Ambient intelligence for entry control

  • Authors:
  • Erik Dovgan;Matjaž Gams

  • Affiliations:
  • Jožef Stefan institute, Slovenia;Jožef Stefan institute, Slovenia

  • Venue:
  • ICCOMP'08 Proceedings of the 12th WSEAS international conference on Computers
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Terrorists are an increasing thread in today's world. Access control is an important issue when dealing with this kind of threads. Advanced input sensors based on biometrics and intelligent methods that learn from experience are recently used to recognize terrorists or simply to detect an unusual behavior of regular stuff. We have designed and developed such a system consisting of four independent modules: expert system, micro learning, macro learning and camera. In the experimental set-up, there are four input sensors: a door sensor, an identity card reader, a fingerprint reader and a camera. Each of the four modules produces an explanation that categorizes an event as alarm or normal, and the system proposes the final suggestion with explanation.