NSF Awards $100K Grant to Develop ‘Crowd-Sourcing’ Technology to Monitor ‘Behavior’ Via Cell Phones

September 27, 2013 - 2:11 PM

cell phones

Cell phones (AP Photo)

(CNSNews.com) The National Science Foundation has awarded a $100,000 grant to the University of Illinois at Urbana-Champaign to “accurately capture crowd behavior” through the use of cell phone applications used by “watchers” in the crowd.

“Proliferation of mobile smartphones has opened up possibilities of leveraging the people and devices in a crowd, (i.e., crowd-sourcing) to gather data from and monitor large crowds,” the grant abstract stated. “However, current solutions either put unpredictable stress on the wireless or cellular infrastructure to a cloud and on energy-constrained smartphones or do not accurately capture crowd behavior.”

The grant, which is funded from Oct. 1, 2013 to Sept. 30, 2014, pays for the university’s “CrowdWatch” project, which is a collaboration between the school and Dartmouth College.

“In response, our CrowdWatch project will investigate monitoring crowds from the ‘inside-out’ via a scalable, distributed and energy-efficient in-network crowd-sourcing framework,” the abstract stated. “Local energy-efficient coordination and processing will enable the off-loading of some of the processing to the devices by establishing a hierarchy of participants -- multi-radio devices (i.e., Wi-Fi and Bluetooth).

“Through probabilistic monitoring of a crowd, CrowdWatch will reduce the demand on the bandwidth to the cloud and enhance traditional crowd-sourcing by enabling information to be delivered back to and among people within the crowd,” the abstract states.

CrowdWatch researchers described how they will use cell phone users with an application on their phone to monitor crowds.

“At the highest level of the hierarchy, CrowdWatch first selects a small group of watchers that act to aggregate local and information from other CrowdWatch nodes in their Wi-Fi neighborhood, with the expectation that the collection of watchers covers the majority of the crowd as needed,” the researchers explained. “Since it is not always necessary to collect sensor data from all devices in a crowd, each watcher targets a number of representative sample areas in its region by probabilistically selecting a set of sampler nodes in its Wi-Fi neighborhood.”

Such technology would have been helpful during the 2012 Summer Olympics in London, which had to depend on camera footage to monitor large crowds and could not be viewed in real time, the researchers noted.

The grant abstract states that the technology will be the source of “experimentation” at two university activities that attract large crowds.

“Validation of CrowdWatch will entail experimentation and measurements of performance metrics such as resource usage, crowd density and user mobility, effectiveness of information distribution and monitoring of interaction frequency among users during two crowed events on our campus, the Engineering Open House and a University Basketball Game,” the abstract states.

A researcher with the project told CNSNews.com that the watchers are “randomly alternating crowd participants” but did not make clear whether those participants were actively taking part or being used through their technology.

When CNSNews.com asked whether this framework was put in place in a particular U.S. city, what entities would have access to the data collected, (i.e. police, government, etc.), the researcher responded:

“It is not a framework for a particular city,” the researcher said. “It is meant to support target events where people use the app.”