Fighting crime through crowdsourcing.

• Position: Computers

Crowdsourcing utilizes the input of a crowd of online users to solve problems collaboratively. To advance this emerging technology, researchers at the University of Miami, Coral Gables, Fla., are developing a computing model that employs crowdsourcing to combine and optimize human efforts and machine computing elements.

The model can be used to perform the complex task of face recognition--a method employed in law enforcement. It is a new approach to using social networks as a formal part of the criminal investigation process, explains computer scientist Brian Blake, vice provost for Academic Affairs and dean of the Graduate School, who is principal investigator of the project. "The breadth of the Internet and popularity of smartphones have facilitated the onset of online crowdsourcing platforms. Our project attempts to leverage the power of the crowd to solve complex problems--on demand."

Unlike previous works, where machines and humans would address distinct tasks, the current project is unique in that the investigators recognize that sometimes the jobs requiring human and/or machine interventions are exactly the same. Traditionally, in a criminal investigation, a workflow might use computers to sort pictures and information, then use the people...