The Atlanta Police Department provided three years of data to process, more than 24,000 cases. The algorithm analyzed that data within hours.
“Our partnership with Georgia Tech has the potential to truly transform the speed and manner in which we currently analyze crime data,” said former Atlanta Police Department Sergeant Frank Ruben, who is now with the city’s Atlanta Information Management department. “The ability this gives our investigators to proactively compare notes and identify trends will aid tremendously in furthering Chief Erika Shields’ priority of reducing violent crime through innovative technology.”
There are challenges with this method, explained Xie, including typos, grammatically incorrect sentences, and differences in how individual officers write their reports. “The reports are very different from one to the next; in fact, they’re never the same. The algorithm has to be robust enough to see errors.”
Xie is receiving financial support for her research from the Atlanta Police Foundation. She’s now working to integrate the algorithm into the North Avenue Smart Corridor and pull in crime sensor data.
The City of Atlanta with its partners, including Georgia Tech, the Georgia Department of Transportation, and many others, will officially unveil the North Avenue project on September 14th. The corridor stretches between Midtown and Downtown Atlanta and features cameras that monitor traffic and public safety, data-collecting road sensors and modern, adaptive traffic lights that exchange information with each other and vehicles traveling along North Avenue. The City will also demonstrate a semi-autonomous vehicle guided by sensors installed along the route.
“The corridor is intended to demonstrate all of the ways that technology can connect us, in particular from a transportation perspective," said Faye DiMassimo, general manager of Renew Atlanta. "In some way, shape or form, all of the technology features of the corridor contribute to a safer experience as well as enhanced mobility.”
Georgia Tech will leverage the integrated smart technology and data to better understand traffic operations along the corridor, ultimately providing feedback to improve system efficiency. "There’s no substitute for the great, robust evaluation that Georgia Tech is going to provide as we measure the performance of the corridor,” said DiMassimo.
Currently, most smart city traffic research focuses on travel time because it’s a challenge that drivers experience every day. One piece that’s missing according to Michael Hunter, associate professor in the School of Civil and Environmental Engineering, is energy use and emissions. He’s using smart technology data collected from connected vehicles, road sensors, and other sources to understand the impact of traffic signal timing and driver behavior on energy use and emissions, leading to more efficient signal control and driving decisions. “On any one car that may only be a small number of gallons saved. However, when you look at that day after day over a year you might start seeing some significant energy savings.”
In addition to analyzing the North Avenue data, Randall Guensler, a professor in the School of Civil and Environmental Engineering, is leading an effort within the project that is collecting data through an app they developed called Commute Warrior. It runs in the background of the user’s smartphone and monitors walking, biking, vehicle trips and other travel activity. Researchers then use the data to study travel behavior, and app users can look back at their trips using a travel journal and interactive map interface.
Hunter and Guensler will utilize this trip data to advance the ability to improve signal timing and driver routing decisions during special events, like Atlanta Falcons or Atlanta United games. The goal is to provide more predictive information and incentivize a change in drivers’ behavior. “If you leave 15 minutes later or a half hour earlier, what would be the difference in energy use, emissions, or travel time?”
Hunter says data-gathering and analyzation are about people and changing their lives for the better. “All the detection in the world, who cares if you’re not turning it into something actionable? We’re gathering data, but how do we use that data to improve the quality of life?”
Unlocking City Data
What good is data if it can’t be easily accessed? And what can data from 10 or even 20 years ago tell us? These are the questions behind Thomas Lodato and Jennifer Clark's research. They’re examining aging or obsolete legacy systems that house budget and spending data for the City of Atlanta, digitizing the data, and migrating it to a more sustainable system. The data spans two decades starting in 1996. The researchers are also looking at how existing or older systems sync with new ones.
“All the discussion about smart cities tends to be about these emerging, new technologies, real-time sensors and partnerships with applications that are providing data,” said Lodato, a research scientist with IPaT and the Center for Urban Innovation. “There’s this wealth of other data that exists that’s embedded in some sort of legacy system.”
Although older budgets are currently available to the public on the City of Atlanta website, they’re in a format that makes it difficult to extract data. The unlocked data, even from 20 years ago, can provide insight into how city officials are spending taxpayer money and allow researchers to create visualizations that show trends over time.
“A city’s budget is about political promises. So when someone asks, ‘Where did my money go?’ we can compare, longitudinally, promises that were set forth and whether or not they were kept,” explained Lodato. “A smart city is not just reconfiguring the technological landscape of a city. It’s also reconfiguring its institutional and political landscape.”
Lodato and Clark also want to understand the socio-technical aspects of data systems — how cities are maintaining them, and who’s maintaining them. They say it’s imperative that cities include systems maintenance in their long-term strategic plans.
"We're interested in the work behind the technology that's creating smart cities," said Clark, director of the Center for Urban Innovation and associate professor in the School of Public Policy. "That includes the work of making data meaningful to people living, working, and investing in cities. Smart cities research often focuses so much on the future of cities that the plans for data – collection, storage, systems architecture – are designed looking forward, not back. But for the data to be meaningful it must be able to speak to change over time. In our work, we focus on the importance of designing and planning for that integrated systems approach to smart cities."
IPaT provided one semester of funding for this project and five others through the Smart & Connected Communities Data Pilot Grants program and is hosting a speaker series at Atlanta City Hall where grant recipients receive feedback on their work.
Photos by: Christopher Moore
Graphics by: Raul Perez
Communications Officer, Institute for People and Technology