Geometrical insights into the dendritic cell algorithm

ABSTRACT

This work examines the dendritic cell algorithm (DCA) from a mathematical perspective. By representing the signal processing phase of the algorithm using the dot product it is shown that the signal processing element of the DCA is actually a collection of linear classifiers. It is further shown that the decision boundaries of these classifiers have the potentially serious drawback of being parallel, severely limiting the applications for which the existing algorithm can be potentially used on. These ideas are further explored using artificially generated data and a novel visualisation technique that allows an entire population of dendritic cells to be inspected as a single classifier. The paper concludes that the applicability of the DCA to more complex problems is highly limited.

REFERENCES

• 1: Y. Al-Hammadi, U. Aickelin, and J. Greensmith. Dca for bot detection. In Proceedings of the IEEE World Congress on Computational Intelligence (WCCI) Hong Kong, pages 1807--1816, 2008.
• 2: Christopher M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, Inc., New York, NY, 1995
• 3: J. Greensmith. The Dendritic Cell Algorithm. PhD thesis, The University of Nottingham, Computer Science, Jubilee Campus, Wollaton Road, Nottingham, NG8 1BB, 2007.
• 4: Julie Greensmith , Uwe Aickelin, The Deterministic Dendritic Cell Algorithm, Proceedings of the 7th international conference on Artificial Immune Systems, August 10-13, 2008, Phuket, Tailand [doi>10.1007/978-3-540-85072-4_26]
• 5: J. Greensmith, U. Aickelin, and J. Twycross. Articulation and clarification of the dendric cell algorithm. In Proceedings of the 5th International Conference on Artificial Immune Systems (ICARIS 2006), pages 404--417, 2006.
• 6: J. Greensmith, J. Feyereisl, and U. Aickelin. The dca: Some comparison: a comparative study between two biologically-inspired algorithms. Evolutionary Intelligence, 1(2):85--112, June 2008.
• 7: T. S. Guzella , T. A. Mota-Santos , W. M. Caminhas, Artificial Immune Systems and Kernel Methods, Proceedings of the 7th international conference on Artificial Immune Systems, August 10-13, 2008, Phuket, Tailand [doi>10.1007/978-3-540-85072-4_27]
• 8: Ralf Herbrich, Learning Kernel Classifiers: Theory and Algorithms, MIT Press, Cambridge, MA, 2001
• 9: G. James. Modern Engineering Mathematics. Pearson Education Limited, 4th edition, 2008.
• 10: P. Matzinger. Tolerance, danger, and the extended family. Annual Review of Immunology, 12(1):991--1045, 1994.
• 11: P. Matzinger. Friendly and dangerous signals: is the tissue in control? Nature Immunology, 8(1):11--13, 2007.
• 12: R. Oates, G. Kendall, and J. Garibaldi. Frequency analysis for dendritic cell population tuning. Evolutionary Intelligence, 1(2):145--157, June 2008.
• 13: Robert Oates , Graham Kendall , Jonathan M. Garibaldi, The Limitations of Frequency Analysis for Dendritic Cell Population Modelling, Proceedings of the 7th international conference on Artificial Immune Systems, August 10-13, 2008, Phuket, Tailand [doi>10.1007/978-3-540-85072-4_29]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.m MISCELLANEOUS

General Terms:
Algorithms

Keywords:
analysis, artificial immune systems, classifiers, dendritic cell algorithm