基于BP神经网络的自适应伪最近邻分类

被引:13
作者
曾勇
舒欢
胡江平
葛月月
机构
[1] 电子科技大学自动化工程学院
关键词
伪最近邻分类; BP神经网络; 自适应;
D O I
暂无
中图分类号
TP183 [人工神经网络与计算];
学科分类号
摘要
在伪最近邻(PNN)分类算法中,待分类样本点与每一类样本集中各个近邻的距离加权系数都是主观确定的,这就使得算法得不到最优距离加权值。针对这一问题,该文提出一种基于BP神经网络的自适应伪最近邻分类算法。首先通过计算待分类样本点与每一类样本集中各个近邻的距离值,并将其作为BP神经网络的输入。然后根据BP神经网络输入与输出之间的映射来自适应确定相应的距离加权值。最后由BP神经网络的输出值判别样本类别号。实验结果表明,该算法能够自适应地调节距离加权系数,同时还能有效地改善分类准确率。
引用
收藏
页码:2774 / 2779
页数:6
相关论文
共 11 条
  • [1] 一种基于BP神经网络的车牌字符分类识别方法
    杨凡
    赵建民
    朱信忠
    [J]. 计算机科学, 2005, (08) : 192 - 195
  • [2] On the stopping criteria for k -Nearest Neighbor in positive unlabeled time series classification problems[J] . Mabel González,Christoph Bergmeir,Isaac Triguero,Yanet Rodríguez,José M Benítez.Information Sciences . 2016
  • [3] Combining Fourier and lagged k -nearest neighbor imputation for biomedical time series data[J] . Shah Atiqur Rahman,Yuxiao Huang,Jan Claassen,Nathaniel Heintzman,Samantha Kleinberg.Journal of Biomedical Informatics . 2015
  • [4] Accelerating wrapper-based feature selection with K -nearest-neighbor[J] . Aiguo Wang,Ning An,Guilin Chen,Lian Li,Gil Alterovitz.Knowledge-Based Systems . 2015
  • [5] Multisite stochastic weather generation using cluster analysis and k-nearest neighbor time series resampling[J] . Nina Marie Caraway,James Lucian McCreight,Balaji Rajagopalan.Journal of Hydrology . 2014
  • [6] Hubness-aware shared neighbor distances for high-dimensional $$k$$ -nearest neighbor classification[J] . Nenad Toma?ev,Dunja Mladeni?.Knowledge and Information Systems . 2014 (1)
  • [7] Optical character recognition in real environments using neural networks and k-nearest neighbor
    Matei, O.
    Pop, P. C.
    Valean, H.
    [J]. APPLIED INTELLIGENCE, 2013, 39 (04) : 739 - 748
  • [8] A hybrid text classification approach with low dependency on parameter by integrating K-nearest neighbor and support vector machine
    Wan, Chin Heng
    Lee, Lam Hong
    Rajkumar, Rajprasad
    Isa, Dino
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (15) : 11880 - 11888
  • [9] A Novel Weighted Voting for K-Nearest Neighbor Rule
    Gou, Jianping
    Xiong, Taisong
    Kuang, Yin
    [J]. JOURNAL OF COMPUTERS, 2011, 6 (05) : 833 - 840
  • [10] Pseudo nearest neighbor rule for pattern classification[J] . Yong Zeng,Yupu Yang,Liang Zhao.Expert Systems With Applications . 2008 (2)