Computer and behavioral scientists at the University of Buffalo are developing a system that studies faces, voices, bodies and other biometrical data to predict terrorist intentions.

"The goal is to identify the perpetrator in a security setting before he or she has the chance to carry out the attack," says Professor Venu Govindaraju.

The project was recently awarded $800,000 by the National Science Foundation to create this system. "We are developing a prototype that examines a video in a number of different security settings, automatically producing a single, integrated score of malfeasance likelihood," adding that the system will incorporate machine "learning" capabilities, which will allow it to adapt over time.

"Human screeners have fatigue and bias, but the machine does not blink."

They might as well be using crystal balls — and it would be a lot cheaper to be sure. The strange folks at DARPA are playing at fortune-telling with their (code named) "Deep Green" program.

Battlefield commanders can feed data into secret software to get back forecasts of how a mission might turn out.

I’ll send them that old toy called 8 Ball.