Biomedical Engineering Reference
In-Depth Information
non-self discrimination. Aickelin [
5
] firstintroduced the theory to solve the
recognition problem in existing AISs. Matzinger [
6
] in 2002 applied the Danger
theory as an alternative approach for self-surrounding high false positive, poor
adaptation, and short self-monitored. Danger Theory is becoming an efficient way
to solve problems such as classifications, and anomaly detections.
They developed a negative selection algorithm (NSA) based on the principles
of self/non-self discrimination in the human immune system [
7
].
This algorithm defines 'self' as normal behavior patterns of a monitored system.
It generates a number of random patterns. If any randomly generated pattern
matches a self-pattern, it fails to become a detector and will be removed. Other-
wise, it becomes a 'detector' and is used to monitor subsequent access patterns.
This algorithm operates on binary string, and adopts R-Contiguous Matching
Function (RCMF) to determine a match degree between antibody and antigen [
5
].
Kim et al. shows that it is costly to only use negative selection. Inspired by
human immune system, an artificial immune system model used for network
intrusion detection has been presented by authors. This two-level (physical level
and logical level) intrusion detection system has a primary part and secondary
selection, and includes three stages: gene library evolution, negative selection, and
clonal selection. These three processes are coordinated across the network to
accommodate an effective intrusion detection system which is distributed, self-
organizing, and lightweight. In 2002, Kim et al. proposed dynamic clonal selection
algorithm. Via the lifecycle mechanism of the immune cells, the detectors identify
the abnormal behavior that was normal in the past.
Algorithm Description
The current intrusion detection system is used to extract the characteristics of
ordinary users' behaviors. Any unmatched behavior orders are considered as
abnormal and would be alarming. The central challenge with computer security is
developing systems which have the ability to differentiate between the normal and
an intrusion which represents potentially harmful activity. A promising solution is
emerging in the form of biologically inspired computing, and in particular, artificial
immune systems (AIS). Both Dendritic Cell Algorithm (DCA) based on Belief
theory and DCA are popular algorithms in the field of artificial immunology.
Dendritic Cell Algorithm
The DCA is a population-based algorithm, designed for tackling anomaly based
detection tasks. It is inspired by functions of natural DCs of the innate immune
system, which form part of the body's first line of defence against invaders.
DCs have the ability to combine a multitude of molecular information and to
Search WWH ::
Custom Search