December 16, 2004
\nWHAT’S NEXT
\nWhen Shots Ring Out, a Listening Device Acts as Witness
\nBy CYRUS FARIVAR<\/p>\n
IN an unusual application of neuroscience research, police agencies around the country may soon be able to equip street corners with microphones and video cameras to fight gun-related crime.<\/p>\n
The system, based on work by Dr. Theodore Berger, director of the Center for Neural Engineering at the University of Southern California, uses the equipment and a computer to recognize gunshots, pinpoint where they came from and transmit the coordinates to a command center. It relies on software that mimics the way the human brain receives, processes and analyzes sound. The system has drawn the attention of several law enforcement agencies, including police departments in Chicago, Oklahoma City and Phoenix and the Los Angeles County Sheriff’s Department.<\/p>\n
“When you put in automated gunshot recognition in a highly visible format like this, the residents no longer have to fear reprisal and the police no longer have to depend on the residents for accurate information,” said Bryan Baker, 56, chief executive officer of Safety Dynamics. He and Dr. Berger co-founded the company in Oak Brook, Ill., 20 months ago to produce the system, called Smart Sensor Enabled Neural Threat Recognition and Identification, or Sentri.<\/p>\n
Dr. Berger, 54, who is also chief scientist at Safety Dynamics, said the system was able to distinguish gunshots from voices, car traffic and construction. “You can find that brains can do it, but you can’t find physical systems that can do it,” Dr. Berger said. “It’s very hard to corrupt the signal in such a way that we don’t know what’s going on.”<\/p>\n
The software is able to recognize sound by dividing it into small sections and matching them to known audio-wave patterns through a technique known as wavelet analysis. The system also examines the incoming sound as a whole, making sure that its components are heard in the proper order, even if one is obscured by other noises, such as a loud truck.<\/i><\/p>\n