American scientists from the Georgia Institute of Technology (GT) tested a mobile camera system controlled by an algorithm aimed at combating street crimes. The results of the research were officially published Web site scientific institution.
Experts trained the neural network on data on various criminal incidents that occurred over many years in the small town of Warner Robins, which has a population of about 66 thousand people.
The general idea is that in any city there are disadvantaged areas where crime is most likely to occur. But Warner-Robins’ analysis of police reports showed that criminal activity tends to progress in urban areas.
Using data obtained using artificial intelligence regarding the places where future crimes are most likely to be committed, scientists moved smart cameras to new locations. Thanks to video surveillance, assaults and burglaries on the streets of Warner Robins dropped by 20 percent during the three-month experiment.
According to the researchers, such solutions could help fight crime in cities and counties with limited resources, as the developed neural network is compatible with existing street video surveillance systems.
Previously in Russia was created Neural network to find lost pets with facial recognition.
Source: Gazeta
Jackson Ruhl is a tech and sci-fi expert, who writes for “Social Bites”. He brings his readers the latest news and developments from the world of technology and science fiction.