一种基于多进化神经网络的分类方法
作者:
基金项目:

Supported by the National Natural Science Foundation of China under Grant No.60273033(国家自然科学基金);the NaturalScience Foundation of Jiangsu Province of China under Grant No.BK2004079(江苏省自然科学基金)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [15]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    分类问题是目前数据挖掘和机器学习领域的重要内容.提出了一种基于多进化神经网络的分类方法CABEN(classification approach based on evolutionary neural networks).利用改进的进化策略和Levenberg-Marquardt方法对多个三层前馈神经网络同时进行训练.训练好各个分类模型以后,将待识别数据分别输入,最后根据绝对多数投票法决定最终分类结果.实验结果表明,该方法可以较好地进行数据分类,而且与传统的神经网络方法以及贝叶斯方法和决策树方法相比,在

    Abstract:

    Classification is important in data mining and machine learning. In this paper, a classification approach based on evolutionary neural networks (CABEN) is presented, which establishes classifiers by a group of three-layer feed-forward neural networks. The neural networks are trained by an improving algorithm synthesizing modified Evolutionary Strategy and Levenberg-Marquardt optimization method. The class label of the identifying data can first be evaluated by each neural network, and the final classification result is obtained according to the absolute-majority-voting rule. Experimental results show that the algorithm CABEN is effective for the classification, and has the better performance in classification precision, stability and fault-tolerance comparing with the traditional neural network methods, Bayesian classifiers and decision trees, especially for the complex classification problems with many classes.

    参考文献
    [1]Han JW, Kamber M. Data Mining: Concepts and Techniques. San Francisco: Morgan Kaufmann Publishers, 2001.
    [2]Theodoridis S, Koutroumbas K. Pattern Recognition. 2nd ed., NewYork: Academic Press, 2003.
    [3]Friedman N, Geiger D, Goldszmidt M. Bayesian network classifiers. Machine Learning, 1997,29(2-3):131-163.
    [4]Shi HB, Wang ZH, Huang HK, Li XJ. A restricted double-level bayesian classification model. Journal of Software, 2004,15(2):193-199 (in Chinese with English abstract). http:∥www.jos.org.cn/1000-9825/15/193.htm
    [5]Quinlan JR. C4.5: Programs for Machine Learning. San Francisco: Morgan Kaufmann Publishers, 1993.1-25.
    [6]Buhrman H, de WolfR. Complexity measures and decision tree complexity: A survey. Theoretical Computer Science, 2002,288(1):2-43.
    [7]Arulampalam G, Bouzerdoum A. A generalized feedforward neural network architecture for classification and regression. Neural Networks, 2003,16(5-6):561-568.
    [8]Wang JG, Shang L, Chen SF, Wang YF. Application of fuzzy classification by evolutionary neural network in incipient fault detection of power transformer. In: Wunsch D, et al., eds. Proc. of the Int'l Joint Conf. on Neural Networks, IJCNN 2004. New York: IEEE Press, 2004. 2279-2283.
    [9]Gupta AK, Greenwood GW. Static task allocation using (μ,λ) evolutionary strategies. Information Sciences, 1996,94(1-4):141-150.
    [10]Guo CH, Tang HW. Global convergence properties of evolution strategies. Mathematica Numerica Sinica, 2001,23(1):105-110 (in Chinese with English abstract).
    [11]Ajith A. Meta learning evolutionary artificial neural networks. Neurocomputing, 2004,56c:1-38.
    [12]Plagianakos VP, Vrahatis MN. Parallel evolutionary training algorithms for "hardware-friendly" neural networks. Natural Computing, 2002,1(2-3):307-322.
    [13]Blake CL, Merz CJ. UCI repository of machine learning databases. 1998. http:∥www.ics.uci.edu/~mlearn/MLRepository.html附中文参考文献:
    [4]石洪波,王志海,黄厚宽,励晓健.一种限定性的双层贝叶斯分类模型.软件学报,2004,15(2):193-199.http:∥www.jos.org.cn/1000-9825/15/193.htm
    [10]郭崇慧,唐焕文.演化策略的全局收敛性.计算数学,2001,23(1):105-110.
    引证文献
引用本文

商琳,王金根,姚望舒,陈世福.一种基于多进化神经网络的分类方法.软件学报,2005,16(9):1577-1583

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2004-08-12
  • 最后修改日期:2005-02-04
文章二维码
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号