Systems, Man, and Cybernetics

 

Home

• [P409] An Intelligent Detection Approach to Multi-Intrusions Based on Hybrid-model Searching Algorithm
  Author(s): Mong-Fong Horng, Wen-Shayng Hsieh, Bo-Chao Chang, Yu-Cheng Lin
  
  

  Abstract
  In this paper, an intelligent detection system for mul-tiple intrusions for smart home is presented. In the de-veloped system, home users equipped with PDAs may lo-cally and remotely receive the alert of home intrusion with captured subject image. There are three key components developed in this system. One is the intrusion image processing (IIP) to recognize the intrusion and extract the intrusion subjects. The second is a hybrid-model searching algorithm to improve the accuracy and computation cost in searching intruding subjects. The thrid is the Universal-Plug-and-Play (UPnP-based) instant messaging (UIM) Through the integrating of the three software component, intelligent intrusion detection is capable of offering a smart home security system. The implementation results show that the presented system at most identify three intruding subjects with at least 80% accuracy better than the previous works.. The presented system demonstrates a smart and automatic solution in comparison with legacy approaches.

  
   

Full Text (PDF)