Artificial intelligence and neural networks in the service of KBSU security

Testing and training of specialized artificial intelligence systems to ensure the integrated security of the university is carried out at the Kabardino-Balkarian State University named after H.M. Berbekov on the basis of the Department of Computer Technologies and Information Security of the Institute of Artificial Intelligence and Digital Technologies, as well as the Center for Monitoring and Security Management of the Engineering Infrastructure and Information Technology Department.

Director of the Institute of Artificial Intelligence and Digital Technologies, Ph.D. Albert Shapsigov said:

Today the open video surveillance system consists of 520 ip-surveillance cameras installed in educational buildings, dormitory buildings and in the surrounding area. Artificial intelligence systems being tested by the university specialists, developed by the company «ITV».

Developed by ITV LLC, they allow for computer analysis of events that fall into the field of view of video cameras. The neural network analyzes people’s behavior 24/7 (when detectors are triggered for certain situations or scenarios: “shooting person”, “lying person”, “sitting person”, “raised hands detector”, etc.) and issues an alarm signal to the video surveillance system dispatcher . The first test results give encouraging results — the detectors correctly recognize test situations and give an alarm in a timely manner.

Head of the Department of Computer Technologies and Information Security of the Institute of Artificial Intelligence and Digital Technologies professor Tatyana Hashirova explained:

The applied issues of using artificial intelligence systems considered in this paper directly intersect with the issues of training our specialists. These detectors are operational only if they are used correctly and the parameters are optimally adjusted. In this we are assisted by a direct line with the software developer — the ITV company.

Upon completion of the test work, a decision will be made on the use of certain detectors in the most vulnerable and critically significant areas of the territory to improve the overall level of the university’s integrated security.