The implementation and running of physical security systems is costly and potentially hazardous for those employed to patrol areas of interest. From a technial perspective, the physical security problem can be seen as minimising the probability that intruders and other anomalous events will occur unobserved. A robotic solution is proposed using an artificial immune system, traditionally applied to software security, to identify threats and hazards: the dendritic cell algorithm. It is demonstrated that the migration from the software world to the hardware world is achievable for this algorithm and key properties of the resulting system are explored empirically and theoretically. It is found that the algorithm has a hitherto unknown frequency-dependent component, making it ideal for filtering out sensor noise. Weaknesses of the algorithm are also discovered, by mathematically phrasing the signal processing phase as a collection of linear classifiers. It is concluded that traditional machine learning approaches are likely to outperform the implemented system in its current form. However, it is also observed that the algorithm’s inherent filtering characteristics make modification, rather than rejection, the most beneficial course of action. Hybridising the dendritic cell algorithm with more traditional machine learning techniques, through the introduction of a training phase and using a non-linear classification phase is suggested as a possible future direction.
Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:546252 |
Date | January 2010 |
Creators | Oates, Robert Foster |
Publisher | University of Nottingham |
Source Sets | Ethos UK |
Detected Language | English |
Type | Electronic Thesis or Dissertation |
Source | http://eprints.nottingham.ac.uk/11485/ |
Page generated in 0.0018 seconds