In this paper, a thought based AIS is attempted and used. It
solved a simple feature selection problem. In real application,
the problem may be more complex. This paper just chooses one
evaluating method (or index) OIF. Generally, more evaluating
methods are needed to be taken in consideration for satisfaction
result. How to introduce more indexes is an unknown question
needed to be explored.
The clonal rule and the mutate rule have the potential to be
improve, too. Some thought from immune evolution and
Generate algorithm could be referenced (Fogel, 1994). It is
obvious that they can affect the efficiency of the model directly.
This research is base on the immune evolution thought in multi
objective optimization, which is widely researched. But its
application in hyperspectral image is not too many so far. Some
works has been done in this paper, and more works are needed
to deep.
ACKNOWLEDGEMENTS
The authors gratefully acknowledge Lv and Dr. Li for providing
useful suggestion during the experiment and the pretreatment of
hyperion data.
This research was supported by National High-tech R&D
Program of China (863 Program) (2007AA12Z174) and
National Natural Science Foundation of China (40771155).
REFERENCES
Burnet, 1959. The clonal selection theory of acquired immunity.
Vanderbilt University Press. New York, USA.
Chavez, P.S., Berlin, G.L., Sowers, L.B., 1982. Statistical
Method for Selecting Landsat MSS Ratios. Journal of Applied
Photographic Engineering, 8, pp. 23-30.
De Castro, L.N., Jon Timmis, 2002. Artificial Immune Systems:
A New Computational Intelligence Approach PARTl.
De Castro, L.N., Jon Timmis, 2002. An Artificial Immune
Network for Multimodal Function Optimization. Evolutionary
Computation, pp. 12-17.
Fogel, D.B., 1994. Applying evolutionary programming to
selected control problems. Computers & Mathematics with
Applications, 27(11), pp. 89-104.
Jeme, N.K., 1974. Towards a network theory of the immune
system. Annual Immunology, 125(C), pp. 373-389.
Li, C.H., Mao, Z.Y., 2005. Multiobjetive Optimization Based
on Artificial. Immune Algorithm. Computer Automated
Measurement & Control, 13(3), pp. 278-280.
Matzinger, P., 2001. The danger Model in its historical context.
Scandinavian Journal of Immunology.
Qi, A.S., Du, C.Y., 1998, Nonlinearmodels in immunity.
Shanghai: Shanghai Scientific and Technological Education
Publishing House.
Swain, P.H., Davis, S.M., 1987. Remote Sensing: The
Quantitative Approach. McGraw-hill International Book
Company.
Timmis, J., Knight, T., 2001. Artificial immunes system: Using
the immune system as inspiration for data mining. In: Abbass
HA, Sarker R A, Newton C S eds. Data Mining: A Heuristic
Approach. Hershey: Idea Publishing Group, pp. 209-230.
Zhang, L.P., Zhong, Y.F., Huang, B. and Li, P.X., 2007. A
Resource Limited Artificial Immune Algorithm for Supervised
Classification of Multi/Hyperspectral. Remote Sensing Image.
International Journal of Remote Sensing, 28(7), pp. 1665-1686.
Zhang, L.P., Zhong, Y.F., Huang, B., Gong J.Y and Li, P.X.,
2007. Dimensionality Reduction Based on Clonal Selection for
Hyperspectral Satellite Imagery. IEEE Transactions on
Geoscience and Remote Sensing.
Zhai, Y.S., Cheng, Z.H., 2006. Multi-objective Optimization
Immune Algorithm Based on Pareto. Computer Engineering
and Applications, pp. 27-29.
Zhong, Y.F., Zhang, L.P., Huang, B. and Li, P.X., 2006. An
unsupervised artificial immune classifier for multi/hyperspectral
remote sensing imagery. IEEE Transactions on Geoscience and
Remote Sensing, 44(2), pp. 420-431.
Zitzler, E., Thiele, L., 1999. Multiobjective evolutionary
algorithms: a comparative case study and the strength pareto
approach. IEEE Transactions on Evolutionary Computation,
3(4).
345
