该方法能够在高浓缩率的情况下更好地代替样本空间.UCI(University of California
Irvine)数据集的仿真实验证明
与aiNet方法相比
该方法在分类准确率和数据浓缩率上分别高出7.26%和11.16%
而且更稳定、可靠.
Abstract
Based on fuzzy theory and artificial immune network
a new data classification method
named fuzzy artificial immune network classification(FAINC)
is put forward. In order to improve the convergence rate
fuzzy C mean clustering algorithm is employed to provide vaccines(initial population)for artificial immune network. The operators such as clonal selection
network compression
immune maturation and immune memory are explored. According to expanding and compressing the population of the network
a stable antibody network can be acquired. Namely
the antibody network represents the concentrated training data to construct the classificator. The simulation experiments of University of California
Irvine(UCI)data sets validate the higher classification accuracy
Liu Hongyan, Chen Jian, Chen Guoqing. Review of classification algorithms for data mining [J]. Journal of Tsinghua University(Science and Technology), 2002,42(6):727-730.
Chiu Chaochang, Hsu P L. A constraint-based genetic algorithm approach for mining classification rules[J].IEEE Transactions on Systems, Man and Cybernetics,2005,32(2):205-220.
Rustkowski L. Adaptive probabilistic neural networks for pattern classification in time-varying environment [J].Neural Networks,2004,15(4):811-827.
Secker A, Freitas A A, Timmis J. AISEC: an artificial immune system for e-mail classification [C]∥Proceedings of 2003 Congress on Evolutionary Computation. Piscataway, USA: IEEE Press, 2003:131-138.
Du Haifeng, Wang Sun'an. Data enriching based on ART-artificial immune network [J]. Pattern Recognition and Artificial Intelligence, 2001,14(4):401-405.
Fu Dongmei, Zheng Deling. Designing and analysis of an immune controller based on the improvement VARELA immune network model [C]∥Proceedings of the Fourth International Conference on Machine Learning and Cybernetics. Piscataway, USA: IEEE Press, 2005: 1121-1126.
Castro L N, Zuben F J V. An evolutionary immune network for data clustering [C]∥Proceedings of the Sixth Brazilian Symposium on Neural Networks. Piscataway, USA: IEEE Press, 2000:84-89.
D'haeseleer P, Forrest S, Helman P. An immunological approach to change detection: algorithms, analysis and applications [C]∥Proceedings of the 1996 IEEE Symposium on Research in Security and Privacy. Piscataway, USA: IEEE Press, 1996:110-119.
Xie Ming, Du Haifeng, Jiao Licheng. A novel evolutionary fuzzy artificial immune network for data clustering[J]. Computer Science,2004,31(10A):219-223.