An Ear for Crime
A high-tech surveillance system being rolled out in high crime urban areas to
stem gun violence comes directly from a USC Viterbi School researcher’s pioneering
brain studies.
Theodore Berger, director of the USC Center for Neural Engineering who holds
the David Packard Chair in the Department of Biomedical Engineering, has spent
much of his research life deciphering how nerve cells code messages to each other.
Berger is also leading a project with the National Science Foundation’s Biomimetic
MicroElectronic Systems Engineering Research Center.
The newly patented microphone surveillance system uses Berger’s insights to recognize
— instantly, and with great accuracy — the sound of a gunshot, and only a gunshot,
within a two-block radius. It precisely locates where the shot was fired; centers
a camera on the shooter and places a 911 call to a central police station. The
police can then take control of the camera to track the shooter and dispatch officers
to the scene.
Late in 2004, the City of Chicago began installing the first five of a planned
80 of the devices in high crime neighborhoods, supplementing existing cameras.
In Los Angeles County, Sheriff Lee Baca has been soliciting community involvement
and participation to deploy 10 of the units in a pilot test. If the test is successful,
more units will be installed.
Algorithms devised by Berger, are at the heart of the "SENTRI" system built
by an Oak Brook, Illinois-based firm named Safety Dynamics (http://www.safetydynamics.net/index.htm)
where Berger holds the position of Chief Scientist.
SENTRI system as installed in Chicago
SENTRI uses acoustic recognizers, posted in trios or larger groupings on utility
poles or other listening posts. The acoustic recognizers are tuned to certain
specific warning sounds associated with gunshots. "A simple loud noise, even
an explosive noise, won't set them off," Berger says.
 |
|
Theodore Berger |
The device listens for the entire sound pattern of a gunshot, not just the initial
explosion, so it is unlikely to mistake other loud noises for gunfire. A specially
configured computer system (a "directional analyzer") accurately triangulates
any authenticated gunshot's location by calculating the difference in the time
the sound arrives at the different microphones in a SENTRI acoustic unit. Then
it points a camera, turns on lights, sounds an alarm and alerts police.
Field tests with handguns have shown 95% accuracy with respect to gunshot recognition,
and 100 percent accuracy with respect to centering the camera on the shooter for
those recognized gunshots.
SENTRI is an acronym for "Smart Sensor Enabled Neural Threat Recognition and
Identification." The "neural" in the title refers directly to Berger's work, in
which he has been deciphering the "language" nerve cells, or neurons, use to convey
information. He has been modeling the way the brain forms memories of sounds
Neurons distinguish signals by firing repeatedly, either faster or slower, in
different temporal patterns.
"It is the time difference between pulses that carries the information," Berger
explains. "This is a coding completely unlike that used by computers, which are
collections of ones and zeros, changing to the beat of a constant clock."
Working with computer specialists, Berger has created neural-like computer systems
that can model the neural time coding and make distinctions the way nerves do.
Four years ago, he and a colleague used the technique to demonstrate the first
speech recognition system that could pick words out of ambient noise as well as
humans can. While work continues on speech recognition applications, the system
has to learn each individual signal, and every word is a signal, so that learning
a language is a time-consuming process.
"But for alarm signals," says Berger, "you start with a relatively small number
of sounds you have to distinguish with high accuracy — gunshots, for example,
or diesel engines for border patrol crossings or oil pipeline thieves, or chainsaws
(and diesels) to listen for outlaw loggers. This vocabulary is quite manageable."
Machine sounds are the only ones in SENTRI's vocabulary. It cannot eavesdrop
on conversations, the scientist emphasizes.
Berger has been working for thirty to create a silicon system that can be transplanted
into living brain or other nervous tissue to restore function lost to disease
or injury. The current line of research that led to the gunshot recognition is
being expanded in a collaboration with computer scientist John Granacki at the
Viterbi School's Information Sciences Institute.
* * *
Here are some web pages with further information:
