Biomedical Engineering Reference
In-Depth Information
Table 2 The results of experiment 2
Generating value
Method
TPR
TNR
FPR
FNR
0.2
DCA
5.91
3.25
3.05
2.85
0.2
DCA-BE
1.65
2.5
2.6
2.69
0.3
DCA
4.27
1.61
1.41
1.21
0.3
DCA-BE
0.08
0.86
0.96
1.05
0.5
DCA
6.03
3.37
3.17
2.97
0.5
DCA-BE
1.76
2.62
2.72
2.81
0.6
DCA
4.27
1.61
1.41
1.21
0.6
DCA-BE
0.08
0.86
0.96
1.05
Table
2
shows the results of experiment 2. From experiment 2 we conclude that
the minimal TPR, TNR, FPR, and FNR are obtained with the help of experiment 2,
we calculate minimal TPR, TNR, FPR, and FNR.
Our method gives better results compared with DCA. With the help of DCA all
the parameters (TPR, TNR, FPR, and FNR) show their maximum values. How-
ever, in general, the method proposed in this paper is effective to detect the
unknown intrusion.
From experiment 2, we conclude that DCA-BE gives better method for the
classification of the data as well as minimum TPR, TNR, FPR, and FNR.
Conclusion and Future Work
This paper compares the two algorithms of Artificial Immune Systems (AIS)
namely, Dendritic Cell Algorithm and Dendritic Cell Algorithm with belief theory.
Integrating the Dendritic Cell Algorithm and Dempster-Belief theory solves the
problem of correlation and Dempster-Belief theory resolves the problem of
unknown and rapidly evolving harmful attacks more efficiently than the DCA.
The simulation results show that the DCA-BE method has improved the correla-
tion factor, minimizing the false +ve and false -ve alarm generation, and increases
the rate of detection of intrusion as compared to the DCA.
However, the feature reduction process of KDD data set takes a large amount of
time. Therefore, in the future work modifying the feature reduction optimization
for the better selection of feature in KDD data set can be attempted.
References
1. Hosseinpour F, Bakar KA, Hardoroudi AH, Kazazi N (2010) Survey on artificial immune
system as a bio-inspired technique for anomaly based intrusion detection systems. In:
International conference on intelligent networking and collaborative systems, pp 158-189
2. Matzinger P (1994) Tolerance, danger and the extended family. Ann Rev Immunol 12:991-
1045
Search WWH ::
Custom Search