Fujitsu Develops AI System That Can Catch Criminals On The Run

When a criminal is on the run, there are so many possibilities in which they can escape. They can escape via a car, via public transport, via foot. They can head down on road, or they can try and escape through the back roads and alleys, and so on. Given the number of law enforcement, it would be pretty hard to try to spread out the entire force over an entire city.

However Fujitsu thinks that they can help as they have developed an AI system (via Engadget) that relies on game theory to help determine where police should deploy their forces to be the most effective. This isn’t a new concept but previously, applying game theory would have taken too long given the size of cities such as Tokyo.

According to Fujitsu, they claim that this is possible thanks to their newly developed technology. ”Fujitsu Laboratories and the University of Electro-Communications have developed an algorithm to rapidly solve city-scale road network security problems. Compared with previous technology, this makes it possible to find the theoretically optimal security plan 20 times faster, on average, for a 100-node problem, and 500 times faster, on average, for a 200-node problem.”

The company also announced their plans to commercialize the system during the fiscal year of 2017, while the University of Electro-Communications will be expanding the technology beyond city-scale road networks and into other fields.

Tyler Lee
Categories: Computers, General
Tags: AI (Artificial Intelligence), Fujitsu